-1-1012345678910
Monday 22nd November : Oral Session 1: Multimodal Learning
0
[930]
Audio-Visual Speech Super-Resolution
Rudrabha Mukhopadhyay, Sindhu B Hegde, Vinay Namboodiri and C.V. Jawahar
Paper  Supplemental  Code  Oral Session 1  Poster Session 1
1
[1098]
Geometry-Aware Multi-Task Learning for Binaural Audio Generation from Video
Rishabh Garg, Ruohan Gao and Kristen Grauman
Paper  Supplemental  Oral Session 1  Poster Session 1
2
[1213]
Taming Visually Guided Sound Generation
Vladimir Iashin and Esa Rahtu
Paper  Supplemental  Code  Oral Session 1  Poster Session 1
3
[1577]
Deep Least Squares Alignment for Unsupervised Domain Adaptation
Youshan Zhang and Brian D. Davison
Paper  Supplemental  Code  Oral Session 1  Poster Session 1
4
[353]
Domain Attention Consistency for Multi-Source Domain Adaptation
Zhongying Deng, Kaiyang Zhou, Yongxin Yang and Tao Xiang
Paper  Supplemental  Code  Oral Session 1  Poster Session 1
Monday 22nd November : Oral Session 2: 3D
5
[762]
Collision Replay: What Does Bumping Into Things Tell You About Scene Geometry?
Alexander Raistrick, Nilesh Kulkarni and David Fouhey
Paper  Supplemental  Oral Session 2  Poster Session 1
6
[195]
Towards Monocular Shape from Refraction
Antonin Sulc, Imari Sato, Bastian Goldluecke and Tali Treibitz
Paper  Supplemental  Code  Oral Session 2  Poster Session 1
7
[443]
Self-Supervised Point Cloud Completion via Inpainting
Himangi Mittal, Brian Okorn, Arpit Jangid and David Held
Paper  Supplemental  Oral Session 2  Poster Session 1
8
[718]
Adaptive GMM Convolution for Point Cloud Learning
Fei Yang, Huan Wang and Zhong Jin
Paper  Supplemental  Code  Oral Session 2  Poster Session 1
9
[1127]
Learning Attention Map for 3D Human Recovery from a Single RGB Image
Peng Xu, Na Jiang, Jun Li and Zhiping Shi
Paper  Supplemental  Oral Session 2  Poster Session 1
Monday 22nd November : Poster Session 1
10
[5]
Foreground Mining via Contrastive Guidance for Weakly Supervised Object Localization
Wonyoung Lee, Minsong Ki, Cheolhyun Mun, Sungpil Kho and Hyeran Byun
Paper  Supplemental  Code  Poster Session 1
11
[12]
Learning to Hide Residual for Boosting Image Compression
Yi-Lun Lee, Yen-Chung Chen, Min-Yuan Tseng, Yi-Hsuan Tsai and Wei-Chen Chiu
Paper  Supplemental  Poster Session 1
12
[38]
Learning Exposure Correction Via Consistency Modeling
Ntumba Elie Nsampi, Zhongyun Hu and Qing Wang
Paper  Supplemental  Code  Poster Session 1
13
[43]
Approaching the Limit of Image Rescaling via Flow Guidance
Shang Li, GuiXuan Zhang, Zhengxiong Luo, Jie Liu, Zhi Zeng and ShuWu Zhang
Paper  Poster Session 1
14
[59]
Gradient Frequency Modulation for Visually Explaining Video Understanding Models
Xin Miao Lin, Wentao Bao, Matthew Wright and Yu Kong
Paper  Supplemental  Poster Session 1
15
[69]
Semi-Supervised Raw-to-Raw Mapping
Mahmoud Afifi and Abdullah Abuolaim
Paper  Poster Session 1
16
[85]
Crafting Object Detection in Very Low Light
Yang Hong, Kaixuan Wei, Linwei Chen and Ying Fu
Paper  Supplemental  Code  Poster Session 1
17
[108]
Feature Space Saturation during Training
Mats L Richter, Justin C Shenk, Wolf Byttner, Anna Wiedenroth and Mikael Huss
Paper  Supplemental  Code  Poster Session 1
18
[121]
Adaptive End-to-End Budgeted Network Learning via Inverse Scale Space
Zuyuan Zhong, Chen Liu and Yanwei Fu
Paper  Supplemental  Poster Session 1
19
[145]
Median Pixel Difference Convolutional Network for Robust Face Recognition
Jiehua Zhang, Zhuo Su and Li Liu
Paper  Supplemental  Poster Session 1
20
[149]
Recurrence-in-Recurrence Networks for Video Deblurring
JoonKyu Park, Seungjun Nah and Kyoung Mu Lee
Paper  Supplemental  Code  Poster Session 1
21
[193]
Learning Synergistic Attention for Light Field Salient Object Detection
Yi Zhang, Geng Chen, Qian Chen, Yujia Sun, Yong Xia, Olivier DEFORGES, Wassim Hamidouche and Lu Zhang
Paper  Supplemental  Code  Poster Session 1
22
[197]
Does a GAN leave distinct model-specific fingerprints?
Yuzhen Ding, Nupur Thakur and baoxin Li
Paper  Supplemental  Poster Session 1
23
[212]
Make Baseline Model Stronger: Embedded Knowledge Distillation in Weight-Sharing Based Ensemble Network
Shuchang LYU, Qi Zhao, Yujing Ma and Lijiang Chen
Paper  Supplemental  Poster Session 1
24
[219]
FAR: A General Framework for Attributional Robustness
Adam Ivankay, Ivan Girardi, Chiara Marchiori and Pascal Frossard
Paper  Supplemental  Poster Session 1
25
[255]
Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs
Philipp Benz, Soomin Ham, Chaoning Zhang, Adil Karjauv and In So Kweon
Paper  Code  Poster Session 1
26
[259]
PDF-Distil: including Prediction Disagreements in Feature-based Distillation for object detection
Heng ZHANG, Elisa Fromont, Sébastien Lefèvre and Bruno AVIGNON
Paper  Code  Poster Session 1
27
[263]
PhIT-Net: Photo-consistent Image Transform for Robust Illumination Invariant Matching
Damian Kaliroff and Guy Gilboa
Paper  Supplemental  Code  Poster Session 1
28
[287]
Absolute Scale from Varifocal Monocular Camera through SfM and Defocus Combined
Nao Mishima, Akihito Seki and Shinsaku Hiura
Paper  Poster Session 1
29
[316]
Deep Motion Blind Video Stabilization
Muhammad Kashif Ali, Sangjoon Yu and Tae Hyun Kim
Paper  Supplemental  Code  Poster Session 1
30
[319]
PS-Transformer: Learning Sparse Photometric Stereo Network using Self-Attention Mechanism
Satoshi Ikehata
Paper  Supplemental  Poster Session 1
31
[365]
MUSE: Feature Self-Distillation with Mutual Information and Self-Information
Yu Gong, Ye Yu, Gaurav Mittal, Greg Mori and Mei Chen
Paper  Supplemental  Poster Session 1
32
[374]
Updated Paired Regions for Shadow Detection from Single Image
Xiao Wang, Siyuan Yao, Pengwen Dai, Rui Wang (State Key Laboratory of Information Security, Institute of Information Engineering, Chinese Academy of Sciences, School of Cyber Security, University of Chinese Academy of Sciences) and Xiaochun Cao
Paper  Supplemental  Poster Session 1
33
[382]
Semi-Online Knowledge Distillation
Zhiqiang Liu, Yanxia Liu and Chengkai Huang
Paper  Code  Poster Session 1
34
[387]
SamplingAug: On the Importance of Patch Sampling Augmentation for Single Image Super-Resolution
Shizun Wang, Ming Lu, Kaixin Chen, Jiaming Liu, Xiaoqi Li, Chuang Zhang and Ming Wu
Paper  Supplemental  Code  Poster Session 1
35
[398]
Deep Video Inpainting Detection
Peng Zhou, Ning Yu, Zuxuan Wu, Larry Davis, Abhinav Shrivastava and Ser-Nam Lim
Paper  Supplemental  Code  Poster Session 1
36
[407]
POEM: 1-bit Point-wise Operations based on Expectation-Maximization for Efficient Point Cloud Processing
Sheng Xu, Junhe Zhao, Yanjing Li, Baochang Zhang and Guodong Guo
Paper  Supplemental  Poster Session 1
37
[415]
One-Step Pixel-Level Perturbation-Based Saliency Detector
Vinnam Kim, Hyunsouk Cho and Sehee Chung
Paper  Supplemental  Code  Poster Session 1
38
[424]
Rethinking Clustering for Robustness
Motasem Alfarra, Juan C Perez (Universidad de los Andes, King Abdullah University of Science and Technology), Adel Bibi, Ali K Thabet, Pablo Arbelaez and Bernard Ghanem
Paper  Supplemental  Code  Poster Session 1
39
[466]
Inter-intra Variant Dual Representations for Self-supervised Video Recognition
Lin ZHANG, Qi She, Zhengyang Shen and Changhu Wang
Paper  Supplemental  Code  Poster Session 1
40
[491]
ContourletNet: A Generalized Rain Removal Architecture Using Multi-Direction Representation and Hierarchical Decomposition
Wei-Ting Chen, Cheng-Che Tsai, Hao-Yu Fang, I-HSIANG CHEN, Jian-Jiun Ding and Sy-Yen Kuo
Paper  Supplemental  Code  Poster Session 1
41
[510]
X-Distill: Improving Self-Supervised Monocular Depth via Cross-Task Distillation
Hong Cai, Janarbek Matai, Shubhankar Borse, Yizhe Zhang, Amin Ansari and Fatih Porikli
Paper  Supplemental  Poster Session 1
42
[524]
Multiple Fusion Adaptation: A Strong Framework for Unsupervised Semantic Segmentation Adaptation
Kai Zhang, Yifan Sun, Rui Wang, Haichang Li and Xiaohui Hu
Paper  Supplemental  Poster Session 1
43
[570]
ECINN: Efficient Counterfactuals from Invertible Neural Networks
Frederik Hvilshøj, Alexandros Iosifidis and Ira Assent
Paper  Supplemental  Code  Poster Session 1
44
[590]
Progressive Growing of Points with Tree-structured Generators
Hyeontae Son and Young Min Kim
Paper  Supplemental  Code  Poster Session 1
45
[619]
Learning Neural Transmittance for Efficient Rendering of Reflectance Fields
Mohammad Shafiei, Sai Bi, Zhengqin Li, Aidas Liaudanskas, Rodrigo J Ortiz Cayon and Ravi Ramamoorthi
Paper  Supplemental  Poster Session 1
46
[625]
Intrinsic Examples: Robust Fingerprinting of Deep Neural Networks
Siyue Wang, Pu Zhao, Xiao Wang, Sang Chin, Thomas Wahl, Yunsi Fei, Qi Alfred Chen and Xue Lin
Paper  Supplemental  Poster Session 1
47
[637]
Edge-aware Bidirectional Diffusion for Dense Depth Estimation from Light Fields
Numair Khan, Min H. Kim and James Tompkin
Paper  Supplemental  Code  Poster Session 1
48
[642]
ZeBRA: Precisely Destroying Neural Networks with Zero-Data Based Repeated Bit Flip Attack
Dahoon Park, Kon-Woo Kwon, Sunghoon Im and Jaeha Kung
Paper  Supplemental  Code  Poster Session 1
49
[678]
Enhancing Local Feature Learning for 3D Point Cloud Processing using Unary-Pairwise Attention
Haoyi Xiu, Xin Liu, Weimin Wang, Kyoung-Sook Kim, Takayuki Shinohara, Qiong Chang and Masashi Matsuoka
Paper  Supplemental  Poster Session 1
50
[697]
Deep Image Matting with Flexible Guidance Input
Hang Cheng, Shugong Xu, Xiufeng Jiang and Rongrong Wang
Paper  Code  Poster Session 1
51
[732]
Spatial Aggregation for Scene Text Recognition
Yili Huang, Chengyu Gu, Shilin Wang, Zheng Huang and Kai Chen
Paper  Poster Session 1
52
[747]
SIR-SRGAN: Super-Resolution Generative Adversarial Networks with Self-Interpolation Ranker
Jun-Hong Huang, Hai-Kun Wang and Zhi-Wu Liao
Paper  Supplemental  Code  Poster Session 1
53
[753]
A Mixed Quantization Network for Efficient Mobile Inverse Tone Mapping
Juan Borrego-Carazo, Mete Ozay, Frederik Laboyrie and Paul Wisbey
Paper  Supplemental  Code  Poster Session 1
54
[756]
Simpler Does It: Generating Semantic Labels with Objectness Guidance
Md Amirul Islam, Matthew Kowal, Sen Jia, Konstantinos Derpanis and Neil Bruce
Paper  Supplemental  Poster Session 1
55
[766]
AMICO: Amodal Instance Composition
Peiye Zhuang, Denis Demandolx, Ayush Saraf, Xuejian Rong, Changil Kim and Jia-Bin Huang
Paper  Supplemental  Poster Session 1
56
[778]
Noisy Annotation Refinement for Object Detection
Jiafeng Mao, Qing Yu, Yoko Yamakata and Kiyoharu Aizawa
Paper  Supplemental  Poster Session 1
57
[813]
Quality Level Prediction of Image Compression using Block-wise Confidence-aware CNN
Kyuwon Kim and Chulju Yang
Paper  Supplemental  Poster Session 1
58
[831]
Teacher-Class Network: A Neural Network Compression Mechanism
Shaiq Munir Malik, Fnu Mohbat, Muhammad Umair Haider, Muhammad Musab Rasheed and Murtaza Taj
Paper  Code  Poster Session 1
59
[835]
UWC: Unit-wise Calibration Towards Rapid Network Compression
Chen Lin, Zheyang Li, Bo Peng, Wenming Tan, Ye Ren and Shiliang Pu
Paper  Poster Session 1
60
[848]
Hardware-Aware Mixed-Precision Neural Networks using In-Train Quantization
Manoj Rohit Vemparala, Nael Fasfous, Lukas Frickenstein, Alexander Frickenstein, Anmol Singh, Driton Salihu, Christian Unger, Naveen Shankar Nagaraja and WALTER STECHELE
Paper  Supplemental  Poster Session 1
61
[871]
Multi-bit Adaptive Distillation for Binary Neural Networks
Ying Nie, Kai Han and Yunhe Wang
Paper  Supplemental  Poster Session 1
62
[875]
Multi-scale Residual Aggregation Deraining Network with Spatial Context-aware Pooling and Activation
Kohei Yamamichi and Xian-Hua Han
Paper  Supplemental  Poster Session 1
63
[894]
Global Context and Geometric Priors for Effective Non-Local Self-Attention
Sanghyun Woo, Dahun Kim, Joon-Young Lee and In So Kweon
Paper  Supplemental  Poster Session 1
64
[904]
LUCES: A Dataset for Near-Field Point Light Source Photometric Stereo
Roberto Mecca, Fotios Logothetis, Ignas Budvytis and Roberto Cipolla
Paper  Supplemental  Code  Poster Session 1
65
[906]
Beyond Classification: Knowledge Distillation using Multi-Object Impressions
Gaurav Kumar Nayak, Monish K Keswani, Sharan Seshadri and Anirban Chakraborty
Paper  Supplemental  Poster Session 1
66
[945]
Rethinking local and global feature representation for semantic segmentation
Mohan Chen, Xinxuan Zhao, Bingfei Fu, Li Zhang and Xiangyang Xue
Paper  Supplemental  Poster Session 1
67
[959]
Faster-FCoViAR: Faster Frequency-Domain Compressed Video Action Recognition
Lu Xiong, Xia Jia, Yue Ming, Jiangwan Zhou, Fan Feng and Nan nan Hu
Paper  Poster Session 1
68
[979]
Training Object Detectors if Only Large Objects are Labeled
Daniel Pototzky, Matthias MK Kirschner, Azhar Sultan and Lars Schmidt-Thieme
Paper  Supplemental  Code  Poster Session 1
69
[1014]
TinyStarGAN v2: Distilling StarGAN v2 for Efficient Diverse Image Synthesis for Multiple Domains
PARAS KAPOOR and Tien D. Bui
Paper  Supplemental  Code  Poster Session 1
70
[1020]
SAGAN: Adversarial Spatial-asymmetric Attention for Noisy Nona-Bayer Reconstruction
S M A Sharif, Rizwan Ali Naqvi and Mithun Biswas
Paper  Supplemental  Code  Poster Session 1
71
[1022]
Robustness Learning via Decision Tree Search Robust Optimisation
Yi-Ling Liu and Alessio Lomuscio
Paper  Supplemental  Poster Session 1
72
[1054]
Deep Knowledge Distillation using Trainable Dense Attention
Bharat Sau, Soumya Roy, Vinay P Namboodiri and Raghu Sesha Iyengar
Paper  Supplemental  Poster Session 1
73
[1075]
Contour-guided Image Completion with Perceptual Grouping
Morteza Rezanejad, Sidharth Gupta, Chandra Gummaluru, Ryan Marten, John Wilder, Michael Gruninger and Dirk B. Walther
Paper  Supplemental  Code  Poster Session 1
74
[1077]
C4Net: Contextual Compression and Complementary Combination Network for Salient Object Detection
Hazarapet Tunanyan
Paper  Supplemental  Poster Session 1
75
[1093]
Noise-Aware Video Saliency Prediction
Ekta Prashnani, Orazio Gallo, Joohwan Kim, Josef Spjut, Pradeep Sen and Iuri Frosio
Paper  Supplemental  Code  Poster Session 1
76
[1126]
NOD: Taking a Closer Look at Detection under Extreme Low-Light Conditions with Night Object Detection Dataset
Igor Morawski, Yu-An Chen, Yu-Sheng Lin and Winston H. Hsu
Paper  Supplemental  Code  Poster Session 1
77
[1137]
Regression as a Simple Yet Effective Tool for Self-supervised Knowledge Distillation
K L Navaneet, Soroush Abbasi Koohpayegani, Ajinkya B Tejankar and Hamed Pirsiavash
Paper  Supplemental  Code  Poster Session 1
78
[1142]
In-N-Out: Towards Good Initialization for Inpainting and Outpainting
Changho Jo, Woobin Im and Sungeui Yoon
Paper  Supplemental  Code  Poster Session 1
79
[1193]
Object Re-identification Using Teacher-Like and Light Students
Yi Xie, Hanxiao Wu, Fei Shen, Jianqing Zhu and Huanqiang Zeng
Paper  Poster Session 1
80
[1206]
From Under- to Overexposure: Single Image Contrast Enhancement via Semi-Supervised Learning
Ziwen Li, Yuehuan Wang and RuoWang Chang
Paper  Poster Session 1
81
[1225]
Multi-Exit Vision Transformer for Dynamic Inference
Arian Bakhtiarnia, Qi Zhang and Alexandros Iosifidis
Paper  Code  Poster Session 1
82
[1238]
SILT: Self-supervised Lighting Transfer Using Implicit Image Decomposition
Nikolina Kubiak, Armin Mustafa, Graeme Phillipson, Stephen Jolly and Simon Hadfield
Paper  Supplemental  Code  Poster Session 1
83
[1240]
Efficient Video Super Resolution by Gated Local Self Attention
Davide Abati, Amir Ghodrati and Amirhossein Habibian
Paper  Supplemental  Poster Session 1
84
[1244]
Microdosing: Knowledge Distillation for GAN Based Compression
Leonhard Helminger, Roberto Azevedo, Abdelaziz Djelouah, Markus Gross and Christopher Schroers
Paper  Supplemental  Poster Session 1
85
[1267]
Reference Guided Image Inpainting using Facial Attributes
Dongsik Yoon, Youngsaeng Jin, Jeong-gi Kwak, Yuanming Li, David K Han and Hanseok Ko
Paper  Supplemental  Poster Session 1
86
[1269]
Conditional De-Identification of 3D Magnetic Resonance Images
Lennart Alexander Van der Goten, Tobias Hepp, Zeynep Akata and Kevin Smith
Paper  Supplemental  Poster Session 1
87
[1283]
M-CAM: Visual Explanation of Challenging Conditioned Dataset with Bias-reducing Memory
Seongyeop Kim and Yong Man Ro
Paper  Supplemental  Poster Session 1
88
[1305]
A Design of Contractive Appearance Flow for Photometric Stereo
Lixiong Chen and Victor Adrian Prisacariu
Paper  Supplemental  Poster Session 1
89
[1342]
One Model to Reconstruct Them All: A Novel Way to Use the Stochastic Noise in StyleGAN
Christian Bartz, Joseph Bethge, Haojin Yang and Meinel Christoph
Paper  Supplemental  Code  Poster Session 1
90
[1349]
IamAlpha: Instant and Adaptive Mobile Network for Alpha Matting
Avinav Goel, Manoj Kumar and Pavan Sudheendra
Paper  Poster Session 1
91
[1371]
An Adaptive Rectification Model for Arbitrary-Shaped Scene Text Recognition
Ye Qian, Long Chen and Feng Su
Paper  Supplemental  Poster Session 1
92
[1381]
CamLessMonoDepth: Monocular Depth Estimation with Unknown Camera Parameters
Sai Shyam Chanduri, Igor Vozniak and Zeeshan Khan Suri
Paper  Supplemental  Poster Session 1
93
[1394]
MAGECally invert images for realistic editing
Asya Grechka, jean Francois Goudou and Matthieu Cord
Paper  Supplemental  Poster Session 1
94
[1395]
GhostShiftAddNet: More Features from Energy-Efficient Operations
Jia Bi, Jonathon Hare and Geoff V Merrett
Paper  Code  Poster Session 1
95
[1406]
Lightweight HDR Camera ISP for Robust Perception in Dynamic Illumination Conditions via Fourier Adversarial Networks
Pranjay Shyam, Sandeep Singh Sengar, Kuk-Jin Yoon and Kyung-Soo Kim
Paper  Supplemental  Poster Session 1
96
[1443]
Adverse Weather Image Translation with Asymmetric and Uncertainty-aware GAN
Jeong-gi Kwak, Youngsaeng Jin, Yuanming Li, Dongsik Yoon, Donghyeon Kim and Hanseok Ko
Paper  Supplemental  Poster Session 1
97
[1447]
Deep Degradation Prior for Real-World Super-Resolution
Kyungdeuk Ko, Bokyeung Lee, Jonghwan Hong, David K Han and Hanseok Ko
Paper  Supplemental  Poster Session 1
98
[1481]
From Seq2Seq Recognition to Handwritten Word Embeddings
George Retsinas, Giorgos Sfikas, Christophoros Nikou and Petros Maragos
Paper  Supplemental  Code  Poster Session 1
99
[1482]
Skeleton-aware Text Image Super-Resolution
Shimon Nakaune, Satoshi Iizuka and Kazuhiro Fukui
Paper  Poster Session 1
100
[1528]
Adaptive Distillation: Aggregating Knowledge from Multiple Paths for Efficient Distillation
Sumanth Chennupati, Mohammad Mahdi Kamani, Zhongwei Cheng and Lin Chen
Paper  Supplemental  Poster Session 1
101
[1529]
Sparse Adversarial Video Attacks with Spatial Transformations
Ronghui Mu, Wenjie Ruan, Leandro Soriano Marcolino and Qiang Ni
Paper  Supplemental  Code  Poster Session 1
102
[1544]
Corrosion Image Data Set for Automating Scientific Assessment of Materials
Biao Yin, Nicholas Josselyn, Thomas Considine, John Kelley, Berend Rinderspacher, Robert Jensen, James F Snyder, Ziming Zhang and Elke A Rundensteiner
Paper  Supplemental  Code  Poster Session 1
103
[1550]
Unsupervised computation of salient motion maps from the interpretation of a frame-based classification network
Etienne Meunier and Patrick Bouthemy
Paper  Supplemental  Poster Session 1
104
[1564]
Robust channel-wise illumination estimation
Firas Laakom, Jenni Raitoharju, Jarno Nikkanen, Alexandros Iosifidis and Moncef Gabbouj
Paper  Poster Session 1
105
[1594]
Perception Visualization: Seeing Through The Eyes Of a DNN
Loris Giulivi, Mark Carman and Giacomo Boracchi
Paper  Supplemental  Code  Poster Session 1
106
[1603]
Mitigating Reverse Engineering Attacks on Local Feature Descriptors
Deeksha Dangwal, Vincent T Lee, Hyo Jin Kim, Tianwei Shen, Meghan Cowan, Rajvi Shah, Caroline Trippel, Brandon Reagen, Timothy Sherwood, Vasileios Balntas, Armin Alaghi and Eddy Ilg
Paper  Supplemental  Poster Session 1
107
[1631]
Parameter Efficient Dynamic Convolution via Tensor Decomposition
Zejiang Hou and Sun-Yuan Kung
Paper  Supplemental  Poster Session 1
108
[1633]
Self-Validation: Early Stopping for Single-Instance Deep Generative Priors
Taihui Li, Zhong Zhuang, Hengyue Liang, Le Peng, Hengkang Wang and Ju Sun
Paper  Supplemental  Code  Poster Session 1
Tuesday 23rd November : Oral Session 3: Action Recognition
109
[807]
Hierarchical Contrastive Motion Learning for Video Action Recognition
Xitong Yang, Xiaodong Yang, Sifei Liu, Deqing Sun, Larry Davis and Jan Kautz
Paper  Supplemental  Oral Session 3  Poster Session 2
110
[974]
Revisiting spatio-temporal layouts for compositional action recognition
Gorjan Radevski, Marie-Francine Moens and Tinne Tuytelaars
Paper  Supplemental  Code  Oral Session 3  Poster Session 2
111
[1095]
AEI: Actors-Environment Interaction with Adaptive Attention for Temporal Action Proposals Generation
Khoa HV Vo, Hyekang Joo, Kashu Yamazaki, Sang Q Truong, Kris Kitani, Minh-Triet Tran and Ngan Le
Paper  Supplemental  Code  Oral Session 3  Poster Session 2
112
[842]
Unsupervised Human Action Recognition with Skeletal Graph Laplacian and Self-Supervised Viewpoints Invariance
Giancarlo Paoletti, Jacopo Cavazza, Cigdem Beyan and Alessio Del Bue
Paper  Supplemental  Code  Oral Session 3  Poster Session 2
113
[14]
UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition
Di Yang, Yaohui Wang, Antitza Dantcheva, Lorenzo Garattoni, Gianpiero Francesca and Francois Bremond
Paper  Supplemental  Code  Oral Session 3  Poster Session 2
Tuesday 23rd November : Oral Session 4: Recognition
114
[473]
Lane Line Detection based on Parallel Spatial Separation Convolution
Xile Shen, Zongqing Lu, Youcheng Zhang and Jing-Hao Xue
Paper  Oral Session 4  Poster Session 2
115
[1087]
Holistic Guidance for Occluded Person Re-Identification
Madhu Kiran, Gnana Praveen Rajasekhar, Le Thanh Nguyen-Meidine, Soufiane Belharbi, Louis-Antoine Blais-Morin and Eric Granger
Paper  Supplemental  Code  Oral Session 4  Poster Session 2
116
[1497]
MMD-ReID: A Simple but Effective Solution for Visible-Thermal Person ReID
Chaitra S Jambigi, Ruchit Rawal and Anirban Chakraborty
Paper  Supplemental  Code  Oral Session 4  Poster Session 2
117
[229]
The Curious Layperson: Fine-Grained Image Recognition without Expert Labels
Subhabrata Choudhury, Iro Laina, Christian Rupprecht and Andrea Vedaldi
Paper  Supplemental  Code  Oral Session 4  Poster Session 2
118
[1506]
Grid Cell Path Integration For Movement-Based Visual Object Recognition
Niels Leadholm, Marcus Lewis and Subutai Ahmad
Paper  Supplemental  Code  Oral Session 4  Poster Session 2
Tuesday 23rd November : Poster Session 2
119
[8]
HCV: Hierarchy-Consistency Verification for Incremental Implicitly-Refined Classification
Kai Wang, Xialei Liu, Luis Herranz and Joost van de Weijer
Paper  Supplemental  Code  Poster Session 2
120
[51]
SuperStyleNet: Deep Image Synthesis with Superpixel Based Style Encoder
Jonghyun Kim, Gen Li, Cheolkon Jung and Joongkyu Kim
Paper  Supplemental  Code  Poster Session 2
121
[63]
UBR²S: Uncertainty-Based Resampling and Reweighting Strategy for Unsupervised Domain Adaptation
Tobias Ringwald and Rainer Stiefelhagen
Paper  Supplemental  Code  Poster Session 2
122
[68]
Repaint: Improving the Generalization of Down-Stream Visual Tasks by Generating Multiple Instances of Training Examples
Amin Banitalebi-Dehkordi and Yong Zhang
Paper  Supplemental  Poster Session 2
123
[84]
Leveraging Class Hierarchies with Metric-Guided Prototype Learning
Vivien Sainte Fare Garnot and Loic Landrieu
Paper  Supplemental  Code  Poster Session 2
124
[94]
Measuring the Biases and Effectiveness of Content-Style Disentanglement
Xiao Liu, Spyridon Thermos, Gabriele Valvano, Agisilaos Chartsias, Alison Q O'Neil and Sotirios Tsaftaris
Paper  Supplemental  Code  Poster Session 2
125
[113]
Multi-Teacher Single-Student Visual Transformer with Multi-Level Attention for Face Spoofing Detection
Yao-Hui Huang, Jun-Wei Hsieh, Ming-Ching Chang, Lipeng Ke, Siwei Lyu and Arpita Samanta Santra
Paper  Supplemental  Poster Session 2
126
[119]
A Strong Baseline for Semi-Supervised Incremental Few-Shot Learning
Linglan Zhao, Dashan Guo, Yunlu Xu, Liang Qiao, Zhanzhan Cheng, Shiliang Pu, Yi Niu and Xiangzhong Fang
Paper  Supplemental  Poster Session 2
127
[138]
Single-Modal Entropy based Active Learning for Visual Question Answering
Dong-Jin Kim, Jae Won Cho, Jinsoo Choi, Yunjae Jung and In So Kweon
Paper  Supplemental  Poster Session 2
128
[142]
Alleviating Noisy-label Effects in Image Classification via Probability Transition Matrix
Ziqi Zhang, Yuexiang Li, Hongxin Wei, Kai Ma, Tao Xu and Yefeng Zheng
Paper  Poster Session 2
129
[158]
Semi-Supervised Learning with Taxonomic Labels
Jong-Chyi Su and Subhransu Maji
Paper  Code  Poster Session 2
130
[180]
Feature and Label Embedding Spaces Matter in Addressing Image Classifier Bias
William Thong and Cees Snoek
Paper  Supplemental  Code  Poster Session 2
131
[181]
Defensive Tensorization
Adrian Bulat, Jean Kossaifi, Sourav Bhattacharya, Yannis Panagakis, Timothy Hospedales, Georgios Tzimiropoulos, Nicholas Lane and Maja Pantic
Paper  Supplemental  Poster Session 2
132
[182]
Two-directional Image Retargeting with Region-Aware Texture Enhancement
Dubok Park
Paper  Supplemental  Poster Session 2
133
[209]
DU-DARTS: Decreasing the Uncertainty of Differentiable Architecture Search
Shun Lu, Yu Hu, Longxing Yang, Zihao Sun, Jilin Mei, Yiming Zeng and Xiaowei Li
Paper  Supplemental  Code  Poster Session 2
134
[218]
Equivariance-bridged SO(2)-Invariant Representation Learning using Graph Convolutional Network
Sungwon Hwang, Hyungtae Lim and Hyun Myung
Paper  Supplemental  Code  Poster Session 2
135
[234]
Contextual Convolution Blocks
David Marwood and Shumeet Baluja
Paper  Poster Session 2
136
[244]
Transformer-based Monocular Depth Estimation with Attention Supervision
Wenjie Chang, Yueyi Zhang and Zhiwei Xiong
Paper  Supplemental  Code  Poster Session 2
137
[251]
A Probabilistic Hard Attention Model For Sequentially Observed Scenes
Samrudhdhi B Rangrej and James J. Clark
Paper  Supplemental  Code  Poster Session 2
138
[282]
Mitigating Bias in Visual Transformers via Targeted Alignment
Sruthi Sudhakar, Viraj Prabhu, Arvindkumar Krishnakumar and Judy Hoffman
Paper  Supplemental  Poster Session 2
139
[296]
Rethinking Token-Mixing MLP for MLP-based Vision Backbone
Tan Yu, XU LI, Yunfeng Cai, Mingming Sun and Ping Li
Paper  Poster Session 2
140
[329]
ESAD: End-to-end Semi-supervised Anomaly Detection
Chaoqin Huang, Fei Ye, Peisen Zhao, Ya Zhang, Yan-Feng Wang and Qi Tian
Paper  Supplemental  Poster Session 2
141
[345]
Searching for TrioNet: Combining Convolution with Local and Global Self-Attention
Huaijin Pi, Huiyu Wang, Yingwei Li, Zizhang Li and Alan Yuille
Paper  Supplemental  Code  Poster Session 2
142
[349]
Multi-Glimpse Network: A Robust and Efficient Classification Architecture based on Recurrent Downsampled Attention
Sia Huat Tan, Runpei Dong and Kaisheng Ma
Paper  Supplemental  Code  Poster Session 2
143
[362]
UDIS: Unsupervised Discovery of Bias in Deep Visual Recognition Models
Arvindkumar Krishnakumar, Viraj Prabhu, Sruthi Sudhakar and Judy Hoffman
Paper  Supplemental  Code  Poster Session 2
144
[378]
Image Composition Assessment with Saliency-augmented Multi-pattern Pooling
Bo Zhang, Li Niu and Liqing Zhang
Paper  Supplemental  Code  Poster Session 2
145
[381]
On Adversarial Robustness of 3D Point Cloud Classification under Adaptive Attacks
Jiachen Sun, Karl Koenig, Yulong Cao, Qi Alfred Chen and Zhuoqing Morley Mao
Paper  Supplemental  Poster Session 2
146
[399]
Back to the Future: Cycle Encoding Prediction for Self-supervised Video Representation Learning
Xinyu Yang, Majid Mirmehdi and Tilo Burghardt
Paper  Code  Poster Session 2
147
[404]
Unsupervised Domain Adaptation of Black-Box Source Models
Haojian Zhang, Yabin Zhang, Kui Jia and Lei Zhang
Paper  Supplemental  Code  Poster Session 2
148
[413]
Adaptive Tensor Networks Decomposition
Chang Nie, Huan Wang and Le Tian
Paper  Supplemental  Poster Session 2
149
[414]
Grand Unified Domain Adaptation
Ziyun Cai, Tengfei Zhang, Jing Xiao-Yuan and Ling Shao
Paper  Poster Session 2
150
[421]
Human Attention in Fine-grained Classification
Yao Rong, Wenjia Xu, Zeynep Akata and Enkelejda Kasneci
Paper  Supplemental  Code  Poster Session 2
151
[440]
Tendentious Noise-rectifying Framework for Pathological HCC Grading
XiaoTian Yu, Zunlei Feng, Yuexuan Wang, Thomas Kwok To Li, Xiuming Zhang and Mingli Song
Paper  Supplemental  Poster Session 2
152
[444]
Rich Semantics Improve Few-Shot Learning
Mohamed Afham Mohamed Aflal, Salman Khan, Muhammad Haris Khan, Muzammal Naseer and Fahad Shahbaz Khan
Paper  Supplemental  Code  Poster Session 2
153
[455]
Self-Supervised Learning in Multi-Task Graphs through Iterative Consensus Shift
Emanuela Haller, Elena Burceanu and Marius Leordeanu
Paper  Supplemental  Code  Poster Session 2
154
[478]
Improving Text-to-Image Synthesis Using Contrastive Learning
Hui Ye, Xiulong Yang, Martin Takac, Rajshekhar Sunderraman and Shihao Ji
Paper  Supplemental  Code  Poster Session 2
155
[484]
Prototype-based Incremental Few-Shot Segmentation
Fabio Cermelli, Massimiliano Mancini, Yongqin Xian, Zeynep Akata and Barbara Caputo
Paper  Supplemental  Code  Poster Session 2
156
[492]
Generative Dynamic Patch Attack
Xiang Li and Shihao Ji
Paper  Supplemental  Code  Poster Session 2
157
[502]
EBJR: Energy-Based Joint Reasoning for Adaptive Inference
Mohammad Akbari, Amin Banitalebi-Dehkordi and Yong Zhang
Paper  Supplemental  Code  Poster Session 2
158
[509]
Robust Semantic Segmentation with Superpixel-Mix
Gianni Franchi, Nacim Belkhir, Mai Lan Ha, Yufei Hu, Andrei Bursuc, Volker Blanz and Angela Yao
Paper  Supplemental  Code  Poster Session 2
159
[514]
Jitter-CAM: Improving the Spatial Resolution of CAM-Based Explanations
Thomas Hartley, Kirill Sidorov, Chris J Willis and David Marshall
Paper  Supplemental  Code  Poster Session 2
160
[520]
Quantised Transforming Auto-Encoders: Achieving Equivariance to Arbitrary Transformations in Deep Networks
Jianbo Jiao and Joao F Henriques
Paper  Supplemental  Code  Poster Session 2
161
[533]
Modeling Explicit Concerning States for Reinforcement Learning in Visual Dialogue
Zipeng Xu, Fandong Meng, Xiaojie Wang, Duo Zheng, Chenxu Lv and Jie Zhou
Paper  Supplemental  Code  Poster Session 2
162
[549]
Variance-stationary Differentiable NAS
Hyeokjun Choe, Byunggook Na, Jisoo Mok and Sungroh Yoon
Paper  Supplemental  Poster Session 2
163
[575]
AttNAS: Searching Attentions for Lightweight Semantic Segmentation
Yingying Jiang, Zhuoxin Gan, ), Ke Lin and Yong A
Paper  Supplemental  Poster Session 2
164
[595]
Few-shot Semantic Segmentation with Self-supervision from Pseudo-classes
Yiwen Li, Gratianus Wesley Putra Data, Yunguan Fu, Yipeng Hu and Victor Adrian Prisacariu
Paper  Supplemental  Poster Session 2
165
[614]
Class-Balanced Distillation for Long-Tailed Visual Recognition
Ahmet Iscen, Andre Araujo, Boqing Gong and Cordelia Schmid
Paper  Supplemental  Poster Session 2
166
[631]
Learning to Generate Novel Classes for Deep Metric Learning
Kyungmoon Lee, Sungyeon Kim, Seunghoon Hong and Suha Kwak
Paper  Supplemental  Poster Session 2
167
[634]
Unsupervised View-Invariant Human Posture Representation
Faegheh Sardari, Bjorn Ommer and Majid Mirmehdi
Paper  Supplemental  Code  Poster Session 2
168
[636]
Self-Supervised Training Enhances Online Continual Learning
Gianmarco J Gallardo, Tyler L Hayes and Christopher Kanan
Paper  Supplemental  Poster Session 2
169
[673]
SemGIF: A Semantics Guided Incremental Few-shot Learning Framework with Generative Replay
S Divakar Bhat, Biplab Banerjee and Subhasis Chaudhuri
Paper  Poster Session 2
170
[685]
Feature Fusion Vision Transformer for Fine-Grained Visual Categorization
Jun Wang, Xiaohan Yu and Yongsheng Gao
Paper  Code  Poster Session 2
171
[699]
Multi-Source Domain Adaptation via supervised contrastive learning and confident consistency regularization
Marin Scalbert, Florent Couzinié-Devy and Maria Vakalopoulou
Paper  Supplemental  Code  Poster Session 2
172
[702]
Fine-grained Multi-Modal Self-Supervised Learning
Duo Wang and Salah Karout
Paper  Supplemental  Poster Session 2
173
[724]
Logsig-RNN: a novel network for robust and efficient skeleton-based action recognition
Hao Ni, Shujian Liao, Weixin Yang, Kevin Schlegel and Terry J Lyons
Paper  Supplemental  Code  Poster Session 2
174
[743]
CvS: Classification via Segmentation For Small Datasets
Nooshin Mojab, Philip S Yu, Joelle Hallak and Darvin Yi
Paper  Poster Session 2
175
[749]
HS3: Learning with Proper Task Complexity in Hierarchically Supervised Semantic Segmentation
Shubhankar Borse, Hong Cai, Yizhe Zhang and Fatih Porikli
Paper  Supplemental  Poster Session 2
176
[757]
Mode-Guided Feature Augmentation for Domain Generalization
Muhammad Haris Khan, Syed Muhammad talha Zaidi, Salman Khan and Fahad Shahbaz Khan
Paper  Supplemental  Poster Session 2
177
[764]
Surprisingly Simple Semi-Supervised Domain Adaptation with Pretraining and Consistency
Samarth Mishra, Kate Saenko and Venkatesh Saligrama
Paper  Supplemental  Code  Poster Session 2
178
[770]
Neighborhood-Aware Neural Architecture Search
Xiaofang Wang, Shengcao Cao, Mengtian Li and Kris Kitani
Paper  Supplemental  Poster Session 2
179
[820]
Self-supervised Knowledge Distillation for Few-shot Learning
Jathushan Rajasegaran, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan and Mubarak Shah
Paper  Code  Poster Session 2
180
[838]
Multi-Class Novelty Detection with Generated Hard Novel Features
Wei-Ta Chu and Wei-Ting Cao
Paper  Poster Session 2
181
[840]
Latent-optimization based Disease-aware Image Editing for Medical Image Augmentation
Aakash saboo, Prashnna K Gyawali, Ankit Shukla, Manoj Sharma, Neeraj Jain and Linwei Wang
Paper  Supplemental  Poster Session 2
182
[874]
Meta-learning the Learning Trends Shared Across Tasks
Jathushan Rajasegaran, Salman Khan, Munawar Hayat, Fahad Shahbaz Khan and Mubarak Shah
Paper  Poster Session 2
183
[876]
Grouping Bilinear Pooling
Rui Zeng and Jingsong He
Paper  Code  Poster Session 2
184
[878]
Temporal Alignment via Event Boundary for Few-shot Action Recongnition
Shuyuan Li, Huabin Liu, Mengjuan Fei, Xiaoyuan Yu and Weiyao Lin
Paper  Supplemental  Poster Session 2
185
[890]
Siamese Prototypical Contrastive Learning
Shentong Mo, Zhun Sun and Chao Li
Paper  Supplemental  Poster Session 2
186
[896]
SPARROW: Semantically Coherent Prototypes for Image Classification
Stefan Kraft, Klaus Broelemann, Andreas Theissler and Gjergji Kasneci
Paper  Supplemental  Poster Session 2
187
[908]
PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labels
Filipe Rolim Cordeiro, Vasileios Belagiannis, Ian Reid and Gustavo Carneiro
Paper  Supplemental  Code  Poster Session 2
188
[912]
Incremental Learning for Animal Pose Estimation using RBF k-DPP
Gaurav Kumar Nayak, Het Shah and Anirban Chakraborty
Paper  Supplemental  Poster Session 2
189
[921]
TridentAdapt: Learning Domain-invariance via Source-Target Confrontation and Self-induced Cross-domain Augmentation
Fengyi Shen, Akhil Gurram, Ahmet Faruk Tuna, Onay Urfalioglu and Alois C. Knoll
Paper  Supplemental  Code  Poster Session 2
190
[946]
Coloured Edge Maps for Oil Palm Ripeness Classification
Wei Yuen Teh and Ian Tan
Paper  Poster Session 2
191
[1006]
SLURP: Side Learning Uncertainty for Regression Problems
Xuanlong Yu, Gianni Franchi and Emanuel Aldea
Paper  Supplemental  Poster Session 2
192
[1007]
Probabilistic Regression with Huber Distributions
David A Mohlin, Gerald Bianchi and Josephine Sullivan
Paper  Supplemental  Code  Poster Session 2
193
[1028]
Training Better Deep Neural Networks with Uncertainty Mining Net
Yang Sun, Abhishek Kolagunda, Steven Eliuk and Xiaolong Wang
Paper  Supplemental  Poster Session 2
194
[1039]
Mini-batch Similarity Graphs for Robust Image Classification
Arnab Kumar Mondal, Vineet Jain and Kaleem Siddiqi
Paper  Supplemental  Code  Poster Session 2
195
[1061]
PAL : Pretext-based Active Learning
Shubhang Bhatnagar, Sachin Goyal, Darshan Tank and Amit Sethi
Paper  Supplemental  Code  Poster Session 2
196
[1101]
Quality Map Fusion for Adversarial Learning
Uche Osahor and Nasser Nasrabadi
Paper  Poster Session 2
197
[1102]
Non-Autoregressive Sign Language Production with Gaussian Space
Eui Jun Hwang, Jung-Ho Kim and Jong C. Park
Paper  Supplemental  Code  Poster Session 2
198
[1158]
Source-free Unsupervised Domain Adaptation with Surrogate Data Generation
Hao Yan, Yuhong Guo and Chunsheng Yang
Paper  Code  Poster Session 2
199
[1165]
Evolving Image Compositions for Feature Representation Learning
Paola Cascante-Bonilla, Arshdeep Sekhon, Yanjun Qi and Vicente Ordonez
Paper  Supplemental  Poster Session 2
200
[1204]
Learnable Discrete Wavelet Pooling (LDW-Pooling) for Convolutional Networks
BorShiun Wang, Jun-Wei Hsieh, Ping-Yang Chen, Ming-Ching Chang, Lipeng Ke and Siwei Lyu
Paper  Supplemental  Poster Session 2
201
[1282]
Are conditional GANs explicitly conditional?
Houssem eddine BOULAHBAL, Adrian Voicila and Andrew I Comport
Paper  Supplemental  Code  Poster Session 2
202
[1291]
Bias Field Robustness Verification of Large Neural Image Classifiers
Patrick Henriksen, Kerstin Hammernik, Daniel Rueckert and Alessio Lomuscio
Paper  Supplemental  Poster Session 2
203
[1293]
Simple Dialogue System with AUDITED
Yusuf Tas and Piotr Koniusz
Paper  Supplemental  Poster Session 2
204
[1320]
FFNB: Forgetting-Free Neural Blocks for Deep Continual Learning
Hichem Sahbi and Haoming Zhan
Paper  Supplemental  Poster Session 2
205
[1355]
Hidden-Fold Networks: Random Recurrent Residuals Using Sparse Supermasks
Ángel López García-Arias, Masanori Hashimoto, Masato Motomura and Jaehoon Yu
Paper  Code  Poster Session 2
206
[1364]
A Simple Approach to Image Tilt Correction with Self-Attention MobileNet for Smartphones
Siddhant Garg, DEBI PRASANNA MOHANTY, Siva Thota and Sukumar Moharana
Paper  Poster Session 2
207
[1377]
Structured Latent Embeddings for Recognizing Unseen Classes in Unseen Domains
Shivam Chandhok, Sanath Narayan, Hisham Cholakkal, Rao Muhammad Anwer, Vineeth N Balasubramanian, Fahad Shahbaz Khan and Ling Shao
Paper  Supplemental  Poster Session 2
208
[1388]
WP2-GAN: Wavelet-based Multi-level GAN for Progressive Facial Expression Translation with Parallel Generators
Jun Shao and Tien Bui
Paper  Supplemental  Poster Session 2
209
[1391]
OODformer: Out-Of-Distribution Detection Transformer
Rajat Koner, Poulami Sinhamahapatra, Karsten Roscher, Stephan Günnemann and Volker Tresp
Paper  Supplemental  Code  Poster Session 2
210
[1415]
Frequency learning for structured CNN filters with Gaussian fractional derivatives
Nikhil Saldanha, Silvia-Laura L Pintea, Jan C van Gemert and Nergis Tomen
Paper  Supplemental  Poster Session 2
211
[1427]
Dynamic Feature Alignment for Semi-supervised Domain Adaptation
Yu Zhang, Gongbo Liang and Nathan Jacobs
Paper  Poster Session 2
212
[1438]
Dual Graph-Based Context Aggregation for Scene Parsing
Mengyu Liu and Hujun Yin
Paper  Poster Session 2
213
[1514]
Stylistic Multi-Task Analysis of Ukiyo-e Woodblock Prints
Selina J. Khan and Nanne van Noord
Paper  Supplemental  Code  Poster Session 2
214
[1522]
Using Synthetic Corruptions to Measure Robustness to Natural Distribution Shifts
Alfred LAUGROS, Alice Caplier and Matthieu Ospici
Paper  Supplemental  Code  Poster Session 2
215
[1546]
Introducing the Boundary-Aware loss for deep image segmentation
Minh ON VU NGOC, Yizi CHEN, Nicolas C. BOUTRY, Joseph Chazalon, Edwin Carlinet, Clement Mallet and Thierry GERAUD
Paper  Supplemental  Code  Poster Session 2
216
[1595]
Learning to ignore: rethinking attention in CNNs
Firas Laakom, Kateryna Chumachenko, Jenni Raitoharju, Alexandros Iosifidis and Moncef Gabbouj
Paper  Supplemental  Poster Session 2
217
[1657]
Noisy Differentiable Architecture Search
Xiangxiang Chu and Bo Zhang
Paper  Supplemental  Code  Poster Session 2
Wednesday 24th November : Oral Session 5: Synthesis / Analysis
218
[141]
Cascaded Cross MLP-Mixer GANs for Cross-View Image Translation
Bin Ren, Hao Tang and Nicu Sebe
Paper  Supplemental  Code  Oral Session 5  Poster Session 3
219
[579]
HairFIT: Pose-invariant Hairstyle Transfer via Flow-based Hair Alignment and Semantic-region-aware Inpainting
Chaeyeon Chung, Taewoo Kim, Hyelin Nam, Seunghwan Choi, Gyojung Gu, Sunghyun Park and Jaegul Choo
Paper  Supplemental  Oral Session 5  Poster Session 3
220
[872]
StyleVideoGAN: A Temporal Generative Model using a Pretrained StyleGAN
Gereon Fox, Ayush Tewari, Mohamed Elgharib and Christian Theobalt
Paper  Supplemental  Oral Session 5  Poster Session 3
221
[1346]
Temporal Meta-Adaptor for Video Object Detection
Chi Wang, Yang Hua, ZHENG LU, Jian Gao and Neil Robertson
Paper  Supplemental  Oral Session 5  Poster Session 3
222
[1617]
Tensor Component Analysis for Interpreting the Latent Space of GANs
James Oldfield, Markos Georgopoulos, Yannis Panagakis, Mihalis A Nicolaou and Ioannis Patras
Paper  Supplemental  Oral Session 5  Poster Session 3
Wednesday 24th November : Oral Session 6: Recognition
223
[97]
BI-GCN: Boundary-Aware Input-Dependent Graph Convolution Network for Biomedical Image Segmentation
Yanda Meng, Hongrun Zhang, Dongxu Gao, Yitian Zhao, Xiaoyun Yang, Xuesheng Qian, Xiaowei Huang and Yalin Zheng
Paper  Supplemental  Code  Oral Session 6  Poster Session 3
224
[133]
CTRN: Class-Temporal Relational Network for Action Detection
Rui Dai, Srijan Das and Francois Bremond
Paper  Supplemental  Oral Session 6  Poster Session 3
225
[487]
Everybody Is Unique: Towards Unbiased Human Mesh Recovery
Ren Li, Srikrishna Karanam, Meng Zheng, Terrence Chen and Ziyan Wu
Paper  Supplemental  Oral Session 6  Poster Session 3
226
[709]
End-to-End Object Detection with Adaptive Clustering Transformer
Minghang Zheng, Peng Gao, Renrui Zhang, Kunchang Li, Hongsheng Li and Hao Dong
Paper  Supplemental  Code  Oral Session 6  Poster Session 3
227
[1360]
A 2-D Wrist Motion Based Sign Language Video Summarization
Evangelos Sartinas, Emmanouil Psarakis, Klimis Antzakas and Dimitrios Kosmopoulos
Paper  Supplemental  Oral Session 6  Poster Session 3
Wednesday 24th November : Poster Session 3
228
[31]
Mask-aware IoU for Anchor Assignment in Real-time Instance Segmentation
Kemal Oksuz, Baris Can Cam, Fehmi Kahraman, Zeynep S Baltacı, Sinan Kalkan and Emre Akbas
Paper  Code  Poster Session 3
229
[35]
Continuous-Time Video Generation via Learning Motion Dynamics with Neural ODE
Kangyeol Kim, Sunghyun Park, Junsoo Lee, Joonseok Lee, Sookyung Kim, Jaegul Choo and Edward Choi
Paper  Supplemental  Poster Session 3
230
[54]
Human-object Interaction Detection without Alignment Supervision
Mert Kilickaya and Arnold W.M. Smeulders
Paper  Supplemental  Poster Session 3
231
[56]
Segmenting Invisible Moving Objects
Hala Lamdouar, Weidi Xie and Andrew Zisserman
Paper  Supplemental  Code  Poster Session 3
232
[96]
Hand-Object Contact Prediction via Motion-Based Pseudo-Labeling and Guided Progressive Label Correction
Takuma Yagi, Md Tasnimul Hasan and Yoichi Sato
Paper  Supplemental  Code  Poster Session 3
233
[128]
LSTA-Net: Long short-term Spatio-Temporal Aggregation Network for Skeleton-based Action Recognition
Tailin Chen, Shidong Wang, Desen Zhou and Yu Guan
Paper  Code  Poster Session 3
234
[134]
Exemplar-Based Early Event Prediction in Video
ZEKUN ZHANG, FARRUKH M KORAISHY and Minh Hoai
Paper  Supplemental  Code  Poster Session 3
235
[148]
DRT: Detection Refinement for Multiple Object Tracking
Bisheng Wang, Christian Fruhwirth-Reisinger, Horst Possegger, Horst Bischof and Guo Cao
Paper  Supplemental  Poster Session 3
236
[183]
ASFormer: Transformer for Action Segmentation
Fangqiu Yi, Hongyu Wen and Tingting Jiang
Paper  Supplemental  Code  Poster Session 3
237
[190]
A Closer Look at Few-Shot Video Classification: A New Baseline and Benchmark
Zhenxi Zhu, Limin Wang, Sheng Guo and Gangshan Wu
Paper  Code  Poster Session 3
238
[221]
MinMaxCAM: Improving object coverage for CAM-based Weakly Supervised Object Localization
Kaili Wang (KU Leuven, University of Antwerp, imec-IDLab), Jose Oramas and Tinne Tuytelaars
Paper  Supplemental  Code  Poster Session 3
239
[242]
PlaneRecNet: Multi-Task Learning with Cross-Task consistency for Piece-Wise Plane Detection and Reconstruction from a Single RGB Image
Yaxu Xie, Fangwen Shu, Jason Rambach, A. Pagani and Didier Stricker
Paper  Supplemental  Code  Poster Session 3
240
[243]
Stacked Temporal Attention: Improving First-person Action Recognition by Emphasizing Discriminative Clips
Lijin Yang, Yifei Huang, Yusuke Sugano and Yoichi Sato
Paper  Supplemental  Poster Session 3
241
[265]
Diagnosing Errors in Video Relation Detectors
Shuo Chen, Pascal Mettes and Cees Snoek
Paper  Supplemental  Code  Poster Session 3
242
[298]
360° Optical Flow using Tangent Images
Mingze Yuan and Christian Richardt
Paper  Supplemental  Code  Poster Session 3
243
[300]
Depth-only Object Tracking
Song Yan, Jinyu Yang, Ales Leonardis and Joni-Kristian Kamarainen
Paper  Supplemental  Code  Poster Session 3
244
[307]
Spatial-Temporal Residual Aggregation for High Resolution Video Inpainting
Vishnu Sanjay Ramiya Srinivasan, Rui Ma, Qiang Tang, Zili Yi and Zhan Xu
Paper  Supplemental  Code  Poster Session 3
245
[308]
Knowing What, Where and When to Look: Video Action modelling with Attention
Juan-Manuel Perez-Rua, Brais Martinez, Xiatian Zhu, Antoine S Toisoul, Victor A Escorcia and Tao Xiang
Paper  Supplemental  Poster Session 3
246
[325]
FacialGAN: Style Transfer and Attribute Manipulation on Synthetic Faces
Ricard Durall Lopez, Jireh Jam, Dominik Strassel, Moi Hoon Yap and Janis Keuper
Paper  Supplemental  Code  Poster Session 3
247
[327]
Render In-between: Motion Guided Video Synthesis for Action Interpolation
Hsuan-I Ho, Xu Chen, Jie Song and Otmar Hilliges
Paper  Supplemental  Code  Poster Session 3
248
[332]
Towards Overcoming False Positives in Visual Relationship Detection
Daisheng Jin, Xiao Ma, Chongzhi Zhang, Yizhuo Zhou, Jiashu Tao, Mingyuan Zhang and Zhoujun Li
Paper  Supplemental  Code  Poster Session 3
249
[340]
Few-shot Action Recognition with Prototype-centered Attentive Learning
Xiatian Zhu, Antoine S Toisoul, Juan-Manuel Perez-Rua, Li Zhang, Brais Martinez and Tao Xiang
Paper  Supplemental  Poster Session 3
250
[342]
A Comprehensive CT Dataset for Liver Computer Assisted Diagnosis
Qingsen Yan, Bo Wang, Dong Gong, Dingwen Zhang, Yang Yang, Zheng You, Yanning Zhang and Javen Qinfeng Shi
Paper  Poster Session 3
251
[348]
ExSinGAN: Learning an Explainable Generative Model from a Single Image
Zicheng Zhang, Congying Han and Tiande Guo
Paper  Supplemental  Code  Poster Session 3
252
[357]
Few-Shot Temporal Action Localization with Query Adaptive Transformer
Sauradip Nag, Xiatian Zhu and Tao Xiang
Paper  Supplemental  Code  Poster Session 3
253
[363]
FlowVOS: Weakly-Supervised Visual Warping for Detail-Preserving and Temporally Consistent Single-Shot Video Object Segmentation
Julia Gong, F. Christopher Holsinger and Serena Yeung
Paper  Supplemental  Code  Poster Session 3
254
[386]
Hierarchical Interaction Network for Video Object Segmentation from Referring Expressions
Zhao Yang, Yansong Tang, Luca Bertinetto, Hengshuang Zhao and Philip Torr
Paper  Supplemental  Poster Session 3
255
[409]
Space-Time Memory Network for Sounding Object Localization in Videos
Sizhe Li, Yapeng Tian and Chenliang Xu
Paper  Supplemental  Code  Poster Session 3
256
[420]
View Birdification in the Crowd: Ground-Plane Localization from Perceived Movements
Mai Nishimura, Shohei Nobuhara and Ko Nishino
Paper  Supplemental  Poster Session 3
257
[425]
You Better Look Twice: a new perspective for designing accurate detectors with reduced computations
Alexandra Dana, Maor Shutman, Yotam Perlitz, Ran Vitek, Tomer Peleg and Roy J Jevnisek
Paper  Supplemental  Code  Poster Session 3
258
[434]
LARNet: Latent Action Representation for Human Action Synthesis
Naman Biyani, Aayush Jung Bahadur Rana, Shruti Vyas and Yogesh Rawat
Paper  Supplemental  Code  Poster Session 3
259
[468]
Point3D: tracking actions as moving points with 3D CNNs
Shentong Mo, Jingfei Xia, Xiaoqing Tan and Bhiksha Raj
Paper  Supplemental  Poster Session 3
260
[483]
TEAM-Net: Multi-modal Learning for Video Action Recognition with Partial Decoding
Zhengwei Wang, Qi She and Aljosa Smolic
Paper  Supplemental  Code  Poster Session 3
261
[499]
Audio-Visual Synchronisation in the wild
Triantafyllos Afouras, Honglie Chen, Weidi Xie, Arsha Nagrani, Andrea Vedaldi and Andrew Zisserman
Paper  Code  Poster Session 3
262
[501]
2.5D-VoteNet: Depth Map based 3D Object Detection for Real-Time Applications
Lanxiao Li and Michael Heizmann
Paper  Supplemental  Poster Session 3
263
[508]
Model Composition: Can Multiple Neural Networks Be Combined into a Single Network Using Only Unlabeled Data?
Amin Banitalebi-Dehkordi, Xinyu Kang and Yong Zhang
Paper  Supplemental  Poster Session 3
264
[548]
MFE: Multi-scale Feature Enhancement for Object Detection
Zhenhu Zhang, Xueying Qin and Fan Zhong
Paper  Poster Session 3
265
[568]
Exploiting Scene Depth for Object Detection with Multimodal Transformers
Hwanjun Song, Eunyoung Kim, Varun Jampani, Deqing Sun, Jae-Gil Lee and Ming-Hsuan Yang
Paper  Supplemental  Code  Poster Session 3
266
[580]
MOS: A Low Latency and Lightweight Framework for Face Detection, Landmark Localization, and Head Pose Estimation
Yepeng Liu, Zaiwang Gu, Shenghua Gao, Dong Wang, Yusheng Zeng and Jun Cheng
Paper  Supplemental  Code  Poster Session 3
267
[601]
Channel DropBlock: An Improved Regularization Method for Fine-Grained Visual Classification
Yifeng Ding, Shuwei Dong, Yujun Tong, Zhanyu Ma, Bo Xiao and Haibin Ling
Paper  Code  Poster Session 3
268
[610]
With a Little Help from my Temporal Context: Multimodal Egocentric Action Recognition
Evangelos Kazakos, Jaesung Huh, Arsha Nagrani, Andrew Zisserman and Dima Damen
Paper  Supplemental  Code  Poster Session 3
269
[611]
HR-RCNN: Hierarchical Relational Reasoning for Object Detection
Hao Chen and Abhinav Shrivastava
Paper  Supplemental  Poster Session 3
270
[615]
Move to See Better: Self-Improving Embodied Object Detection
Zhaoyuan Fang, Ayush Jain, Gabriel Sarch, Adam Harley and Katerina Fragkiadaki
Paper  Supplemental  Code  Poster Session 3
271
[628]
Joint Detection of Motion Boundaries and Occlusions
Hannah H Kim, Shuzhi Yu and Carlo Tomasi
Paper  Code  Poster Session 3
272
[646]
Boosting Adversarial Transferability through Enhanced Momentum
Xiaosen Wang, Jiadong Lin, Han Hu, Jingdong Wang and Kun He
Paper  Supplemental  Code  Poster Session 3
273
[651]
Deep Video Decaptioning
Pengpeng Chu, Weize Quan, Tong Wang, Pan Wang, Peiran Ren and Dong-Ming Yan
Paper  Supplemental  Code  Poster Session 3
274
[675]
Paying Attention to Varying Receptive Fields: Object Detection with Atrous Filters and Vision Transformers
Arthur Jian Shun Lam, Jun Yi Lim, Ricky Sutopo and Vishnu Monn Baskaran
Paper  Supplemental  Poster Session 3
275
[684]
CAFENet: Class-Agnostic Few-Shot Edge Detection Network
YoungHyun Park, Jun Seo and Jaekyun Moon
Paper  Supplemental  Poster Session 3
276
[694]
Re-ID-AR: Improved Person Re-identification in Videovia Joint Weakly Supervised Action Recognition
Aishah Alsehaim and Toby P Breckon
Paper  Supplemental  Poster Session 3
277
[701]
TICaM: A Time-of-flight In-car Cabin Monitoring Dataset
Jigyasa S Katrolia, Ahmed ElSherif, Hartmut Feld, Bruno Mirbach, Jason Rambach and Didier Stricker
Paper  Supplemental  Poster Session 3
278
[706]
Spatiotemporal Deformable Scene Graphs for Complex Activity Detection
Salman Khan and Fabio Cuzzolin
Paper  Supplemental  Code  Poster Session 3
279
[711]
Learning Not to Reconstruct Anomalies
Marcella Astrid, Muhammad Zaigham Zaheer, Jae-Yeong Lee and Seung-Ik Lee
Paper  Supplemental  Code  Poster Session 3
280
[736]
Towards Dynamic and Scalable Active Learning with Neural Architecture Adaption for Object Detection
Fuhui Tang, ChenHan Jiang, Dafeng Wei, Hang Xu, Andi Zhang, Wei Zhang, Hongtao Lu and Chunjing Xu
Paper  Poster Session 3
281
[739]
Zero-Shot Action Recognition from Diverse Object-Scene Compositions
Carlo Bretti and Pascal Mettes
Paper  Code  Poster Session 3
282
[745]
Grounded Situation Recognition with Transformers
Junhyeong Cho, Youngseok Yoon, Hyeonjun Lee and Suha Kwak
Paper  Supplemental  Code  Poster Session 3
283
[773]
Unsupervised Discovery of Actions in Instructional Videos
AJ Piergiovanni, Anelia Angelova, Michael S Ryoo (Google, Stony Brook University) and Irfan Essa
Paper  Supplemental  Poster Session 3
284
[784]
VIN: Voxel-based Implicit Network for Joint3D Object Detection and Segmentation for Lidars
Yuanxin Zhong, Minghan Zhu and Huei Peng
Paper  Supplemental  Code  Poster Session 3
285
[795]
Wide and Narrow: Video Prediction from Context and Motion
Jaehoon Cho, Jiyoung Lee, Changjae Oh, Wonil Song and Kwanghoon Sohn
Paper  Supplemental  Poster Session 3
286
[844]
Weakly-Supervised Dense Action Anticipation
Haotong Zhang, Fuhai Chen and Angela Yao
Paper  Supplemental  Code  Poster Session 3
287
[900]
Quantum Unsupervised Domain Adaptation: Does Entanglement Help?
Nanqing Dong, Michael C. Kampffmeyer and Irina D Voiculescu
Paper  Poster Session 3
288
[971]
A cappella: Audio-visual Singing Voice Separation
Juan Felipe Montesinos, Venkatesh Shenoy Kadandale and Gloria Haro
Paper  Supplemental  Code  Poster Session 3
289
[993]
Dynamic Graph Warping Transformer for Video Alignment
Junyan Wang, Yang Long, Maurice Pagnucco and Yang Song
Paper  Poster Session 3
290
[1008]
Semi-Supervised Few-Shot Object Detection with a Teacher-Student Network
Wuti Xiong, Yawen Cui and Li Liu
Paper  Poster Session 3
291
[1038]
Guided Flow Field Estimation by Generating Independent Patches
Mohsen Tabejamaat, Farhood Negin and Francois Bremond
Paper  Supplemental  Poster Session 3
292
[1053]
GTA: Global Temporal Attention for Video Action Understanding
Bo He, Xitong Yang, Zuxuan Wu, Hao Chen, Ser-Nam Lim and Abhinav Shrivastava
Paper  Supplemental  Poster Session 3
293
[1056]
A Simple Baseline for Weakly-Supervised Human-centric Relation Detection
Raghav Goyal and Leonid Sigal
Paper  Supplemental  Code  Poster Session 3
294
[1079]
One-Shot Deep Model for End-to-End Multi-Person Activity Recognition
Shuhei Tarashima
Paper  Supplemental  Poster Session 3
295
[1083]
Attention to Action: Leveraging Attention for Object Navigation
Shi Chen and Qi Zhao
Paper  Supplemental  Code  Poster Session 3
296
[1100]
Refining FFT-based Heatmap for the Detection of Cluster Distributed Targets in Satellite Images
Huan Zhang, Zhiyi Xu, Xiaolin Han and Weidong Sun
Paper  Poster Session 3
297
[1115]
Semantic-Guided Radar-Vision Fusion for Depth Estimation and Object Detection
Wei-Yu Lee, Ljubomir Jovanov and Wilfried Philips
Paper  Supplemental  Poster Session 3
298
[1119]
Multi-Modality Task Cascade for 3D Object Detection
Jinhyung Park, Xinshuo Weng, Yunze Man and Kris Kitani
Paper  Supplemental  Code  Poster Session 3
299
[1124]
Selective Pseudo-Labeling with Reinforcement Learning for Semi-Supervised Domain Adaptation
Bingyu Liu, Yuhong Guo, Jieping Ye and Weihong Deng
Paper  Poster Session 3
300
[1171]
V3GAN: Decomposing Background, Foreground and Motion for Video Generation
Arti Keshari, Sonam Gupta and Sukhendu Das
Paper  Supplemental  Code  Poster Session 3
301
[1187]
Transferring Domain-Agnostic Knowledge in Video Question Answering
Tianran Wu, Noa Garcia, Mayu Otani, Chenhui Chu, Yuta Nakashima and Haruo Takemura
Paper  Supplemental  Poster Session 3
302
[1188]
Unsupervised Spatio-temporal Latent Feature Clustering for Multiple-object Tracking and Segmentation
Abubakar Siddique, Reza Jalil Mozhdehi and Henry Medeiros
Paper  Code  Poster Session 3
303
[1190]
Label2im: Knowledge Graph Guided Image Generation from Labels
Hewen Xiao, Yuqiu Kong, Hongchen Tan, Xiuping Liu and Baocai Yin
Paper  Supplemental  Poster Session 3
304
[1200]
TNT: Text-Conditioned Network with Transductive Inference for Few-Shot Video Classification
Andrés Villa, Juan-Manuel Perez-Rua, Vladimir Araujo, Juan Carlos Niebles, Victor A Escorcia and Alvaro Soto
Paper  Supplemental  Poster Session 3
305
[1254]
A Foundation for 3D Human Behavior Detection in Privacy-Sensitive Domains
Thomas TH Heitzinger and Martin Kampel
Paper  Supplemental  Poster Session 3
306
[1273]
Student-Teacher Feature Pyramid Matching for Anomaly Detection
Guodong Wang, Shumin Han, Errui Ding and Di Huang
Paper  Supplemental  Code  Poster Session 3
307
[1275]
Image Completion with Adaptive Multi-Temperature Mask-Guided Attention
Xiang Zhou, Yuan Zeng and Yi Gong
Paper  Supplemental  Poster Session 3
308
[1276]
TAPL: Dynamic Part-based Visual Tracking via Attention-guided Part Localization
Wei Han, Hantao Huang and Xiaoxi Yu
Paper  Supplemental  Poster Session 3
309
[1295]
SVD-GAN for Real-Time Unsupervised Video Anomaly Detection
Dinesh Jackson Samuel and Fabio Cuzzolin
Paper  Supplemental  Code  Poster Session 3
310
[1339]
Localizing Objects with Self-supervised Transformers and no Labels
Oriane Siméoni, Gilles Puy, Huy V. Vo, Simon W Roburin, Spyros Gidaris, Andrei Bursuc, Patrick Pérez, Renaud Marlet and Jean Ponce
Paper  Supplemental  Code  Poster Session 3
311
[1352]
FAST3D: Flow-Aware Self-Training for 3D Object Detectors
Christian Fruhwirth-Reisinger, Michael Opitz, Horst Possegger and Horst Bischof
Paper  Supplemental  Poster Session 3
312
[1376]
Conditional Model Selection for Efficient Video Understanding
Mihir Jain, Haitam Ben Yahia, Amir Ghodrati, Amirhossein Habibian and Fatih Porikli
Paper  Supplemental  Poster Session 3
313
[1378]
Order-independent Matching with Shape Similarity for Parking Slot Detection
Yin Ziyi, Ruijin Liu, Zejian Yuan and Zhiliang Xiong
Paper  Supplemental  Poster Session 3
314
[1400]
FETNet: Feature Exchange Transformer Network for RGB-D Object Detection
Zhibin Xiao, Jing-Hao Xue, Pengwei Xie and Guijin Wang
Paper  Poster Session 3
315
[1430]
AudViSum: Self-Supervised Deep Reinforcement Learning for Diverse Audio-Visual Summary Generation
Sanjoy Chowdhury, Aditya Patra, Subhrajyoti Dasgupta and Ujjwal Bhattacharya
Paper  Supplemental  Poster Session 3
316
[1435]
MIGS: Meta Image Generation from Scene Graphs
Azade Farshad, Sabrina Musatian, Helisa Dhamo and Nassir Navab
Paper  Supplemental  Poster Session 3
317
[1445]
3D Object Tracking with Transformer
Yubo Cui, Zheng Fang, Jiayao Shan, Zuoxu Gu and Sifan Zhou
Paper  Supplemental  Code  Poster Session 3
318
[1480]
Multi-attribute Pizza Generator: Cross-domain Attribute Control with Conditional StyleGAN
Fangda Han, Guoyao Hao, Ricardo Guerrero and Vladimir Pavlovic
Paper  Supplemental  Code  Poster Session 3
319
[1500]
Monocular Arbitrary Moving Object Discovery and Segmentation
Michal Neoral, Jan Sochman and Jiri Matas
Paper  Code  Poster Session 3
320
[1518]
An attention-driven hierarchical multi-scale representation for visual recognition
Zachary Wharton, Ardhendu Behera and Asish Bera
Paper  Supplemental  Poster Session 3
321
[1536]
ERA: Entity–relationship Aware Video Summarization with Wasserstein GAN
Guande Wu, Jianzhe Peter Lin and Claudio Silva
Paper  Supplemental  Code  Poster Session 3
322
[1542]
Enhancing Human Motion Assessment by Self-supervised Representation Learning
Mahdiar Nekoui and Li Cheng
Paper  Poster Session 3
323
[1568]
Livestock Monitoring with Transformer
Bhavesh Tangirala, Ishan Bhandari, Daniel Laszlo, Deepak K Gupta, Rajat Thomas and Devanshu Arya
Paper  Supplemental  Code  Poster Session 3
324
[1571]
CHASE: Robust Visual Tracking via Cell-Level Differentiable Neural Architecture Search
Seyed Mojtaba Marvasti-Zadeh, Javad Khaghani, Li Cheng, Hossein Ghanei-Yakhdan and Shohreh Kasaei
Paper  Supplemental  Code  Poster Session 3
325
[1642]
Highly Efficient Natural Image Matting
Yijie Zhong, Bo Li, Lv Tang, Hao Tang and Shouhong Ding
Paper  Supplemental  Poster Session 3
Thursday 25th November : Oral Session 7: Image Enhancement
326
[506]
Single Pixel Spectral Color Constancy
Samu Koskinen, Erman Acar and Joni-Kristian Kamarainen
Paper  Oral Session 7  Poster Session 4
327
[620]
Few-Shot Domain Adaptation for Low Light RAW Image Enhancement
Ram K Prabhakar, Vishal Vinod, Nihar R. Sahoo and Venkatesh Babu RADHAKRISHNAN
Paper  Supplemental  Oral Session 7  Poster Session 4
328
[1117]
Learned Regularizers and Geometry for Image Denoising
Stacey E Levine, Ryan M Cecil and Marcelo Bertalmío
Paper  Oral Session 7  Poster Session 4
329
[1167]
Unsupervised Image Denoising with Frequency Domain Knowledge
Nahyun Kim, Donggon Jang, Sunhyeok Lee, Bomi Kim and Daeshik Kim
Paper  Supplemental  Code  Oral Session 7  Poster Session 4
330
[868]
KonIQ++: Boosting No-Reference Image Quality Assessment in the Wild by Jointly Predicting Image Quality and Defects
Shaolin Su, Vlad Hosu, Hanhe Lin, Yanning Zhang and Dietmar Saupe
Paper  Supplemental  Code  Oral Session 7  Poster Session 4
Thursday 25th November : Oral Session 8: Representation Learning
331
[783]
Selection of Source Images Heavily Influences the Effectiveness of Adversarial Attacks
Utku Ozbulak, Esla Timothy Anzaku, Wesley De Neve and Arnout Van Messem
Paper  Supplemental  Code  Oral Session 8  Poster Session 4
332
[1327]
Pseudo-Labeling for Class Incremental Learning
Alexis Lechat, Stephane Herbin and Frederic Jurie
Paper  Supplemental  Code  Oral Session 8  Poster Session 4
333
[126]
Learning to Sparsify Differences of Synaptic Signal for Efficient Event Processing
Yusuke Sekikawa and Keisuke Uto
Paper  Supplemental  Code  Oral Session 8  Poster Session 4
334
[1258]
DISCO: accurate Discrete Scale Convolutions
Ivan Sosnovik, Artem Moskalev and Arnold W.M. Smeulders
Paper  Supplemental  Oral Session 8  Poster Session 4
335
[591]
How Important is Importance Sampling for Deep Budgeted Training?
Eric Arazo, Diego Ortego, Paul Albert, Noel O'Connor and Kevin McGuinness
Paper  Code  Oral Session 8  Poster Session 4
Thursday 25th November : Poster Session 4
336
[16]
TransFusion: Cross-view Fusion with Transformer for 3D Human Pose Estimation
Haoyu Ma, Liangjian Chen, Deying Kong, Zhe Wang, Xingwei Liu, Hao Tang, Xiangyi Yan, Yusheng Xie, Shih-Yao Lin and Xiaohui Xie
Paper  Code  Poster Session 4
337
[44]
Text-Based Person Search with Limited Data
Xiao Han, Sen He, Li Zhang and Tao Xiang
Paper  Supplemental  Code  Poster Session 4
338
[57]
PartGAN: Unsupervised Part Decomposition for Image Generation and Segmentation
Yuheng Li, Krishna Kumar Singh, Yang Xue and Yong Jae Lee
Paper  Supplemental  Poster Session 4
339
[79]
Each Attribute Matters: Contrastive Attention for Sentence-based Image Editing
Liuqing Zhao, Fan Lyu, Fuyuan Hu, Kaizhu Huang, Fenglei Xu and Linyan Li
Paper  Supplemental  Code  Poster Session 4
340
[91]
Boundary Guided Context Aggregation for Semantic Segmentation
Haoxiang Ma, Hongyu Yang and Di Huang
Paper  Supplemental  Code  Poster Session 4
341
[92]
Learning multiplane images from single views with self-supervision
Gustavo Sutter P. Carvalho, Diogo C Luvizon, Antonio Joia, Andre GC Pacheco and Otávio Penatti
Paper  Supplemental  Poster Session 4
342
[103]
Local-Global Associative Frame Assemble in Video Re-ID
Qilei Li, Jiabo Huang and Shaogang Gong
Paper  Code  Poster Session 4
343
[117]
Image-Text Alignment using Adaptive Cross-attention with Transformer Encoder for Scene Graphs
Juyong Song and Sunghyun Choi
Paper  Supplemental  Code  Poster Session 4
344
[129]
Joint-Aware Regression: Rethinking Regression-Based Method for 3D Hand Pose Estimation
Xiaozheng Zheng, Pengfei Ren, Haifeng Sun, Jingyu Wang, Qi Qi and Jianxin Liao
Paper  Supplemental  Poster Session 4
345
[130]
AniFormer: Data-driven 3D Animation with Transformer
Haoyu Chen, Hao Tang, Nicu Sebe and Guoying Zhao
Paper  Supplemental  Code  Poster Session 4
346
[223]
HandTailor: Towards High-Precision Monocular 3D Hand Recovery
Jun Lv, Wenqiang Xu, Lixin Yang, Sucheng Qian, Chongzhao Mao and Cewu Lu
Paper  Supplemental  Code  Poster Session 4
347
[236]
Temporal-Spatial Graph Attention Networks for DCE-MRI Breast Tumor Segmentation
Tianxu Lv and Xiang Pan
Paper  Poster Session 4
348
[254]
MorphGAN: One-Shot Face Synthesis GAN for Detecting Recognition Bias
Nataniel Ruiz, Barry Theobald, Anurag Ranjan, Ahmed Hussen Abdelaziz and Nicholas Apostoloff
Paper  Supplemental  Poster Session 4
349
[264]
MVT: Multi-view Vision Transformer for 3D Object Recognition
Shuo Chen, Tan Yu and Ping Li
Paper  Poster Session 4
350
[271]
Learning Texture Generators for 3D Shape Collections from Internet Photo Sets
Rui Yu, Yue Dong, Pieter Peers and Xin Tong
Paper  Supplemental  Poster Session 4
351
[284]
Leveraging Geometry for Shape Estimation from a Single RGB Image
Florian Maximilian Langer, Ignas Budvytis and Roberto Cipolla
Paper  Supplemental  Poster Session 4
352
[286]
Higher-Order Implicit Fairing Networks for 3D Human Pose Estimation
Jianning Quan and Abdessamad Ben Hamza
Paper  Poster Session 4
353
[291]
Talking Head Generation with Audio and Speech Related Facial Action Units
Sen Chen, Zhilei Liu, Jiaxing Liu, Zhengxiang Yan and Longbiao Wang
Paper  Supplemental  Poster Session 4
354
[299]
Deep Line Encoding for Monocular 3D Object Detection and Depth Prediction
Ce Liu, Shuhang Gu, Luc Van Gool and Radu Timofte
Paper  Supplemental  Code  Poster Session 4
355
[328]
DomainMix: Learning Generalizable Person Re-Identification Without Human Annotations
Wenhao Wang, Shengcai Liao, Fang Zhao, Cuicui Kang and Ling Shao
Paper  Supplemental  Code  Poster Session 4
356
[330]
Separating Content and Style for Unsupervised Image-to-Image Translation
Yunfei Liu, Haofei Wang, Yang Yue and Feng Lu
Paper  Code  Poster Session 4
357
[334]
Extended Differentiable Marching Cubes by Manifold-Preserving Shape Inflation
Kiichi Itoh, Tatsuya Yatagawa, Yutaka Ohtake and Suzuki Hiromasa
Paper  Supplemental  Poster Session 4
358
[352]
Robust Ellipsoid-specific Fitting via Expectation Maximization
Mingyang Zhao, Xiaohong Jia, Lei Ma, Xinling Qiu, Xin Jiang and Dong-Ming Yan
Paper  Supplemental  Code  Poster Session 4
359
[391]
Multi-Granularity Hypergraphs and Adversarial Complementary Learning for Person Re-identification
Yi Ma, Tian Bai, Wenyu Zhang and Jian Hu
Paper  Supplemental  Poster Session 4
360
[423]
Intersection Prediction from Single 360° Image via Deep Detection of Possible Direction of Travel
Naoki Sugimoto, Satoshi Ikehata and Kiyoharu Aizawa
Paper  Supplemental  Poster Session 4
361
[451]
Elsa: Energy-based Learning for Semi-supervised Anomaly Detection
Sungwon Han, HyeonHo Song, Seung Eon Lee, Sungwon Park and Meeyoung Cha
Paper  Supplemental  Poster Session 4
362
[467]
Inside Out Visual Place Recognition
Sarah Ibrahimi, Nanne van Noord, Tim Alpherts and Marcel Worring
Paper  Supplemental  Code  Poster Session 4
363
[471]
GaitMask: Mask-based Model for Gait Recognition
Beibei Lin, Yu Liu and Shunli Zhang
Paper  Poster Session 4
364
[476]
PRN: Psychology-Inspired Relation Network for Detecting Social Interaction Groups from Single Images
Jiaqi Yu, Jinhai Yang, Hua Yang and Guangtao Zhai
Paper  Supplemental  Poster Session 4
365
[517]
Leveraging Human Selective Attention for Medical Image Analysis with Limited Training Data
Yifei Huang, Xiaoxiao Li, Lijin Yang, Lin Gu, Yingying Zhu, Hirofumi Seo, Qiuming Meng, Tatsuya Harada and Yoichi Sato
Paper  Supplemental  Poster Session 4
366
[544]
OMAD: Object Model with Articulated Deformations for Pose Estimation and Retrieval
Han Xue, Liu Liu, Wenqiang Xu, Haoyuan Fu and Cewu Lu
Paper  Supplemental  Code  Poster Session 4
367
[585]
Separable Batch Normalization for Robust Facial Landmark Localization
Shuangping Jin, Zhenhua Feng, Wankou Yang and Josef Kittler
Paper  Supplemental  Code  Poster Session 4
368
[600]
Cascading Feature Extraction for Fast Point Cloud Registration
Yoichiro Hisadome and Yusuke Matsui
Paper  Code  Poster Session 4
369
[604]
Center-wise Local Image Mixture For Contrastive Representation Learning
Hao Li, Xiaopeng Zhang and Hongkai Xiong
Paper  Supplemental  Poster Session 4
370
[606]
Multi-Stream Attention Learning for Monocular Vehicle Velocity and Inter-Vehicle Distance Estimation
Kuan-Chih Huang, Yu-Kai Huang and Winston H. Hsu
Paper  Poster Session 4
371
[638]
GaussiGAN: Controllable Image Synthesis with 3D Gaussians from Unposed Silhouettes
Youssef Alami Mejjati, Isa Milefchik, Aaron K Gokaslan, Oliver Wang, Kwang In Kim and James Tompkin
Paper  Supplemental  Code  Poster Session 4
372
[643]
360-Degree Gaze Estimation in the Wild Using Multiple Zoom Scales
Ashesh Ashesh, Chu-Song Chen and Hsuan-Tien Lin
Paper  Supplemental  Code  Poster Session 4
373
[686]
DEX: Domain Embedding Expansion for Generalized Person Re-identification
Phuay Wee Eugene Ang, Shan Lin and Alex Kot
Paper  Supplemental  Poster Session 4
374
[690]
Mitigating Mode Collapse by Sidestepping Catastrophic Forgetting
Karttikeya Mangalam and Rohin Garg
Paper  Supplemental  Code  Poster Session 4
375
[691]
Privacy Preserving for Medical Image Analysis via Non-Linear Deformation Proxy
Bach Kim, Jose Dolz, Christian Desrosiers and Pierre-Marc Jodoin
Paper  Supplemental  Poster Session 4
376
[692]
Depth-aware Object Segmentation and Grasp Detection for Robotic Picking Tasks
Stefan Ainetter, Christoph Böhm, Rohit Dhakate, Stephan Weiss and Friedrich Fraundorfer
Paper  Supplemental  Poster Session 4
377
[698]
Ray-ONet: Efficient 3D Reconstruction From A Single RGB Image
Wenjing Bian, Zirui Wang, Kejie Li and Victor Adrian Prisacariu
Paper  Supplemental  Code  Poster Session 4
378
[730]
Self-Supervised Monocular Depth Estimation with Internal Feature Fusion
Hang Zhou, David Greenwood and Sarah Taylor
Paper  Supplemental  Code  Poster Session 4
379
[735]
DeepSportLab: a Unified Framework for Ball Detection, Player Instance Segmentation and Pose Estimation in Team Sports Scenes
Seyed Abolfazl Ghasemzadeh, Gabriel Van Zandycke, Maxime Istasse, Niels Sayez, Amirafshar Moshtaghpour and Christophe De Vleeschouwer
Paper  Supplemental  Code  Poster Session 4
380
[737]
Visual Keyword Spotting with Attention
Prajwal K R, Liliane Momeni, Triantafyllos Afouras and Andrew Zisserman
Paper  Poster Session 4
381
[748]
Multimodal Semi-Supervised Learning for 3D Objects
Zhimin Chen, Longlong Jing, Yang Liang, YingLi Tian and Bing Li
Paper  Supplemental  Poster Session 4
382
[761]
Improving Face Recognition with Large Age Gaps by Learning to Distinguish Children
Jungsoo Lee, JooYeol Yun, Sunghyun Park, Yonggyu Kim and Jaegul Choo
Paper  Supplemental  Code  Poster Session 4
383
[772]
Bird’s Eye View Segmentation Using Lifted 2D Semantic Features
Isht Dwivedi, Srikanth Malla, Yi-Ting Chen and Behzad Dariush
Paper  Supplemental  Code  Poster Session 4
384
[777]
Decentralised Person Re-Identification with Selective Knowledge Aggregation
Shitong Sun, Guile Wu and Shaogang Gong
Paper  Poster Session 4
385
[794]
Weakly Supervised Semantic Segmentation: From Box to Tag and Back
Zongliang Ji and Olga Veksler
Paper  Supplemental  Code  Poster Session 4
386
[803]
Context-Aware Unsupervised Clustering for Person Search
Byeong-Ju Han, Kuhyeun Ko and Jae-Young Sim
Paper  Supplemental  Code  Poster Session 4
387
[812]
Hierarchical Graph Networks for 3D Human Pose Estimation
Han Li, Bowen Shi, Wenrui Dai, Yabo Chen, Botao Wang, Yu Sun, MIN GUO, Chenglin Li, Junni Zou and Hongkai Xiong
Paper  Supplemental  Poster Session 4
388
[817]
Local and Global Point Cloud Reconstruction for 3D Hand Pose Estimation
Ziwei Yu, Linlin Yang, Shicheng Chen and Angela Yao
Paper  Supplemental  Poster Session 4
389
[836]
Self-Supervised Learning of Image Scale and Orientation
Jongmin Lee, Yoonwoo Jeong and Minsu Cho
Paper  Supplemental  Code  Poster Session 4
390
[877]
Continuous Event-Line Constraint for Closed-Form Velocity Initialization
Xin Peng, Wanting Xu, Jiaqi Yang and Laurent Kneip
Paper  Supplemental  Poster Session 4
391
[902]
IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer
Paper  Supplemental  Poster Session 4
392
[911]
On Automatic Data Augmentation for 3D Point Cloud Classification
Wanyue Zhang, Xun Xu, Fayao Liu, Le Zhang and Chuan Sheng Foo
Paper  Supplemental  Poster Session 4
393
[926]
Unified 3D Mesh Recovery of Humans and Animals by Learning Animal Exercise
Youwang Kim, Ji-Yeon Kim, Kyungdon Joo and Tae-Hyun Oh
Paper  Supplemental  Poster Session 4
394
[929]
Weakly Supervised Training of Monocular 3D Object Detectors Using Wide Baseline Multi-view Traffic Camera Data
Matthew R Howe, Ian Reid and Jamie Mackenzie
Paper  Supplemental  Code  Poster Session 4
395
[931]
Discriminative Clue Alignment Network for Both Image- and Video-Based Person Re-Identification
Panwen Hu, Xinyu Zhou and Rui Huang
Paper  Poster Session 4
396
[936]
3D Flow Field Estimation around a Vehicle Using Convolutional Neural Networks
Fangge Chen and Kei Akasaka
Paper  Supplemental  Poster Session 4
397
[948]
DeepUME: Learning the Universal Manifold Embedding for Robust Point Cloud Registration
Natalie Lang and Joseph M Francos
Paper  Supplemental  Code  Poster Session 4
398
[997]
Self-Supervised Real-time Video Stabilization
Jinsoo Choi, Jaesik Park and In So Kweon
Paper  Supplemental  Poster Session 4
399
[998]
Two Heads are Better than One: Geometric-Latent Attention for Point Cloud Classification and Segmentation
Hanz Cuevas, Antonio-Javier Gallego and Robert B Fisher
Paper  Supplemental  Code  Poster Session 4
400
[1011]
Looking at the whole picture: constrained unsupervised anomaly segmentation
Julio Silva-Rodríguez, Valery Naranjo and Jose Dolz
Paper  Supplemental  Code  Poster Session 4
401
[1035]
GPRAR: Graph Convolutional Network based Pose Reconstruction and Action Recognition for Human Trajectory Prediction
Manh Huynh and Gita Alaghband
Paper  Supplemental  Code  Poster Session 4
402
[1043]
Learning to Deblur and Rotate Motion-Blurred Faces
Givi Meishvili, Attila Szabo, Simon Jenni and Paolo Favaro
Paper  Supplemental  Code  Poster Session 4
403
[1048]
Learning Query Expansion over the Nearest Neighbor Graph
Benjamin Klein and Lior Wolf
Paper  Poster Session 4
404
[1109]
Learning to Predict Convolutional Filters with Guidance for Conditional Image Generation
Lei Chen, Mengyao Zhai and Greg Mori
Paper  Supplemental  Poster Session 4
405
[1112]
3D-RETR: End-to-End Single and Multi-View 3D Reconstruction with Transformers
Zai Shi, Zhao Meng, Yiran Xing, Yunpu Ma and Roger Wattenhofer
Paper  Supplemental  Code  Poster Session 4
406
[1139]
Scan-IT: Domain segmentation of spatial transcriptomics images by graph neural network
Zixuan Cang, Xinyi Ning, Annika Nie, Min Xu and Jing Zhang
Paper  Supplemental  Code  Poster Session 4
407
[1141]
Distilling Dynamic Spatial Relation Network for Human Pose Estimation
Kewei Wu, Tao Wang, Zhao Xie and Dan Guo
Paper  Poster Session 4
408
[1157]
Diffeomorphism Matching for Fast Unsupervised Pretraining on Radiographs
Thanh Minh Huynh, Chanh D Tr Nguyen, Ta Duc Huy, Huyen Hoang, Trung Bui and QUOC HUNG TRUONG
Paper  Supplemental  Code  Poster Session 4
409
[1202]
Efficient Cross-Modal Retrieval via Deep Binary Hashing and Quantization
Yang Shi and Young Joo Chung
Paper  Supplemental  Poster Session 4
410
[1216]
Planar Shape Based Registration for Multi-modal Geometry
Muxingzi Li and Florent Lafarge
Paper  Supplemental  Poster Session 4
411
[1231]
Adaptive Content Feature Enhancement GAN for Multimodal Selfie to Anime Translation
Yuanming Li, Jeong-gi Kwak, Dongsik Yoon, Youngsaeng Jin, David K Han and Hanseok Ko
Paper  Supplemental  Poster Session 4
412
[1245]
HAT-Net: A Hierarchical Transformer Graph Neural Network for Grading of Colorectal Cancer Histology Images
Yihan Su, Yu Bai, Bo Zhang, Zheng Zhang and Wendong Wang
Paper  Poster Session 4
413
[1249]
DKMA-ULD: Domain Knowledge augmented Multi-head Attention based Robust Universal Lesion Detection
Manu Sheoran, Meghal Dani, Monika Sharma and Lovekesh Vig
Paper  Supplemental  Poster Session 4
414
[1277]
ASM-Net: Category-level Pose and Shape Estimation Using Parametric Deformation
Shuichi Akizuki and Manabu Hashimoto
Paper  Code  Poster Session 4
415
[1278]
SDNet: Unconstrained Object Structure Detector Network for In-Field Real-Time Crop Part Location And Phenotyping
Louis Lac, Jean-Pierre Da Costa, Marc Donias, Barna Keresztes and Marine Louargant
Paper  Code  Poster Session 4
416
[1299]
X Resolution Correspondence Networks
Georgi Tinchev, Shuda Li, Kai Han, David Mitchell and Rigas Kouskouridas
Paper  Supplemental  Code  Poster Session 4
417
[1321]
Stabilized Semi-Supervised Training for COVID Lesion Segmentation
Pranjal Sahu, Saikiran Kumar Vunnava and HONG QIN
Paper  Supplemental  Poster Session 4
418
[1334]
Towards Holistic Real-time Human 3D Pose Estimation using MocapNETs
Ammar Qammaz and Antonis A Argyros
Paper  Supplemental  Code  Poster Session 4
419
[1340]
Probabilistic Estimation of 3D Human Shape and Pose with a Semantic Local Parametric Model
Akash Sengupta, Ignas Budvytis and Roberto Cipolla
Paper  Supplemental  Poster Session 4
420
[1386]
WAN: Watermarking Attack Network
Seung-Hun Nam, IN JAE YU, Seung-Min Mun, Daesik Kim and Wonhyuk Ahn
Paper  Supplemental  Poster Session 4
421
[1387]
Robust Crowd Counting via Image Enhancement and Dynamic Feature Selection
Nayeong Kim and Suha Kwak
Paper  Supplemental  Poster Session 4
422
[1405]
Subpixel Heatmap Regression for Facial Landmark Localization
Adrian Bulat, Enrique Sanchez and Georgios Tzimiropoulos
Paper  Supplemental  Code  Poster Session 4
423
[1417]
Gaussian map predictions for 3D surface feature localisation and counting
Justin Le Louëdec and Grzegorz Cielniak
Paper  Code  Poster Session 4
424
[1431]
Multi-view Image-based Hand Geometry Refinement using Differentiable Monte Carlo Ray Tracing
Giorgos Karvounas, Nikolaos Kyriazis, Iason Oikonomidis, Aggeliki Tsoli and Antonis A Argyros
Paper  Supplemental  Poster Session 4
425
[1436]
Surround-view Free Space Boundary Detection with Polar Representation
Zidong Cao, Ang Li, Zhiliang Xiong and Zejian Yuan
Paper  Supplemental  Poster Session 4
426
[1451]
Duplicate Latent Representation Suppression for Multi-object Variational Autoencoders
Li Nanbo and Robert B Fisher
Paper  Supplemental  Poster Session 4
427
[1467]
Shape Feature Loss for Kidney Segmentation in 3D Ultrasound Images
Haithem Boussaid and Rouet Laurence
Paper  Poster Session 4
428
[1468]
Personalized One-Shot Lipreading for an ALS Patient
Bipasha Sen, Aditya Agarwal, Rudrabha Mukhopadhyay, Vinay Namboodiri and C.V. Jawahar
Paper  Poster Session 4
429
[1488]
OSS-Net: Memory Efficient High Resolution Semantic Segmentation of 3D Medical Data
Christoph Reich, Tim Prangemeier, Ozdemir Cetin and Heinz Koeppl
Paper  Code  Poster Session 4
430
[1502]
Pose-Transformation and Radial Distance Clustering for Unsupervised Person Re-identification
Siddharth Seth, Akash Sonth and Anirban Chakraborty
Paper  Supplemental  Poster Session 4
431
[1545]
AGCN: Adversarial Graph Convolutional Network for 3D Point Cloud Segmentation
Seunghoi Kim and Daniel Alexander
Paper  Poster Session 4
432
[1551]
SwinFGHash: Fine-grained Image Retrieval via Transformer-based Hashing Network
Di Lu, Jinpeng Wang, Ziyun Zeng, Bin Chen, Shudeng Wu and Shu-Tao Xia
Paper  Supplemental  Poster Session 4
433
[1605]
Cross-Modal Generative Augmentation for Visual Question Answering
Zixu Wang, Yishu Miao and Lucia Specia
Paper  Poster Session 4
434
[376]
Tensor Composition Net for Visual Relationship Prediction
Yuting Qiang, Yongxin Yang, Xueting Zhang, Yanwen Guo and Timothy Hospedales
Paper  Supplemental  Poster Session 4