WACV 2022

406 papers

Busy-Quiet Video Disentangling for Video Classification

Guoxi Huang, Adrian G. Bors

AuxAdapt: Stable and Efficient Test-Time Adaptation for Temporally Consistent Video Semantic Segmentation

Yizhe Zhang, Shubhankar Borse, Hong Cai, Fatih Porikli

Hyper-Convolution Networks for Biomedical Image Segmentation

Tianyu Ma, Adrian V. Dalca, Mert R. Sabuncu

A Riemannian Framework for Analysis of Human Body Surface

Emery Pierson, Mohamed Daoudi, Alice-Barbara Tumpach

Geometrically Adaptive Dictionary Attack on Face Recognition

Junyoung Byun, Hyojun Go, Changick Kim

EZCrop: Energy-Zoned Channels for Robust Output Pruning

Rui Lin, Jie Ran, Dongpeng Wang, King Hung Chiu, Ngai Wong

To Miss-Attend Is to Misalign! Residual Self-Attentive Feature Alignment for Adapting Object Detectors

Vaishnavi Khindkar, Chetan Arora, Vineeth N Balasubramanian, Anbumani Subramanian, Rohit Saluja

Self-Supervised Video Representation Learning With Cross-Stream Prototypical Contrasting

Martine Toering, Ioannis Gatopoulos, Maarten Stol, Vincent Tao Hu

EdgeConv With Attention Module for Monocular Depth Estimation

Minhyeok Lee, Sangwon Hwang, Chaewon Park, Sangyoun Lee

Data InStance Prior (DISP) in Generative Adversarial Networks

Puneet Mangla, Nupur Kumari, Mayank Singh, Balaji Krishnamurthy, Vineeth N. Balasubramanian

Tensor-Based Non-Rigid Structure From Motion

Stella Graßhof, Sami Sebastian Brandt

M3DETR: Multi-Representation, Multi-Scale, Mutual-Relation 3D Object Detection With Transformers

Tianrui Guan, Jun Wang, Shiyi Lan, Rohan Chandra, Zuxuan Wu

Deep Two-Stream Video Inference for Human Body Pose and Shape Estimation

Ziwen Li, Bo Xu, Han Huang, Cheng Lu, Yandong Guo

EllipsoidNet: Ellipsoid Representation for Point Cloud Classification and Segmentation

Yecheng Lyu, Xinming Huang, Ziming Zhang

Improving Fractal Pre-Training

Connor Anderson, Ryan Farrell

Progressive Automatic Design of Search Space for One-Shot Neural Architecture Search

Xin Xia, Xuefeng Xiao, Xing Wang, Min Zheng

Lightweight Monocular Depth With a Novel Neural Architecture Search Method

Lam Huynh, Phong Nguyen, Jiri Matas, Esa Rahtu, Janne Heikkila

SC-UDA: Style and Content Gaps Aware Unsupervised Domain Adaptation for Object Detection

Fuxun Yu, Di Wang, Yinpeng Chen, Nikolaos Karianakis, Tong Shen

Single-Photon Camera Guided Extreme Dynamic Range Imaging

Yuhao Liu, Felipe Gutierrez-Barragan, Atul Ingle, Mohit Gupta, Andreas Velten

MEGAN: Memory Enhanced Graph Attention Network for Space-Time Video Super-Resolution

Chenyu You, Lianyi Han, Aosong Feng, Ruihan Zhao, Hui Tang

Transferable 3D Adversarial Textures Using End-to-End Optimization

Camilo Pestana, Naveed Akhtar, Nazanin Rahnavard, Mubarak Shah, Ajmal Mian

Measuring Hidden Bias Within Face Recognition via Racial Phenotypes

Seyma Yucer, Furkan Tektas, Noura Al Moubayed, Toby P. Breckon

MaskSplit: Self-Supervised Meta-Learning for Few-Shot Semantic Segmentation

Mustafa Sercan Amac, Ahmet Sencan, Bugra Baran, Nazli Ikizler-Cinbis, Ramazan Gokberk Cinbis

Geometry-Aware Hierarchical Bayesian Learning on Manifolds

Yonghui Fan, Yalin Wang

Online Continual Learning via Candidates Voting

Jiangpeng He, Fengqing Zhu

MTGLS: Multi-Task Gaze Estimation With Limited Supervision

Shreya Ghosh, Munawar Hayat, Abhinav Dhall, Jarrod Knibbe

Modeling Dynamic Target Deformation in Camera Calibration

Annika Hagemann, Moritz Knorr, Christoph Stiller

Meta-Learning for Multi-Label Few-Shot Classification

Christian Simon, Piotr Koniusz, Mehrtash Harandi

Mixed-Dual-Head Meets Box Priors: A Robust Framework for Semi-Supervised Segmentation

Chenshu Chen, Tao Liu, Wenming Tan, Shiliang Pu

YOLO-ReT: Towards High Accuracy Real-Time Object Detection on Edge GPUs

Prakhar Ganesh, Yao Chen, Yin Yang, Deming Chen, Marianne Winslett

TA-Net: Topology-Aware Network for Gland Segmentation

Haotian Wang, Min Xian, Aleksandar Vakanski

CoordiNet: Uncertainty-Aware Pose Regressor for Reliable Vehicle Localization

Arthur Moreau, Nathan Piasco, Dzmitry Tsishkou, Bogdan Stanciulescu, Arnaud de La Fortelle

Fusion Point Pruning for Optimized 2D Object Detection With Radar-Camera Fusion

Lukas Stäcker, Philipp Heidenreich, Jason Rambach, Didier Stricker

PoP-Net: Pose Over Parts Network for Multi-Person 3D Pose Estimation From a Depth Image

Yuliang Guo, Zhong Li, Zekun Li, Xiangyu Du, Shuxue Quan

Mesh Convolutional Autoencoder for Semi-Regular Meshes of Different Sizes

Sara Hahner, Jochen Garcke

A Semi-Supervised Generalized VAE Framework for Abnormality Detection Using One-Class Classification

Renuka Sharma, Satvik Mashkaria, Suyash P. Awate

Complete Face Recovery GAN: Unsupervised Joint Face Rotation and De-Occlusion From a Single-View Image

Yeong-Joon Ju, Gun-Hee Lee, Jung-Ho Hong, Seong-Whan Lee

Leaky Gated Cross-Attention for Weakly Supervised Multi-Modal Temporal Action Localization

Jun-Tae Lee, Sungrack Yun, Mihir Jain

Interpretable Semantic Photo Geolocation

Jonas Theiner, Eric Muller-Budack, Ralph Ewerth

How and What To Learn: Taxonomizing Self-Supervised Learning for 3D Action Recognition

Amor Ben Tanfous, Aimen Zerroug, Drew Linsley, Thomas Serre

Few-Shot Object Detection by Attending to Per-Sample-Prototype

Hojun Lee, Myunggi Lee, Nojun Kwak

Shape-Coded ArUco: Fiducial Marker for Bridging 2D and 3D Modalities

Lilika Makabe, Hiroaki Santo, Fumio Okura, Yasuyuki Matsushita

Geometry-Inspired Top-K Adversarial Perturbations

Nurislam Tursynbek, Aleksandr Petiushko, Ivan Oseledets

DAD: Data-Free Adversarial Defense at Test Time

Gaurav Kumar Nayak, Ruchit Rawal, Anirban Chakraborty

Learning Temporal Video Procedure Segmentation From an Automatically Collected Large Dataset

Lei Ji, Chenfei Wu, Daisy Zhou, Kun Yan, Edward Cui

Hierarchical Modeling for Task Recognition and Action Segmentation in Weakly-Labeled Instructional Videos

Reza Ghoddoosian, Saif Sayed, Vassilis Athitsos

Ortho-Shot: Low Displacement Rank Regularization With Data Augmentation for Few-Shot Learning

Uche Osahor, Nasser M. Nasrabadi

Multi-Domain Semantic Segmentation With Overlapping Labels

Petra Bevandic, Marin Orsic, Ivan Grubišić, Josip Saric, Siniša Šegvić

Multi-Stream Dynamic Video Summarization

Mohamed Elfeki, Liqiang Wang, Ali Borji

Active Learning for Improved Semi-Supervised Semantic Segmentation in Satellite Images

Shasvat Desai, Debasmita Ghose

Spatiotemporal Initialization for 3D CNNs With Generated Motion Patterns

Hirokatsu Kataoka, Kensho Hara, Ryusuke Hayashi, Eisuke Yamagata, Nakamasa Inoue

Controlled GAN-Based Creature Synthesis via a Challenging Game Art Dataset - Addressing the Noise-Latent Trade-Off

Vaibhav Vavilala, David Forsyth

Perceptual Consistency in Video Segmentation

Yizhe Zhang, Shubhankar Borse, Hong Cai, Ying Wang, Ning Bi

Adversarial Branch Architecture Search for Unsupervised Domain Adaptation

Luca Robbiano, Muhammad Rameez Ur Rahman, Fabio Galasso, Barbara Caputo, Fabio Maria Carlucci

Learning From the CNN-Based Compressed Domain

Zhenzhen Wang, Minghai Qin, Yen-Kuang Chen

Cross-Modal Adversarial Reprogramming

Paarth Neekhara, Shehzeen Hussain, Jinglong Du, Shlomo Dubnov, Farinaz Koushanfar

Modeling Aleatoric Uncertainty for Camouflaged Object Detection

Jiawei Liu, Jing Zhang, Nick Barnes

Intelligent Camera Selection Decisions for Target Tracking in a Camera Network

Anil Sharma, Saket Anand, Sanjit K Kaul

Self-Supervised Shape Alignment for Sports Field Registration

Feng Shi, Paul Marchwica, Juan Camilo Gamboa Higuera, Michael Jamieson, Mehrsan Javan

Channel Pruning via Lookahead Search Guided Reinforcement Learning

Zi Wang, Chengcheng Li

Learning To Reconstruct 3D Non-Cuboid Room Layout From a Single RGB Image

Cheng Yang, Jia Zheng, xili dai, Rui Tang, Yi Ma

Human-Aided Saliency Maps Improve Generalization of Deep Learning

Aidan Boyd, Kevin W. Bowyer, Adam Czajka

Seeing Implicit Neural Representations As Fourier Series

Nuri Benbarka, Timon Höfer, Hamd ul-Moqeet Riaz, Andreas Zell

WEPDTOF: A Dataset and Benchmark Algorithms for In-the-Wild People Detection and Tracking From Overhead Fisheye Cameras

Ozan Tezcan, Zhihao Duan, Mertcan Cokbas, Prakash Ishwar, Janusz Konrad

Natural Language Video Moment Localization Through Query-Controlled Temporal Convolution

Lingyu Zhang, Richard J. Radke

Multi-Branch Neural Networks for Video Anomaly Detection in Adverse Lighting and Weather Conditions

Sam Leroux, Bo Li, Pieter Simoens

Recursive Contour-Saliency Blending Network for Accurate Salient Object Detection

Yun Yi Ke, Takahiro Tsubono

MUGL: Large Scale Multi Person Conditional Action Generation With Locomotion

Shubh Maheshwari, Debtanu Gupta, Ravi Kiran Sarvadevabhatla

Hole-Robust Wireframe Detection

Naejin Kong, Kiwoong Park, Harshith Goka

Data Augmented 3D Semantic Scene Completion With 2D Segmentation Priors

Aloisio Dourado, Frederico Guth, Teofilo de Campos

Preventing Catastrophic Forgetting and Distribution Mismatch in Knowledge Distillation via Synthetic Data

Kuluhan Binici, Nam Trung Pham, Tulika Mitra, Karianto Leman

Robust Lane Detection via Expanded Self Attention

Minhyeok Lee, Junhyeop Lee, Dogyoon Lee, Woojin Kim, Sangwon Hwang

Hyperspectral Image Super-Resolution With RGB Image Super-Resolution as an Auxiliary Task

Ke Li, Dengxin Dai, Luc Van Gool

Mending Neural Implicit Modeling for 3D Vehicle Reconstruction in the Wild

Shivam Duggal, Zihao Wang, Wei-Chiu Ma, Sivabalan Manivasagam, Justin Liang

Compensation Tracker: Reprocessing Lost Object for Multi-Object Tracking

Zhibo Zou, Junjie Huang, Ping Luo

How Good Is Your Explanation? Algorithmic Stability Measures To Assess the Quality of Explanations for Deep Neural Networks

Thomas FEL, David Vigouroux, Remi Cadene, Thomas Serre

Hierarchical Proxy-Based Loss for Deep Metric Learning

Zhibo Yang, Muhammet Bastan, Xinliang Zhu, Douglas Gray, Dimitris Samaras

Improving Single-Image Defocus Deblurring: How Dual-Pixel Images Help Through Multi-Task Learning

Abdullah Abuolaim, Mahmoud Afifi, Michael S. Brown

Efficient Counterfactual Debiasing for Visual Question Answering

Camila Kolling, Martin More, Nathan Gavenski, Eduardo Pooch, Otávio Parraga

Multi-Task Classification of Sewer Pipe Defects and Properties Using a Cross-Task Graph Neural Network Decoder

Joakim Bruslund Haurum, Meysam Madadi, Sergio Escalera, Thomas B. Moeslund

Multi-Domain Incremental Learning for Semantic Segmentation

Prachi Garg, Rohit Saluja, Vineeth N Balasubramanian, Chetan Arora, Anbumani Subramanian

Reconstructing Training Data From Diverse ML Models by Ensemble Inversion

Qian Wang, Daniel Kurz

Single Image Object Counting and Localizing Using Active-Learning

Inbar Huberman-Spiegelglas, Raanan Fattal

CFLOW-AD: Real-Time Unsupervised Anomaly Detection With Localization via Conditional Normalizing Flows

Denis Gudovskiy, Shun Ishizaka, Kazuki Kozuka

SporeAgent: Reinforced Scene-Level Plausibility for Object Pose Refinement

Dominik Bauer, Timothy Patten, Markus Vincze

Digital and Physical-World Attacks on Remote Pulse Detection

Jeremy Speth, Nathan Vance, Patrick Flynn, Kevin W. Bowyer, Adam Czajka

Visual Understanding of Complex Table Structures From Document Images

Sachin Raja, Ajoy Mondal, C.V. Jawahar

Short-Term Solar Irradiance Prediction From Sky Images With a Clear Sky Model

Huiyu Gao, miaomiao Liu

T-Net: A Resource-Constrained Tiny Convolutional Neural Network for Medical Image Segmentation

Tariq M. Khan, Antonio Robles-Kelly, Syed S. Naqvi

PPCD-GAN: Progressive Pruning and Class-Aware Distillation for Large-Scale Conditional GANs Compression

Duc Minh Vo, Akihiro Sugimoto, Hideki Nakayama

FT-DeepNets: Fault-Tolerant Convolutional Neural Networks With Kernel-Based Duplication

Iljoo Baek, Wei Chen, Zhihao Zhu, Soheil Samii, Raj Rajkumar

DG-Labeler and DGL-MOTS Dataset: Boost the Autonomous Driving Perception

Yiming Cui, Zhiwen Cao, Yixin Xie, Xingyu Jiang, Feng Tao

Transductive Weakly-Supervised Player Detection Using Soccer Broadcast Videos

Chris Andrew Gadde, C.V. Jawahar

Self-Supervised Learning of Domain Invariant Features for Depth Estimation

Hiroyasu Akada, Shariq Farooq Bhat, Ibraheem Alhashim, Peter Wonka

Self-Supervised Test-Time Adaptation on Video Data

Fatemeh Azimi, Sebastian Palacio, Federico Raue, Jörn Hees, Luca Bertinetto

ForeSI: Success-Aware Visual Navigation Agent

Mahdi Kazemi Moghaddam, Ehsan Abbasnejad, Qi Wu, Javen Qinfeng Shi, Anton van den Hengel

Monocular Depth Estimation With Adaptive Geometric Attention

Taher Naderi, Amir Sadovnik, Jason Hayward, Hairong Qi

Registration of Human Point Set Using Automatic Key Point Detection and Region-Aware Features

Amar Maharjan, Xiaohui Yuan

Auto White-Balance Correction for Mixed-Illuminant Scenes

Mahmoud Afifi, Marcus A. Brubaker, Michael S. Brown

Facial Attribute Transformers for Precise and Robust Makeup Transfer

Zhaoyi Wan, Haoran Chen, Jie An, Wentao Jiang, Cong Yao