CVPR

Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes

Zhengqi Li, Simon Niklaus, Noah Snavely, Oliver Wang

Comments CVPR 2021, Project Website: http://www.cs.cornell.edu/~zl548/NSFF/

Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation

Elad Richardson, Yuval Alaluf, Or Patashnik, Yotam Nitzan, Yaniv Azar, Stav Shapiro, Daniel Cohen-Or

Comments Accepted to CVPR 2021, project page available at https://eladrich.github.io/pixel2style2pixel/

Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization

Junting Pan, Siyu Chen, Mike Zheng Shou, Yu Liu, Jing Shao, Hongsheng Li

Comments Accepted in CVPR 2021

Ternary Feature Masks: zero-forgetting for task-incremental learning

Marc Masana, Tinne Tuytelaars, Joost van de Weijer

Comments To appear in the IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPR-W) on Continual Learning in Computer Vision (CLVision) 2021

Variational Relational Point Completion Network

Liang Pan, Xinyi Chen, Zhongang Cai, Junzhe Zhang, Haiyu Zhao, Shuai Yi, Ziwei Liu

Comments 15 pages, 13 figures, accepted to CVPR 2021 (Oral), project webpage: https://paul007pl.github.io/projects/VRCNet.html

Style-Aware Normalized Loss for Improving Arbitrary Style Transfer

Jiaxin Cheng, Ayush Jaiswal, Yue Wu, Pradeep Natarajan, Prem Natarajan

Comments Accepted as CVPR 2021 Oral Paper

T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval

Xiaohan Wang, Linchao Zhu, Yi Yang

Comments Accepted to CVPR 2021

Perceptual Loss for Robust Unsupervised Homography Estimation

Daniel Koguciuk, Elahe Arani, Bahram Zonooz

Comments Accepted at Image Matching: Local Features & Beyond (CVPR 2021 Workshop)

Comparing Representations in Tracking for Event Camera-based SLAM

Jianhao Jiao, Huaiyang Huang, Liang Li, Zhijian He, Yilong Zhu, Ming Liu

Comments 9 pages, 7 figures, accepted by CVPR Workshop 2021

Lighting, Reflectance and Geometry Estimation from 360$^{\circ}$ Panoramic Stereo

Junxuan Li, Hongdong Li, Yasuyuki Matsushita

Comments Accepted to CVPR 2021. Codes in: https://github.com/junxuan-li/LRG_360Panoramic

SE-SSD: Self-Ensembling Single-Stage Object Detector From Point Cloud

Wu Zheng, Weiliang Tang, Li Jiang, Chi-Wing Fu

Comments Accepted by CVPR 2021

Learning Semantic-Aware Dynamics for Video Prediction

Xinzhu Bei, Yanchao Yang, Stefano Soatto

Comments Paper accepted at CVPR 2021

An Efficient Approach for Anomaly Detection in Traffic Videos

Keval Doshi, Yasin Yilmaz

Comments Accepted to CVPR 2021 - AI City Workshop

Engineering Sketch Generation for Computer-Aided Design

Karl D. D. Willis, Pradeep Kumar Jayaraman, Joseph G. Lambourne, Hang Chu, Yewen Pu

Comments The 1st Workshop on Sketch-Oriented Deep Learning @ CVPR 2021

Removing Diffraction Image Artifacts in Under-Display Camera via Dynamic Skip Connection Network

Ruicheng Feng, Chongyi Li, Huaijin Chen, Shuai Li, Chen Change Loy, Jinwei Gu

Comments CVPR 2021 camera-ready version

LAFEAT: Piercing Through Adversarial Defenses with Latent Features

Yunrui Yu, Xitong Gao, Cheng-Zhong Xu

Comments Accepted as an oral paper in Conference on Computer Vision and Pattern Recognition (CVPR) 2021. 11 pages, 6 figures, 3 tables

Conditional Coding and Variable Bitrate for Practical Learned Video Coding

Théo Ladune, Pierrick Philippe, Wassim Hamidouche, Lu Zhang, Olivier Déforges

Journal ref CLIC workshop, CVPR 2021, Jun 2021, Nashville, United States

Surrogate Gradient Field for Latent Space Manipulation

Minjun Li, Yanghua Jin, Huachun Zhu

Comments 19 pages, 18 figures, CVPR 2021

Fashion-Guided Adversarial Attack on Person Segmentation

Marc Treu, Trung-Nghia Le, Huy H. Nguyen, Junichi Yamagishi, Isao Echizen

Comments Accepted to Workshop on Media Forensics, CVPR 2021. Project page: https://github.com/nii-yamagishilab/fashion_adv

Journal ref CVPR Workshops 2021

DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort

Yuxuan Zhang, Huan Ling, Jun Gao, Kangxue Yin, Jean-Francois Lafleche, Adela Barriuso, Antonio Torralba, Sanja Fidler

Comments Accepted to CVPR 2021 as an Oral paper. Webpage: https://nv-tlabs.github.io/datasetGAN/

Towards Extremely Compact RNNs for Video Recognition with Fully Decomposed Hierarchical Tucker Structure

Miao Yin, Siyu Liao, Xiao-Yang Liu, Xiaodong Wang, Bo Yuan

Comments This paper is a preprint that was accepted in CVPR'21. arXiv admin note: substantial text overlap with arXiv:2005.04366

Efficacy of Bayesian Neural Networks in Active Learning

Vineeth Rakesh, Swayambhoo Jain

Comments Published at CVPR Workshop on Learning From Limited or Imperfect Data (LLID) 2021

Video Class Agnostic Segmentation Benchmark for Autonomous Driving

Mennatullah Siam, Alex Kendall, Martin Jagersand

Comments Accepted in WAD workshop, CVPR 2021

Symmetric Parallax Attention for Stereo Image Super-Resolution

Yingqian Wang, Xinyi Ying, Longguang Wang, Jungang Yang, Wei An, Yulan Guo

Comments Accepted to NTIRE workshop at CVPR 2021. The first two authors contribute equally to this work

Trust Region Based Adversarial Attack on Neural Networks

Zhewei Yao, Amir Gholami, Peng Xu, Kurt Keutzer, Michael Mahoney

Journal ref CVPR 2019

SqueezeNext: Hardware-Aware Neural Network Design

Amir Gholami, Kiseok Kwon, Bichen Wu, Zizheng Tai, Xiangyu Yue, Peter Jin, Sicheng Zhao, Kurt Keutzer

Comments 12 Pages

Journal ref Design Automation Conference 2018 (and CVPR 2018 workshop)

Temporal Query Networks for Fine-grained Video Understanding

Chuhan Zhang, Ankush Gupta, Andrew Zisserman

Comments Accepted to CVPR 2021(Oral). Project page: http://www.robots.ox.ac.uk/~vgg/research/tqn/

OmniLayout: Room Layout Reconstruction from Indoor Spherical Panoramas

Shivansh Rao, Vikas Kumar, Daniel Kifer, Lee Giles, Ankur Mali

Comments Accepted at CVPR, OmniCV Workshop. 10 Pages, 9 Figures, 6 Tables

DANICE: Domain adaptation without forgetting in neural image compression

Sudeep Katakol, Luis Herranz, Fei Yang, Marta Mrak

Comments Accepted to CLIC Workshop at CVPR 2021

Contrastive Learning for Compact Single Image Dehazing

Haiyan Wu, Yanyun Qu, Shaohui Lin, Jian Zhou, Ruizhi Qiao, Zhizhong Zhang, Yuan Xie, Lizhuang Ma

Comments CVPR 2021 accepted paper. Code: https://github.com/GlassyWu/AECR-Net