CVPR - arXivDaily 期刊&会议

2105.06993 2021-10-04 cs.CV

Omnimatte: Associating Objects and Their Effects in Video

Erika Lu, Forrester Cole, Tali Dekel, Andrew Zisserman, William T. Freeman, Michael Rubinstein

Comments CVPR 2021 Oral. Project webpage: https://omnimatte.github.io/. Added references

2109.12530 2021-09-28 cs.CV

Structure-Preserving Image Super-Resolution

Cheng Ma, Yongming Rao, Jiwen Lu, Jie Zhou

Comments Accepted by T-PAMI. Journal version of arXiv:2003.13081 (CVPR 2020)

2006.06666 2021-09-28 cs.CV cs.CL

VirTex: Learning Visual Representations from Textual Annotations

Karan Desai, Justin Johnson

Comments CVPR 2021. [v3: better captioning results on fixing beam search bug]

1910.01523 2021-09-27 cs.LG cs.NE

ReNAS:Relativistic Evaluation of Neural Architecture Search

Yixing Xu, Yunhe Wang, Kai Han, Yehui Tang, Shangling Jui, Chunjing Xu, Chang Xu

Comments CVPR 2021, Oral

2106.02036 2021-09-23 cs.CV cs.AI cs.LG cs.MM

Anticipative Video Transformer

Rohit Girdhar, Kristen Grauman

Comments ICCV 2021. Ranked #1 in CVPR'21 EPIC-Kitchens-100 Action Anticipation challenge. Webpage/code/models: http://facebookresearch.github.io/AVT

2109.10688 2021-09-23 cs.CV

Finding Facial Forgery Artifacts with Parts-Based Detectors

Steven Schwarcz, Rama Chellappa

Comments Accepted into the CVPR Workshop on Media Forensics 2021

2105.10678 2021-09-23 cs.CV

Video-based Person Re-identification without Bells and Whistles

Chih-Ting Liu, Jun-Cheng Chen, Chu-Song Chen, Shao-Yi Chien

Comments This paper was accepted by CVPR 2021 Biometrics Workshop

2109.10060 2021-09-22 cs.CV

DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers

Changlin Li, Guangrun Wang, Bing Wang, Xiaodan Liang, Zhihui Li, Xiaojun Chang

Comments Extension of the CVPR 2021 oral paper (CVPR2021/html/Li_Dynamic_Slimmable_Network_CVPR_2021_paper.html" target="_blank" rel="noopener">https://openaccess.thecvf.com/content/CVPR2021/html/Li_Dynamic_Slimmable_Network_CVPR_2021_paper.html)

2101.05796 2021-09-17 cs.CV cs.LG eess.IV

DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flows

Valentin Wolf, Andreas Lugmayr, Martin Danelljan, Luc Van Gool, Radu Timofte

Comments CVPR 2021 Oral

2109.06875 2021-09-16 cs.CV

Multi-Scale Aligned Distillation for Low-Resolution Detection

Lu Qi, Jason Kuen, Jiuxiang Gu, Zhe Lin, Yi Wang, Yukang Chen, Yanwei Li, Jiaya Jia

Comments In CVPR 2021

1909.12205 2021-09-15 cs.LG cs.CV stat.ML

Adaptive Binary-Ternary Quantization

Ryan Razani, Grégoire Morin, Vahid Partovi Nia, Eyyüb Sari

Journal ref CVPR 2021 BiVision Workshop

2109.05346 2021-09-14 cs.CV cs.AI

BGT-Net: Bidirectional GRU Transformer Network for Scene Graph Generation

Naina Dhingra, Florian Ritter, Andreas Kunz

Comments 8 pages, 7 supplementary pages

Journal ref Journal-ref: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition pages: 2150--2159 year: 2021

2011.07491 2021-09-14 cs.CV cs.LG eess.IV

Anomaly Detection in Video via Self-Supervised and Multi-Task Learning

Mariana-Iuliana Georgescu, Antonio Barbalau, Radu Tudor Ionescu, Fahad Shahbaz Khan, Marius Popescu, Mubarak Shah

Comments Accepted at CVPR 2021. Main paper and supplementary are both included

2103.16874 2021-09-13 cs.CV

VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization

Seunghwan Choi, Sunghyun Park, Minsoo Lee, Jaegul Choo

Comments 21 pages; project page: https://psh01087.github.io/VITON-HD; accepted to CVPR 2021; code URL added, references formatted

2006.06664 2021-09-09 cs.CV cs.LG

Quasi-Dense Similarity Learning for Multiple Object Tracking

Jiangmiao Pang, Linlu Qiu, Xia Li, Haofeng Chen, Qi Li, Trevor Darrell, Fisher Yu

Comments CVPR 2021 oral paper; Multiple object tracking on large-scale datasets

2109.02749 2021-09-08 cs.CV cs.LG

Pano3D: A Holistic Benchmark and a Solid Baseline for $360^o$ Depth Estimation

Georgios Albanis, Nikolaos Zioulis, Petros Drakoulis, Vasileios Gkitsas, Vladimiros Sterzentsenko, Federico Alvarez, Dimitrios Zarpalas, Petros Daras

Comments Presented at the OmniCV CVPR 2021 workshop. Code, models, data and demo at https://vcl3d.github.io/Pano3D/

2006.14580 2021-09-08 cs.CV cs.CR cs.LG

Backdoor Attacks Against Deep Learning Systems in the Physical World

Emily Wenger, Josephine Passananti, Arjun Bhagoji, Yuanshun Yao, Haitao Zheng, Ben Y. Zhao

Comments Accepted to the 2021 Conference on Computer Vision and Pattern Recognition (CVPR 2021); 14 pages

2109.01999 2021-09-07 eess.IV cs.CV cs.MM

Image Compression with Recurrent Neural Network and Generalized Divisive Normalization

Khawar Islam, L. Minh Dang, Sujin Lee, Hyeonjoon Moon

Comments Accpeted at IEEE CVPR Workshop

2006.10187 2021-09-07 cs.CV

TearingNet: Point Cloud Autoencoder to Learn Topology-Friendly Representations

Jiahao Pang, Duanshun Li, Dong Tian

Comments Accepted at CVPR 2021

2104.09315 2021-09-06 cs.CV cs.LG

A Mathematical Analysis of Learning Loss for Active Learning in Regression

Megh Shukla, Shuaib Ahmed

Comments Accepted: 2021 IEEE CVPR Workshop on Fair, Data Efficient and Trusted Computer Vision

2004.01314 2021-09-06 cs.CV cs.RO

Towards Better Generalization: Joint Depth-Pose Learning without PoseNet

Wang Zhao, Shaohui Liu, Yezhi Shu, Yong-Jin Liu

Comments To appear in CVPR 2020

2104.03954 2021-09-01 cs.CV cs.GR

De-rendering the World's Revolutionary Artefacts

Shangzhe Wu, Ameesh Makadia, Jiajun Wu, Noah Snavely, Richard Tucker, Angjoo Kanazawa

Comments CVPR 2021. Project page: https://sorderender.github.io/

2106.15058 2021-08-31 cs.CV cs.LG

Improving Transferability of Adversarial Patches on Face Recognition with Generative Models

Zihao Xiao, Xianfeng Gao, Chilin Fu, Yinpeng Dong, Wei Gao, Xiaolu Zhang, Jun Zhou, Jun Zhu

Comments Accpeted by CVPR 2021. Based on the camera ready version, some typos are fixed

2010.08719 2021-08-27 cs.CV cs.AI

Cascaded Refinement Network for Point Cloud Completion with Self-supervision

Xiaogang Wang, Marcelo H Ang, Gim Hee Lee

Comments Accepted by PAMI. Extended version of the following paper: Cascaded Refinement Network for Point Cloud Completion. CVPR 2020. arXiv link: arXiv:2004.03327

2003.12473 2021-08-27 eess.IV cs.CV

Augmenting Colonoscopy using Extended and Directional CycleGAN for Lossy Image Translation

Shawn Mathew, Saad Nadeem, Sruti Kumari, Arie Kaufman

Comments CVPR 2020. **First two authors contributed equally to this work

2108.10606 2021-08-25 cs.CV cs.DM

Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Paths

Andrea Hornakova, Timo Kaiser, Paul Swoboda, Michal Rolinek, Bodo Rosenhahn, Roberto Henschel

Comments ICCV 2021. Short version published at CVPR 2021 RVSU workshop CameraReady/paper_V3.pdf" target="_blank" rel="noopener">https://omnomnom.vision.rwth-aachen.de/data/RobMOTS/workshop/papers/9/CameraReady/paper_V3.pdf . Implementation available at https://github.com/LPMP/LPMP and https://github.com/TimoK93/ApLift

2104.09248 2021-08-24 cs.CV cs.LG

LSPnet: A 2D Localization-oriented Spacecraft Pose Estimation Neural Network

Albert Garcia, Mohamed Adel Musallam, Vincent Gaudilliere, Enjie Ghorbel, Kassem Al Ismaeil, Marcos Perez, Djamila Aouada

Comments 9 pages, 5 figures, published at AI4Space 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

Journal ref Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (2021) p. 2048-2056

2103.06422 2021-08-24 cs.CV

Holistic 3D Scene Understanding from a Single Image with Implicit Representation

Cheng Zhang, Zhaopeng Cui, Yinda Zhang, Bing Zeng, Marc Pollefeys, Shuaicheng Liu

Comments Published in CVPR 2021

2103.02396 2021-08-24 cs.CV

$S^3$: Learnable Sparse Signal Superdensity for Guided Depth Estimation

Yu-Kai Huang, Yueh-Cheng Liu, Tsung-Han Wu, Hung-Ting Su, Yu-Cheng Chang, Tsung-Lin Tsou, Yu-An Wang, Winston H. Hsu

Comments CVPR 2021

2011.11036 2021-08-24 cs.CV

Interpreting Super-Resolution Networks with Local Attribution Maps

Jinjin Gu, Chao Dong

Comments Accepted by CVPR 2021