CVPR - arXivDaily 期刊&会议

2105.06818 2021-05-17 cs.CV cs.MM

Collaborative Spatial-Temporal Modeling for Language-Queried Video Actor Segmentation

Tianrui Hui, Shaofei Huang, Si Liu, Zihan Ding, Guanbin Li, Wenguan Wang, Jizhong Han, Fei Wang

Comments Accepted by CVPR 2021

2105.06663 2021-05-17 cs.CV

Sketch2Model: View-Aware 3D Modeling from Single Free-Hand Sketches

Song-Hai Zhang, Yuan-Chen Guo, Qing-Wen Gu

Comments Accepted to CVPR 2021

2105.06623 2021-05-17 cs.CV

City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones

Chong Liu, Yuqi Zhang, Hao Luo, Jiasheng Tang, Weihua Chen, Xianzhe Xu, Fan Wang, Hao Li, Yi-Dong Shen

Comments CVPR 2021 AI CITY CHALLENGE City-Scale Multi-Camera Vehicle Tracking Top 1

2105.05712 2021-05-17 cs.CV cs.NE

Directional GAN: A Novel Conditioning Strategy for Generative Networks

Shradha Agrawal, Shankar Venkitachalam, Dhanya Raghu, Deepak Pai

Comments Accepted to AICC workshop at CVPR 2021

2103.14230 2021-05-17 cs.AI cs.CV cs.LG

Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution

Chi Zhang, Baoxiong Jia, Song-Chun Zhu, Yixin Zhu

Comments CVPR 2021 paper. Supplementary: http://wellyzhang.github.io/attach/cvpr21zhang_prae_supp.pdf Project: http://wellyzhang.github.io/project/prae.html

2011.12646 2021-05-17 cs.CV

Quantifying Explainers of Graph Neural Networks in Computational Pathology

Guillaume Jaume, Pushpak Pati, Behzad Bozorgtabar, Antonio Foncubierta-Rodríguez, Florinda Feroce, Anna Maria Anniciello, Tilman Rau, Jean-Philippe Thiran, Maria Gabrani, Orcun Goksel

Comments CVPR 2021

2105.06462 2021-05-14 cs.CV

Self-Supervised Collision Handling via Generative 3D Garment Models for Virtual Try-On

Igor Santesteban, Nils Thuerey, Miguel A. Otaduy, Dan Casas

Comments Accepted to CVPR 2021. Project website http://mslab.es/projects/SelfSupervisedGarmentCollisions

2105.06461 2021-05-14 cs.CV cs.AI cs.LG cs.MM

3D Spatial Recognition without Spatially Labeled 3D

Zhongzheng Ren, Ishan Misra, Alexander G. Schwing, Rohit Girdhar

Comments CVPR 2021

2105.06458 2021-05-14 cs.CV

High-Resolution Complex Scene Synthesis with Transformers

Manuel Jahn, Robin Rombach, Björn Ommer

Comments AI for Content Creation Workshop, CVPR 2021

2105.06407 2021-05-14 cs.CV cs.AI cs.GR

Deep Graphics Encoder for Real-Time Video Makeup Synthesis from Example

Robin Kips, Ruowei Jiang, Sileye Ba, Edmund Phung, Parham Aarabi, Pietro Gori, Matthieu Perrot, Isabelle Bloch

Comments CVPR 2021 Workshop AI for Content Creation

2105.06152 2021-05-14 cs.CV

When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks

Jiahang Wang, Sheng Jin, Wentao Liu, Weizhong Liu, Chen Qian, Ping Luo

Comments Accepted by CVPR 2021

2105.06047 2021-05-14 cs.CV cs.AI cs.LG

Compatibility-aware Heterogeneous Visual Search

Rahul Duggal, Hao Zhou, Shuo Yang, Yuanjun Xiong, Wei Xia, Zhuowen Tu, Stefano Soatto

Comments Accepted at CVPR 2021

2105.05847 2021-05-13 cs.CV cs.LG

Learning to Generate Novel Scene Compositions from Single Images and Videos

Vadim Sushko, Juergen Gall, Anna Khoreva

Comments The AI for Content Creation (AICC) workshop at CVPR 2021. The full 8-page version of this submission is available at arXiv:2103.13389

2105.05486 2021-05-13 cs.CV

TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text

Amanpreet Singh, Guan Pang, Mandy Toh, Jing Huang, Wojciech Galuba, Tal Hassner

Comments To appear in CVPR 2021. 15 pages, 7 figures. First three authors contributed equally. More info at https://textvqa.org/textocr

2012.00987 2021-05-13 cs.CV

PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Clouds

Yi Wei, Ziyi Wang, Yongming Rao, Jiwen Lu, Jie Zhou

Comments Accepted to CVPR 2021

2105.05312 2021-05-13 cs.CV

Incremental Few-Shot Instance Segmentation

Dan Andrei Ganea, Bas Boom, Ronald Poppe

Comments Accepted to CVPR 2021

2105.05226 2021-05-12 cs.CV

Home Action Genome: Cooperative Compositional Action Understanding

Nishant Rai, Haofeng Chen, Jingwei Ji, Rishi Desai, Kazuki Kozuka, Shun Ishizaka, Ehsan Adeli, Juan Carlos Niebles

Comments CVPR '21

2105.05217 2021-05-12 cs.CV

Representation Learning via Global Temporal Alignment and Cycle-Consistency

Isma Hadji, Konstantinos G. Derpanis, Allan D. Jepson

Comments accepted to CVPR 2021

2105.05207 2021-05-12 cs.CV

Rethinking of Radar's Role: A Camera-Radar Dataset and Systematic Annotator via Coordinate Alignment

Yizhou Wang, Gaoang Wang, Hung-Min Hsu, Hui Liu, Jenq-Neng Hwang

Comments 10 pages, 7 figures, 6 tables, CVPR 2021 Workshop on Autonomous Driving

2105.05066 2021-05-12 cs.CV

ChaLearn LAP Large Scale Signer Independent Isolated Sign Language Recognition Challenge: Design, Results and Future Research

Ozge Mercanoglu Sincan, Julio C. S. Jacques Junior, Sergio Escalera, Hacer Yalim Keles

Comments Preprint of the accepted paper at ChaLearn Looking at People Sign Language Recognition in the Wild Workshop at CVPR 2021

2105.04872 2021-05-12 cs.CV

EDPN: Enhanced Deep Pyramid Network for Blurry Image Restoration

Ruikang Xu, Zeyu Xiao, Jie Huang, Yueyi Zhang, Zhiwei Xiong

Comments Accepted at NTIRE Workshop, CVPR 2021. Ruikang and Zeyu contribute equally to this work

2105.04836 2021-05-12 cs.CV

Found a Reason for me? Weakly-supervised Grounded Visual Question Answering using Capsules

Aisha Urooj Khan, Hilde Kuehne, Kevin Duarte, Chuang Gan, Niels Lobo, Mubarak Shah

Comments IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021

2105.03596 2021-05-12 cs.CV

Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platforms

Wei Lou, Lei Xun, Amin Sabet, Jia Bi, Jonathon Hare, Geoff V. Merrett

Comments Accepted at CVPR ECV Workshop 2021

2007.08461 2021-05-12 cs.CV

How to trust unlabeled data? Instance Credibility Inference for Few-Shot Learning

Yikai Wang, Li Zhang, Yuan Yao, Yanwei Fu

Comments Journal extension of arXiv:2003.11853 that appears in CVPR 2020 Code and models are released at https://github.com/Yikai-Wang/ICI-FSL

2003.07848 2021-05-12 cs.CV

Learning to Structure an Image with Few Colors

Yunzhong Hou, Liang Zheng, Stephen Gould

Journal ref CVPR 2020

2105.04489 2021-05-11 cs.CV cs.CL cs.LG cs.SD eess.AS

Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions

Mathew Monfort, SouYoung Jin, Alexander Liu, David Harwath, Rogerio Feris, James Glass, Aude Oliva

Comments To appear at CVPR 2021

2105.04154 2021-05-11 cs.CV cs.AI

Unsupervised Human Pose Estimation through Transforming Shape Templates

Luca Schmidtke, Athanasios Vlontzos, Simon Ellershaw, Anna Lukens, Tomoki Arichi, Bernhard Kainz

Comments CVPR 2021 (poster). Project page: https://infantmotion.github.io/

2105.03570 2021-05-11 cs.CV

Domain-Specific Suppression for Adaptive Object Detection

Yu Wang, Rui Zhang, Shuo Zhang, Miao Li, YangYang Xia, XiShan Zhang, ShaoLi Liu

Comments Accepted in CVPR 2021

2105.03494 2021-05-11 cs.CV

The iWildCam 2021 Competition Dataset

Sara Beery, Arushi Agarwal, Elijah Cole, Vighnesh Birodkar

Comments FGVC8 Workshop at CVPR 2021. arXiv admin note: substantial text overlap with arXiv:2004.10340

2104.14852 2021-05-11 cs.CV

NTIRE 2021 Challenge on Video Super-Resolution

Sanghyun Son, Suyoung Lee, Seungjun Nah, Radu Timofte, Kyoung Mu Lee

Comments An official report for NTIRE 2021 Video Super-Resolution Challenge, in conjunction with CVPR 2021