CVPR

Digital Gimbal: End-to-end Deep Image Stabilization with Learnable Exposure Times

Omer Dahary, Matan Jacoby, Alex M. Bronstein

Comments CVPR 2021

Deep Parametric Shape Predictions using Distance Fields

Dmitriy Smirnov, Matthew Fisher, Vladimir G. Kim, Richard Zhang, Justin Solomon

Comments Accepted to CVPR 2020

Journal ref Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. (2020) 561-570

One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation

Zhengzhe Liu, Xiaojuan Qi, Chi-Wing Fu

Comments Accepted by CVPR 2021

Tracking Grow-Finish Pigs Across Large Pens Using Multiple Cameras

Aniket Shirke, Aziz Saifuddin, Achleshwar Luthra, Jiangong Li, Tawni Williams, Xiaodan Hu, Aneesh Kotnana, Okan Kocabalkanli, Narendra Ahuja, Angela Green-Miller, Isabella Condotta, Ryan N. Dilger, Matthew Caesar

Comments 6 pages, 4 figures, Accepted at the CVPR 2021 CV4Animals workshop

Square Root Bundle Adjustment for Large-Scale Reconstruction

Nikolaus Demmel, Christiane Sommer, Daniel Cremers, Vladyslav Usenko

Comments Accepted to CVPR 2021. Updated version corresponding to CVPR camera-ready. Formatting changes and minor tweaks to fit page requirements

DeFMO: Deblurring and Shape Recovery of Fast Moving Objects

Denys Rozumnyi, Martin R. Oswald, Vittorio Ferrari, Jiri Matas, Marc Pollefeys

Comments CVPR 2021 camera-ready

Journal ref 2021 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

End-to-end optimized image compression with competition of prior distributions

Benoit Brummer, Christophe De Vleeschouwer

Journal ref 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

A Bop and Beyond: A Second Order Optimizer for Binarized Neural Networks

Cuauhtemoc Daniel Suarez-Ramirez, Miguel Gonzalez-Mendoza, Leonardo Chang-Fernandez, Gilberto Ochoa-Ruiz, Mario Alberto Duran-Vega

Comments 9 pages, 12 figures, Preprint accepted to the LatinX in CV Research Workshop at CVPR'21

Graph Relation Transformer: Incorporating pairwise object features into the Transformer architecture

Michael Yang, Aditya Anantharaman, Zachary Kitowski, Derik Clive Robert

Comments Presented as poster in CVPR 2021 Visual Question Answering Workshop

Pre-Trained Image Processing Transformer

Hanting Chen, Yunhe Wang, Tianyu Guo, Chang Xu, Yiping Deng, Zhenhua Liu, Siwei Ma, Chunjing Xu, Chao Xu, Wen Gao

Comments CVPR 2021

MDMMT: Multidomain Multimodal Transformer for Video Retrieval

Maksim Dzabraev, Maksim Kalashnikov, Stepan Komkov, Aleksandr Petiushko

Journal ref CVPR Workshops 2021: 3354-3363

There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge

Francisco Rivera Valverde, Juana Valeria Hurtado, Abhinav Valada

Comments Accepted at CVPR 2021. Dataset, code and models are available at http://rl.uni-freiburg.de/research/multimodal-distill

Journal ref IEEE/ CVF International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11612-11621, 2021

MOPT: Multi-Object Panoptic Tracking

Juana Valeria Hurtado, Rohit Mohan, Wolfram Burgard, Abhinav Valada

Comments Code & models are available at http://rl.uni-freiburg.de/research/panoptictracking

Journal ref The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshop on Scalability in Autonomous Driving, 2020

Learnable Companding Quantization for Accurate Low-bit Neural Networks

Kohei Yamamoto

Comments Accepted at CVPR 2021

Journal ref Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 5029-5038

Fast Walsh-Hadamard Transform and Smooth-Thresholding Based Binary Layers in Deep Neural Networks

Hongyi Pan, Diaa Dabawi, Ahmet Enis Cetin

Comments The paper (v1) has been accepted to CVPR 2021 BiVision Workshop. We notice the final Conv2D is also a 1x1 convolution layer so we update the result with changing the layer in v2. In v3, we update citation 37 because its authorship changes. In v4, we propose the improved version of smooth thresholding called "weighted smooth thresholding"

iVPF: Numerical Invertible Volume Preserving Flow for Efficient Lossless Compression

Shifeng Zhang, Chen Zhang, Ning Kang, Zhenguo Li

Comments Accepted for CVPR 2021

ENSEI: Efficient Secure Inference via Frequency-Domain Homomorphic Convolution for Privacy-Preserving Visual Recognition

Song Bian, Tianchen Wang, Masayuki Hiromoto, Yiyu Shi, Takashi Sato

Comments 10 pages, 3 figures, in Proceedings of Conference on Computer Vision and Pattern Recognition (CVPR 2020)

Task Agnostic Robust Learning on Corrupt Outputs by Correlation-Guided Mixture Density Networks

Sungjoon Choi, Sanghoon Hong, Kyungjae Lee, Sungbin Lim

Comments Accepted to Computer Vision and Pattern Recognition (CVPR) 2020

Unrestricted Adversarial Attacks on ImageNet Competition

Yuefeng Chen, Xiaofeng Mao, Yuan He, Hui Xue, Chao Li, Yinpeng Dong, Qi-An Fu, Xiao Yang, Wenzhao Xiang, Tianyu Pang, Hang Su, Jun Zhu, Fangcheng Liu, Chao Zhang, Hongyang Zhang, Yichi Zhang, Shilong Liu, Chang Liu, Wenzhao Xiang, Yajie Wang, Huipeng Zhou, Haoran Lyu, Yidan Xu, Zixuan Xu, Taoyu Zhu, Wenjun Li, Xianfeng Gao, Guoqiu Wang, Huanqian Yan, Ying Guo, Chaoning Zhang, Zheng Fang, Yang Wang, Bingyang Fu, Yunfei Zheng, Yekui Wang, Haorong Luo, Zhen Yang

Comments CVPR-2021 AIC Phase VI Track2: Unrestricted Adversarial Attacks on ImageNet

A Transformer-based Cross-modal Fusion Model with Adversarial Training for VQA Challenge 2021

Ke-Han Lu, Bo-Han Fang, Kuan-Yu Chen

Comments CVPR 2021 Workshop: Visual Question Answering (VQA) Challenge

NAS-FCOS: Efficient Search for Object Detection Architectures

Ning Wang, Yang Gao, Hao Chen, Peng Wang, Zhi Tian, Chunhua Shen, Yanning Zhang

Comments 14 pages, 11 figures, journal extension of NAS-FCOS (CVPR 2020), accepted by IJCV. arXiv admin note: substantial text overlap with arXiv:1906.04423

Multi-Label Learning from Single Positive Labels

Elijah Cole, Oisin Mac Aodha, Titouan Lorieul, Pietro Perona, Dan Morris, Nebojsa Jojic

Comments CVPR 2021. Supplementary material included

On the benefits of defining vicinal distributions in latent space

Puneet Mangla, Vedant Singh, Shreyas Jayant Havaldar, Vineeth N Balasubramanian

Comments Accepted at Elsevier Pattern Recognition Letters (2021), Best Paper Award at CVPR 2021 Workshop on Adversarial Machine Learning in Real-World Computer Vision (AML-CV), Also accepted at ICLR 2021 Workshops on Robust-Reliable Machine Learning (Oral) and Generalization beyond the training distribution (Abstract)

Dense Relational Image Captioning via Multi-task Triple-Stream Networks

Dong-Jin Kim, Tae-Hyun Oh, Jinsoo Choi, In So Kweon

Comments IEEE TPAMI accepted. Journal extension of our CVPR 2019 paper ( arXiv:1903.05942 ). Source code : https://github.com/Dong-JinKim/DenseRelationalCaptioning

Learning Single/Multi-Attribute of Object with Symmetry and Group

Yong-Lu Li, Yue Xu, Xinyu Xu, Xiaohan Mao, Cewu Lu

Comments TPAMI, an extended version of SymNet (CVPR'20), a part of HAKE-Object. Code: https://github.com/DirtyHarryLYL/SymNet. arXiv admin note: substantial text overlap with arXiv:2004.00587

Center-based 3D Object Detection and Tracking

Tianwei Yin, Xingyi Zhou, Philipp Krähenbühl

Comments update nuScenes and Waymo results

Journal ref Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2021

SAIC_Cambridge-HuPBA-FBK Submission to the EPIC-Kitchens-100 Action Recognition Challenge 2021

Swathikiran Sudhakaran, Adrian Bulat, Juan-Manuel Perez-Rua, Alex Falcon, Sergio Escalera, Oswald Lanz, Brais Martinez, Georgios Tzimiropoulos

Comments Ranked third in the EPIC-Kitchens-100 Action Recognition Challenge @ CVPR 2021

The Challenge of Appearance-Free Object Tracking with Feedforward Neural Networks

Girik Malik, Drew Linsley, Thomas Serre, Ennio Mingolla

Comments Accepted at CVPR Workshop on Dynamic Neural Networks Meet Computer Vision

Supervised Contrastive Replay: Revisiting the Nearest Class Mean Classifier in Online Class-Incremental Continual Learning

Zheda Mai, Ruiwen Li, Hyunwoo Kim, Scott Sanner

Comments In Workshop on Continual Learning in Computer Vision at CVPR 2021

Normalized Diversification

Shaohui Liu, Xiao Zhang, Jianqiao Wangni, Jianbo Shi

Comments 12 pages, 9 figures, to appear in CVPR 2019