每日论文速递：计算机视觉相关（4月6日更新版）

正文

请到「今天看啥」查看全文

[13] Exploring the ability of CNNs to generalise to previously unseen scales over wide scale ranges

作者 | Ylva Jansson, Tony Lindeberg

链接 | https://arxiv.org/pdf/2004.01536

[14] RANSAC-Flow: generic two-stage image alignment

作者 | Xi Shen, François Darmon, Alexei A. Efros, Mathieu Aubry

链接 | https://arxiv.org/pdf/2004.01526

[15] Two-Stream AMTnet for Action Detection

作者 | Suman Saha, Gurkirt Singh, Fabio Cuzzolin

链接 | https://arxiv.org/pdf/2004.01494

[16] Cell Segmentation and Tracking using Distance Transform Predictions and Movement Estimation with Graph-Based Matching

作者 | Tim Scherr, Katharina Löffler, Moritz Böhland, Ralf Mikut

链接 | https://arxiv.org/pdf/2004.01486

备注 | algorithms used for the Cell Tracking Challenge competition at IEEE International Symposium on Biomedical Imaging (ISBI) 2020

[17] Gradient Centralization: A New Optimization Technique for Deep Neural Networks

作者 | Hongwei Yong, Jianqiang Huang, Xiansheng Hua, Lei Zhang

链接 | https://arxiv.org/pdf/2004.01461

[18] Self-Paced Deep Regression Forests with Consideration on Underrepresented Samples

作者 | Lili Pan, Shijie Ai, Yazhou Ren, Zenglin Xu

链接 | https://arxiv.org/pdf/2004.01459

[19] Disassembling Object Representations without Labels

作者 | Zunlei Feng, Xinchao Wang, Yongming He, Yike Yuan, Xin Gao, Mingli Song

链接 | https://arxiv.org/pdf/2004.01426

[20] Demographic Bias: A Challenge for Fingervein Recognition Systems?

作者 | P. Drozdowski, B. Prommegger, G. Wimmer, R. Schraml, C. Rathgeb, A. Uhl, C. Busch

链接 | https://arxiv.org/pdf/2004.01418

备注 | 5 pages, 2 figures, 8 tables. Submitted to European Signal Processing Conference (EUSIPCO) -- special session on bias in biometrics

[21] TEA: Temporal Excitation and Aggregation for Action Recognition

作者 | Yan Li, Bin Ji, Xintian Shi, Jianguo Zhang, Bin Kang, Limin Wang

链接 | https://arxiv.org/pdf/2004.01398

备注 | CVPR2020.

[22] LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention

作者 | Junbo Yin, Jianbing Shen, Chenye Guan, Dingfu Zhou, Ruigang Yang

链接 | https://arxiv.org/pdf/2004.01389

项目链接 | https://github.com/yinjunbo/3DVID

备注 | Accepted to CVPR 2020.

[23] Effective Fusion of Deep Multitasking Representations for Robust Visual Tracking

作者 | Seyed Mojtaba Marvasti-Zadeh, Hossein Ghanei-Yakhdan, Shohreh Kasaei, Kamal Nasrollahi, Thomas B. Moeslund

链接 | https://arxiv.org/pdf/2004.01382

备注 | 2020 Springer.

[24] Sequential Learning for Domain Generalization

作者 | Da Li, Yongxin Yang, Yi-Zhe Song, Timothy Hospedales

链接 | https://arxiv.org/pdf/2004.01377

[25] FairALM: Augmented Lagrangian Method for Training Fair Models with Little Regret

作者 | Vishnu Suresh Lokhande, Aditya Kumar Akash, Sathya N. Ravi, Vikas Singh

链接 | https://arxiv.org/pdf/2004.01355

[26] Deep White-Balance Editing

请到「今天看啥」查看全文