每日论文速递：计算机视觉相关（3月18日更新版）

正文

请到「今天看啥」查看全文

[13] An Efficient Method for the Classification of Croplands in Scarce-Label Regions

作者 | Houtan Ghaffari

链接 | https://arxiv.org/abs/2103.09588

[14] The Invertible U-Net for Optical-Flow-free Video Interframe Generation

作者 | Saem Park, Donghun Han, Nojun Kwak

链接 | https://arxiv.org/abs/2103.09576

[15] Hierarchical Random Walker Segmentation for Large Volumetric Biomedical Data

作者 | Dominik Drees, Xiaoyi Jiang

链接 | https://arxiv.org/abs/2103.09564

[16] Multi-channel Deep Supervision for Crowd Counting

作者 | Bo Wei, Mulin Chen, Qi Wang, Xuelong Li

链接 | https://arxiv.org/abs/2103.09553

[17] Meta-learning of Pooling Layers for Character Recognition

作者 | Takato Otsuzuki, Heon Song, Seiichi Uchida, Hideaki Hayashi

链接 | https://arxiv.org/abs/2103.09528

[18] CNN Model & Tuning for Global Road Damage Detection

作者 | Rahul Vishwakarma, Ravigopal Vennelakanti (Hitachi America Ltd. R&D)

链接 | https://arxiv.org/abs/2103.09512

备注 | Invited submission to IEEE BigData Cup Global Road Damage Detection Challenge 2020

[19] Revisiting the Loss Weight Adjustment in Object Detection

作者 | Wenxin Yu, Bin Hu, Yucheng Hu, Tianxiang Lan, Yuanfan You, Dong Yin

链接 | https://arxiv.org/abs/2103.09488

[20] Disentangled Cycle Consistency for Highly-realistic Virtual Try-On

作者 | Chongjian Ge, Yibing Song, Yuying Ge, Han Yang, Wei Liu, Ping Luo

链接 | https://arxiv.org/abs/2103.09479

[21] Virtual Dress Swap Using Landmark Detection

作者 | Odar Zeynal, Saber Malekzadeh

链接 | https://arxiv.org/abs/2103.09475

[22] You Only Look One-level Feature

作者 | Qiang Chen, Yingming Wang, Tong Yang, Xiangyu Zhang, Jian Cheng, Jian Sun

链接 | https://arxiv.org/abs/2103.09460

备注 | Accepted by CVPR2021. We provide more details and add additional comparison with YOLOv4 in this version

[23] Learning Discriminative Prototypes with Dynamic Time Warping

作者 | Xiaobin Chang, Frederick Tung, Greg Mori

链接 | https://arxiv.org/abs/2103.09458

备注 | CVPR'21 preview, 10 pages, 8 figures

[24] Prediction-assistant Frame Super-Resolution for Video Streaming

作者 | Wang Shen, Wenbo Bao, Guangtao Zhai, Charlie L Wang, Jerry W Hu, Zhiyong Gao

链接 | https://arxiv.org/abs/2103.09455

[25] Adversarial Attacks on Camera-LiDAR Models for 3D Car Detection

作者 | Mazen Abdelfattah, Kaiwen Yuan, Z. Jane Wang, Rabab Ward

链接 | https://arxiv.org/abs/2103.09448

备注 | arXiv admin note: text overlap with arXiv:2101.10747

[26] Improved Deep Classwise Hashing With Centers Similarity Learning for Image Retrieval

作者 | Ming Zhang, Hong Yan

链接 | https://arxiv.org/abs/2103.09442

备注 | Accepted at ICPR'20

[27] Pose-GNN : Camera Pose Estimation System Using Graph Neural Networks

作者 | Ahmed Elmoogy, Xiaodai Dong, Tao Lu, Robert Westendorp, Kishore Reddy

链接 | https://arxiv.org/abs/2103.09435

[28] YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection

请到「今天看啥」查看全文