出品 | 深度学习这件小事公众号如需转载,请联系后台授权 计算机视觉(10月4日更新版) [1] Video Temporal Relationship Mining for Data-Efficient Person Re-identification作者 | Siyu Chen, Dengjie Li, Lishuai Gao, Fan Liang, Wei Zhang, Lin Ma链接 | https://arxiv.org/abs/2110.00549 [2] Self-Supervised Decomposition, Disentanglement and Prediction of Video Sequences while Interpreting Dynamics: A Koopman Perspective作者 | Armand Comas, Sandesh Ghimire, Haolin Li, Mario Sznaier, Octavia Camps链接 | https://arxiv.org/abs/2110.00547 [3] Self-supervised Secondary Landmark Detection via 3D Representation Learning作者 | Praneet C. Bala, Jan Zimmermann, Hyun Soo Park, Benjamin Y. Hayden链接 | https://arxiv.org/abs/2110.00543 [4] TEACh: Task-driven Embodied Agents that Chat作者 | Aishwarya Padmakumar, Jesse Thomason, Ayush Shrivastava, Patr
………………………………