Dense Interaction Learning for Video-based Person Re-identification

• Published in: 2021 IEEE/CVF International Conference on Computer Vision (ICCV) pp. 1470 - 1481
• Main Authors: He, Tianyu, Jin, Xin, Shen, Xu, Huang, Jianqiang, Chen, Zhibo, Hua, Xian-Sheng
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.10.2021
• Subjects: Architecture; Buildings; Computer architecture; Computer vision; Decoding; Feature extraction; Image and video retrieval; Task analysis; Video analysis and understanding; Vision applications and systems
• ISSN: 2380-7504
• DOI: 10.1109/ICCV48922.2021.00152

Video-based person re-identification (re-ID) aims at matching the same person across video clips. Efficiently exploiting multi-scale fine-grained features while building the structural interaction among them is pivotal for its success. In this paper, we propose a hybrid framework, Dense Interaction Learning (DenseIL), that takes the principal advantages of both CNN-based and Attention-based architectures to tackle video-based person re-ID difficulties. DenseIL contains a CNN encoder and a Dense Interaction (DI) decoder. The CNN encoder is responsible for efficiently extracting discriminative spatial features while the DI decoder is designed to densely model spatial-temporal inherent interaction across frames. Different from previous works, we additionally let the DI decoder densely attends to intermediate fine-grained CNN features and that naturally yields multi-grained spatial-temporal representation for each video clip. Moreover, we introduce Spatio-TEmporal Positional Embedding (STEP-Emb) into the DI decoder to investigate the positional relation among the spatial-temporal inputs. Our experiments consistently and significantly outperform all the state-of-the-art methods on multiple standard video-based person re-ID datasets.