Dense Interaction Learning for Video-Based Person Re-Identification

Tianyu He, Xin Jin, Xu Shen, Jianqiang Huang, Zhibo Chen, Xian-Sheng Hua; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 1490-1501

Abstract


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.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{He_2021_ICCV, author = {He, Tianyu and Jin, Xin and Shen, Xu and Huang, Jianqiang and Chen, Zhibo and Hua, Xian-Sheng}, title = {Dense Interaction Learning for Video-Based Person Re-Identification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {1490-1501} }