BiCnet-TKS: Learning Efficient Spatial-Temporal Representation for Video Person Re-Identification
This work addresses the problem of efficient and accurate person re-identification in videos for surveillance and security applications, representing an incremental improvement with computational gains.
The paper tackles video person re-identification by proposing BiCnet-TKS, an efficient spatial-temporal representation that uses a bilateral complementary network and temporal kernel selection to capture detailed and contextual features, achieving state-of-the-art performance with about 50% less computation on multiple benchmarks.
In this paper, we present an efficient spatial-temporal representation for video person re-identification (reID). Firstly, we propose a Bilateral Complementary Network (BiCnet) for spatial complementarity modeling. Specifically, BiCnet contains two branches. Detail Branch processes frames at original resolution to preserve the detailed visual clues, and Context Branch with a down-sampling strategy is employed to capture long-range contexts. On each branch, BiCnet appends multiple parallel and diverse attention modules to discover divergent body parts for consecutive frames, so as to obtain an integral characteristic of target identity. Furthermore, a Temporal Kernel Selection (TKS) block is designed to capture short-term as well as long-term temporal relations by an adaptive mode. TKS can be inserted into BiCnet at any depth to construct BiCnetTKS for spatial-temporal modeling. Experimental results on multiple benchmarks show that BiCnet-TKS outperforms state-of-the-arts with about 50% less computations. The source code is available at https://github.com/ blue-blue272/BiCnet-TKS.