Spatial-Temporal Synergic Residual Learning for Video Person Re-Identification
This addresses the problem of identifying individuals across video frames for applications like surveillance, but it appears incremental as it builds on existing re-identification methods with a novel network design.
The paper tackles video person re-identification by proposing the Spatial-Temporal Synergic Residual Network (STSRN) to learn robust features from video sequences, achieving superior performance on datasets like iLIDS-VID, PRID2011, and MARS compared to most state-of-the-art methods.
We tackle the problem of person re-identification in video setting in this paper, which has been viewed as a crucial task in many applications. Meanwhile, it is very challenging since the task requires learning effective representations from video sequences with heterogeneous spatial-temporal information. We present a novel method - Spatial-Temporal Synergic Residual Network (STSRN) for this problem. STSRN contains a spatial residual extractor, a temporal residual processor and a spatial-temporal smooth module. The smoother can alleviate sample noises along the spatial-temporal dimensions thus enable STSRN extracts more robust spatial-temporal features of consecutive frames. Extensive experiments are conducted on several challenging datasets including iLIDS-VID, PRID2011 and MARS. The results demonstrate that the proposed method achieves consistently superior performance over most of state-of-the-art methods.