Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification

By Mang Ye, Jianbing Shen, David J. Crandall, Ling Shao, Jiebo Luo. European Conference on Computer Vision, 2020

493 citations recorded by the source corpus.

Visible-infrared person re-identification (VI-ReID) is a challenging cross-modality pedestrian retrieval problem. Due to the large intra-class variations and cross-modality discrepancy with large amount of sample noise, it is difficult to learn discriminative part features. Existing VI-ReID methods instead tend to learn global representations, which have limited discriminability and weak robustness to noisy images. In this paper, we propose a novel dynamic dual-attentive aggregation (DDAG) learning method by mining both intra-modality part-level and cross-modality graph-level contextual cues for VI-ReID. We propose an intra-modality weighted-part attention module to extract discriminative part-aggregated features, by imposing the domain knowledge on the part relationship mining. To enhance robustness against noisy samples, we introduce cross-modality graph structured attention to reinforce the representation with the contextual relations across the two modalities. We also develop a parameter-free dynamic dual aggregation learning strategy to adaptively integrate the two components in a progressive joint training manner. Extensive experiments demonstrate that DDAG outperforms the state-of-the-art methods under various settings.

View Paper: https://www.semanticscholar.org/paper/2dd42e92b9aca3aa74edba3d449c540b390f6916

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

  1. Wei Tang
  2. Bo Du
  3. Weijian Ruan
  4. Fazhi He
  5. Y. Liu
  6. Yansong Duan
  7. Mike Zheng Shou
  8. Tongzhen Si

Citations in the corpus