{
  "id": "2007.09314",
  "version": "v1",
  "published": "2020-07-18T03:08:13.000Z",
  "updated": "2020-07-18T03:08:13.000Z",
  "title": "Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification",
  "authors": [
    "Mang Ye",
    "Jianbing Shen",
    "David J. Crandall",
    "Ling Shao",
    "Jiebo Luo"
  ],
  "comment": "Accepted by ECCV20",
  "categories": [
    "cs.CV"
  ],
  "abstract": "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.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2020-07-18T03:08:13.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "visible-infrared person re-identification",
      "dynamic dual-attentive aggregation learning",
      "cross-modality pedestrian retrieval problem",
      "dual aggregation learning strategy",
      "dynamic dual aggregation learning"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}