A Video Is Worth Three Views: Trigeminal Transformers for Video-Based Person Re-Identification

Video-based person Re-Identification (Re-ID) is a hot research topic in intelligent transportation systems, which aims to retrieve video sequences of the same person under non-overlapping surveillance cameras. Compared with static images, video sequences contain more visual information from multiple views, such as spatial and temporal views. However, previous Re-ID methods usually focus on single limited views, lacking diverse observations from different views. To capture richer perceptions and extract more comprehensive representations, the authors propose a novel learning framework named Trigeminal Transformers (TMT) to tackle video-based person Re-ID. More specifically, the authors first design a View-wise Projector (VP) to jointly transform raw videos from spatial, temporal and spatial-temporal views. In addition, inspired by the great success of Vision Transformers (ViT), the authors introduce the Transformer structure for information enhancement and aggregation. In the work, three Self-view Transformers (ST) are proposed to exploit the relationships of local features for information enhancement in spatial, temporal and spatial-temporal. Moreover, a Cross-view Transformer (CT) is proposed to aggregate the multi-view features for comprehensive representations. Experimental results indicate that the approach can obtain better performance than some other state-of-the-art approaches on four public Re-ID benchmarks.

• Record URL:
  • https://doi.org/10.1109/TITS.2024.3386914
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/oclc/41297384
• Supplemental Notes:
  • Copyright © 2024, IEEE.
• Authors:
  • Liu, X
  • Zhang, P
  • Yu, Chaofan
  • 0000-0002-7112-7821
  • Qian, X
  • Yang, X
  • Lu, Haoang
• Publication Date: 2024-9

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: pp 12818-12828
• Serial:
  • IEEE Transactions on Intelligent Transportation Systems
  • Volume: 25
  • Issue Number: 9
  • Publisher: Institute of Electrical and Electronics Engineers (IEEE)
  • ISSN: 1524-9050
  • Serial URL: http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=6979

Subject/Index Terms

• TRT Terms: Data quality; Detection and identification technologies; Human beings; Image analysis; Machine vision; Video
• Subject Areas: Safety and Human Factors; Security and Emergencies; Transportation (General);

Filing Info

• Accession Number: 01938905
• Record Type: Publication
• Files: TRIS
• Created Date: Dec 6 2024 2:15PM