EUVIMEDEUVIMED entdecken
Crossref

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

Xuehu Liu, Pingping Zhang, Chenyang Yu, Xuesheng Qian, Xiaoyun Yang, Huchuan Lu

IEEE Transactions on Intelligent Transportation Systems · 2024-09 · 25 (9) · 12818-12828

DOI: 10.1109/tits.2024.3386914 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2024-09. Verfasst von Xuehu Liu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 40-mal zitiert (Crossref) und nennt 57 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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, we propose a novel learning framework named Trigeminal Transformers (TMT) to tackle video-based person Re-ID. More specifically, we 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), we introduce the Transformer structure for information enhancement and aggregation. In our 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 our approach can obtain better performance than some other state-of-the-art approaches on four public Re-ID benchmarks.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China

Zitieren

APA

Liu, X., Zhang, P., Yu, C., Qian, X., Yang, X., & Lu, H. (2024). A Video Is Worth Three Views: Trigeminal Transformers for Video-Based Person Re-Identification. IEEE Transactions on Intelligent Transportation Systems, 25(9), 12818-12828. https://doi.org/10.1109/tits.2024.3386914

Vancouver

Liu X, Zhang P, Yu C, Qian X, Yang X, Lu H. A Video Is Worth Three Views: Trigeminal Transformers for Video-Based Person Re-Identification. IEEE Transactions on Intelligent Transportation Systems. 2024;25(9):12818-12828. doi:10.1109/tits.2024.3386914

BibTeX
@article{Liu2024,
  author = {Liu, Xuehu and Zhang, Pingping and Yu, Chenyang and Qian, Xuesheng and Yang, Xiaoyun and Lu, Huchuan},
  title = {A Video Is Worth Three Views: Trigeminal Transformers for Video-Based Person Re-Identification},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  year = {2024},
  volume = {25},
  number = {9},
  pages = {12818--12828},
  doi = {10.1109/tits.2024.3386914}
}
Kostenlos starten →