What is it about?
Video-based person re-identification refers to the process of retrieving a specific person's video track from multiple video tracks of various people, across different cameras. We propose a new video-based person re-identification algorithm based on attention and feature fusion, which significantly improves the identification accuracy compared to baseline algorithms. In addition, we compare it with some existing popular algorithms, showing that the proposed algorithm is competitive.
Featured Image
Photo by Alien system on Unsplash
Why is it important?
We presented the relevant theory and implementation details of the proposed algorithm and conducted experiments on a public dataset to validate its recognition performance. Additionally, we outlined the next steps for further research. We hope to draw more attention to the field of video-based person re-identification, which can better support the intelligence of video surveillance systems.
Perspectives
Looking forward to more people discovering
Aiping Wang
Read the Original
This page is a summary of: Video-based Person Re-identification Method based on Attention and Feature Fusion, November 2022, ACM (Association for Computing Machinery),
DOI: 10.1145/3577164.3577168.
You can read the full text:
Contributors
The following have contributed to this page
