Dynamic adaptive synergistic attention network for visible-infrared person re-identification
Linjie Sha, Shuli Cheng, Shuxian Liu · 2025
Read Dynamic adaptive synergistic attention network for visible-infrared person re-identification by Linjie Sha, Shuli Cheng, Shuxian Liu (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12738584.txt.
Description
Security cameras see in color by day and infrared by night, and matching the same person across both views is a core surveillance task. Linjie Sha and co-authors present a network built to close that gap. Its fusion module mixes the two image types adaptively, switching channels by content rather than by fixed rule.
A companion attention module reads channel context at several scales with cheap one-dimensional filters. A four-part loss, weighted by gradient analysis instead of guesswork, keeps the training goals in balance. On the RegDB benchmark the system hit 96.2 percent top-rank accuracy. Tests in dim light and across designs back the gains. The 2025 paper advances cross-modal person matching.
Catalog record
| CREATOR | Linjie Sha, Shuli Cheng, Shuxian Liu |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 85 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |