Embedding-based pair generation for contrastive representation learning in audio-visual surveillance data.
Saved in:
| Title: | Embedding-based pair generation for contrastive representation learning in audio-visual surveillance data. |
|---|---|
| Authors: | Wang, Wei-Cheng1, weicheng.wang@ugent.be, De Coninck, Sander1, Leroux, Sam1, Simoens, Pieter1 |
| Source: | Frontiers in Robotics & AI; 2025, p1-14, 14p |
| Database: | Applied Science & Technology Source |
| ISSN: | 22969144 |
|---|---|
| DOI: | 10.3389/frobt.2024.1490718 |
