← back to paper

Review history

arxiv: 2506.13458 · 2 revisions

Leveraging Vision-Language Pre-training for Human Activity Recognition in Still Images

1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 2.0
   123783 ms 6143 in 12997 out 2026-08-15T20:00:39.642840+00:00
2. 2026-08-07 REJECT MODERATE v1.4.0-alltime-deepseek-medium novelty 2.0
   144844 ms 6150 in 15207 out 2026-08-07T00:33:16.233681+00:00