Showing 2024Show all
2 papers · 1 filter
cs.CV2024
Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model Enhancement
Qianhan Feng, Wenshuo Li, Tong Lin +1
Vision-Language Models (VLMs) bring powerful understanding and reasoning capabilities to multimodal tasks. Meanwhile, the great need for capable aritificial intelligence on mobile…
cs.CV2024
Full-Stage Pseudo Label Quality Enhancement for Weakly-supervised Temporal Action Localization
Qianhan Feng, Wenshuo Li, Tong Lin +1
Weakly-supervised Temporal Action Localization (WSTAL) aims to localize actions in untrimmed videos using only video-level supervision. Latest WSTAL methods introduce pseudo label…