Zero-Shot Temporal Action Detection by Learning Multimodal Prompts and Text-Enhanced Actionness

Reallocating and Evolving General Knowledge for Few-shot Learning

Y Su, X Liu, Z Huang, J He, R Hong… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Large-scale vision-language pre-trained models like CLIP are extensively employed in few-
shot tasks due to their robust generalization capabilities. Existing methods usually …
相关文章 所有 2 个版本

Text-Video Knowledge Guided Prompting for Weakly Supervised Temporal Action Localization

Y Shao, F Zhang, C Xu - … on Circuits and Systems for Video …, 2024 - ieeexplore.ieee.org
Weakly supervised temporal action localization (WTAL) aims to localize action instances
with only video-level labels for supervision. Recent methods convert category labels to …
相关文章