
Integrating Visual Language Models with Vision Transformers enhances video action understanding by aligning spatio-temporal representations.


coremsg

enhancing-video-transformers-for-action-understanding-with-vlm-aided-training


Enhancing Video Transformers for Action Understanding with VLM-aided Training


title_rewrite


The author proposes a recursive video captioning model, Video ReCap, to efficiently process videos of varying lengths and generate captions at multiple hierarchy levels.


Recursive-Video-Captioning-Model-for-Long-Videos


Recursive Video Captioning Model for Long Videos
