SRL-CLIP: Efficient CLIP Video Adaptation via Structured Semantic Role Labels

Understand

Adapting CLIP for videos has gained popularity due to its semantic and rich representation.

• While CLIP is a good starting point, it typically undergoes post-pretraining (contrastive finetuning) on large video narration or caption datasets (e.g.
• HowTo100M, WebVid2.5M).
• However, such narrations or captions often lack comprehensive information needed to represent a video holistically.