Follow the Saliency: Supervised Saliency for Retrieval-augmented Dense Video Captioning
A retrieval-augmented dense video captioning approach that injects supervised saliency signals into both the retrieval and generation stages.
#dense video captioning
Content tagged with "dense video captioning"
SAIL: Similarity-Aware Guidance and Inter-Caption Augmentation-based Learning for Weakly-Supervised Dense Video Captioning
Tackles weakly-supervised dense video captioning through similarity-aware guidance and inter-caption augmentation.
Sali4Vid: Saliency-Aware Video Reweighting and Adaptive Caption Retrieval for Dense Video Captioning
A dense video captioning framework that reweights video frames by saliency and adaptively retrieves relevant captions at inference time.
Retrieval-Augmented Dense Video Captioning and QA System
End-to-end pipeline for automated highlight extraction, dense captioning, and natural-language QA over long-form (1hr+) videos. Funded by Piaspace (2025).