ClipSum shows that frozen CLIP features outperform traditional CNN features and fine-tuned CLIP for instructional video summarization on YouCook2.
Proceedings of the Annual Meeting of the Association for Computational Linguistics (2020)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Multimodal Abstractive Summarization of Instructional Videos with Vision-Language Models
ClipSum shows that frozen CLIP features outperform traditional CNN features and fine-tuned CLIP for instructional video summarization on YouCook2.