AI Paper Atlas

Research map / Video / Video-language understanding

VidChapters-7M: Video Chapters at Scale

Antoine Yang, Arsha Nagrani, Ivan Laptev, Josef Sivic, Cordelia Schmid

NeurIPS 2023 · Video › Video-language understanding · approach: Dense video captioning · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add visual input to speech-only model (ablation)Vid2Seq · VidChapters-7M chapter generation (test)SODA_c: 10.5 -> 11.4Improved
replace speech input with visual-only input (ablation)Vid2Seq · VidChapters-7M chapter generation (test)SODA_c: 10.5 -> 5.5Hurt
add HowTo100M pretraining (speech+visual) (ablation)Vid2Seq · VidChapters-7M chapter generation (test)SODA_c: 10.6 -> 11.4Improved
add HowTo100M pretraining (speech only) (ablation)Vid2Seq · VidChapters-7M chapter generation (test)SODA_c: 10.2 -> 10.5Improved
add HowTo100M pretraining (visual only) (ablation)Vid2Seq · VidChapters-7M chapter generation (test)SODA_c: 3.1 -> 5.5Improved
add visual input to speech-only model (ablation)Vid2Seq · VidChapters-7M chapter title generation given GT boundaries (test)CIDEr: 105.3 -> 120.5Improved
add HowTo100M pretraining (ablation)Vid2Seq · VidChapters-7M chapter title generation given GT boundaries (test)CIDEr: 110.8 -> 120.5Improved
add VidChapters-7M (ASR+Chap.) pretraining on top of C4+HTM (ablation)Vid2Seq · YouCook2 (val) finetunedCIDEr: 53.2 -> 67.2Improved
add VidChapters-7M pretrainingPDVC · YouCook2 (val) finetunedCIDEr: 28.8 -> 34.7Improved
add VidChapters-7M ASR only to C4+HTM pretraining (ablation)Vid2Seq · YouCook2 (val) finetunedCIDEr: 53.2 -> 50.1Hurt
increase fraction of VidChapters-7M used for pretraining (1% to 10% to 100%) (ablation)Vid2Seq · YouCook2 (val) finetunedCIDEr: 52.7 -> 63.9 -> 67.2Improved
increase fraction of VidChapters-7M used for pretraining (1% to 10% to 100%) (ablation)Vid2Seq · YouCook2 (val) zero-shotCIDEr: 7.2 -> 11.5 -> 13.3Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy