AI Paper Atlas

Research map / Video / Video segmentation and tracking

Less Is More: Learning Highlight Detection From Video Duration

Bo Xiong, Yannis Kalantidis, Deepti Ghadiyaram, Kristen Grauman

CVPR 2019 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 134 citations (OpenAlex)

Check 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
Use domain-specific rather than domain-agnostic Instagram trainingDuration-based highlight detector · YouTube HighlightsmAP: 0.505 -> 0.564Improved
Use domain-specific rather than domain-agnostic Instagram trainingDuration-based highlight detector · TVSumTop-5 mAP: 0.524 -> 0.563Improved
Add learned latent weighting of noisy ranking pairs (ablation)Duration-based highlight detector · YouTube HighlightsmAP: 0.425 -> 0.564Improved
Add learned latent weighting of noisy ranking pairs (ablation)Duration-based highlight detector · TVSummAP: 0.400 -> 0.563Improved
Replace learned, continuous input-conditioned pair weights with alternating binary latent selection (ablation)Duration-based highlight detector · YouTube HighlightsmAP: 0.458 -> 0.564Improved
Replace learned, continuous input-conditioned pair weights with alternating binary latent selection (ablation)Duration-based highlight detector · TVSummAP: 0.444 -> 0.563Improved
Increase training videos per domain from 1,000 to 10,000 (ablation)Ours-S · YouTube HighlightsmAP: +6.5%Improved
Increase training videos per domain from 1,000 to 10,000 (ablation)Ours-A · YouTube HighlightsmAP: +3.7%Improved
Use group size n=8 for pair-weight softmax (ablation)Duration-based highlight detector · YouTube Highlights and TVSummAPImproved
Vary short- and long-video duration cutoffs within the tested range (ablation)Duration-based highlight detector · YouTube Highlights and TVSummAPNo clear effect
Weight test pairs with the learned latent pair predictor (ablation)Duration-based ranking model · Held-out short-versus-long video segment pairssuccessful ranking rate: 58.2% -> 87.2%Improved
Train on YouTube8M instead of Instagram videosOurs-A · YouTube HighlightsmAP: 0.505 -> 0.317Hurt

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