AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Enhancing Video Summarization via Vision-Language Embedding

Bryan A. Plummer, Matthew Brown, Svetlana Lazebnik

CVPR 2017 · Vision-language and multimodal › Human and embodied modeling · approach: Language-grounded scene text and structure · 121 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
Add semantic representativeness and semantic interestingnessSubmod-V · UT EgocentricF-measure: 29.35 -> 34.15Improved
Add semantic representativeness (ablation)Submod-V · UT EgocentricF-measure: 29.35 -> 33.24Improved
Add semantic interestingness (ablation)Submod-V · UT EgocentricF-measure: 29.35 -> 31.58Improved
Replace both visual-only representativeness and interestingness with semantic versions (ablation)Submod-V · UT EgocentricF-measure: 29.35 -> 29.54No clear effect
Add semantic representativeness and semantic interestingness (ablation)Submod-V · UT EgocentricF-measure: 29.35 -> 33.50Improved
Train the vision-language embedding on Flickr30k rather than UTE (ablation)Submod-V + Both · UT EgocentricF-measure: 34.15 -> 33.50Hurt
Add semantic representativeness (ablation)Submod-V · TV EpisodesF-measure: 38.18 -> 40.90Mixed
Add semantic representativeness (ablation)Submod-V · TV EpisodesRecall: 33.47 -> 37.02Improved
Replace visual-only representativeness with semantic representativeness (ablation)Submod-V · TV EpisodesF-measure: 38.18 -> 37.29No clear effect
Train the embedding on TV Episodes rather than Flickr30k (ablation)Submod-V + Sem. Rep. · TV EpisodesF-measure: 39.87 -> 40.90Improved
Add unconstrained freeform text guidance at test timeFull model with UTE embedding · UT EgocentricF-measure: 34.15 -> 34.90Improved
Add unconstrained freeform text guidance at test timeFull model with TV Episodes embedding · TV EpisodesF-measure: 40.90 -> 41.18Improved

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