AI Paper Atlas

Research map / Video / Video-language understanding

An Efficient Framework for Dense Video Captioning

Maitreya Suin, A. N. Rajagopalan

AAAI 2020 · Video › Video-language understanding · approach: Dense video captioning · 52 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
learned frame selection instead of uniform sampling (15 frames) (ablation)RL frame-selection dense captioner (15 frames) · ActivityNet Captions valMETEOR: 5.44 -> 5.70Improved
learned frame selection instead of random sampling (15 frames) (ablation)RL frame-selection dense captioner (15 frames) · ActivityNet Captions valMETEOR: 5.20 -> 5.70Improved
learned frame selection instead of uniform sampling (25 frames) (ablation)RL frame-selection dense captioner (15 frames) · ActivityNet Captions valBLEU-4: 1.42 -> 1.35Mixed
add knowledge distillation loss (ablation)RL frame-selection dense captioner (15 frames) · ActivityNet Captions valMETEOR: 5.61 -> 5.70Improved
add global representation reward (ablation)RL frame-selection dense captioner (15 frames) · ActivityNet Captions valMETEOR: 5.32 -> 5.70Improved
add event proposal reward (ablation)RL frame-selection dense captioner (15 frames) · ActivityNet Captions valMETEOR: 5.07 -> 5.70Improved
add state encoder representation to proposal and caption modules (ablation)RL frame-selection dense captioner (15 frames) · ActivityNet Captions valMETEOR: 5.14 -> 5.70Improved
add event, global and distillation terms beyond language reward only (ablation)RL frame-selection dense captioner (15 frames) · ActivityNet Captions valMETEOR: 4.93 -> 5.70Improved
watch 25 frames instead of all frames (ablation)RL frame-selection dense captioner (15 frames) · ActivityNet Captions valMETEOR: 6.21 -> 6.23No clear effect
watch 8 frames instead of 25 frames (ablation)RL frame-selection dense captioner (15 frames) · ActivityNet Captions valMETEOR: 6.23 -> 4.98Hurt

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