AI Paper Atlas

Research map / Video / Video-language understanding

Towards Diverse Paragraph Captioning for Untrimmed Videos

Yuqing Song, Shizhe Chen, Qin Jin

CVPR 2021 · Video › Video-language understanding · approach: Dense video captioning · 33 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
Replace event-proposal captioning with direct paragraph generationVideo paragraph captioning · ActivityNet Captions ae-testCIDEr: 24.14 -> 27.36Improved
Add progressive memory exposure (ablation)Vanilla video paragraph captioner · ActivityNet ae-testDiv@1: 64.92 -> 66.79Improved
Add over-accessed memory decay (ablation)Vanilla video paragraph captioner · ActivityNet ae-testDiv@1: 64.92 -> 66.18Improved
Add both progressive memory exposure and over-accessed memory decay (ablation)Vanilla video paragraph captioner · ActivityNet ae-testCIDEr: 24.11 -> 25.65Improved
Add token-level high-frequency penalty (ablation)Captioner with both dynamic memory mechanisms · ActivityNet ae-testDiv@1: 67.90 -> 68.42Improved
Add CIDEr relevance reward in RL (ablation)Captioner with dynamic memories and token penalty · ActivityNet ae-testCIDEr: 26.55 -> 27.06Improved
Add phrase-level high-frequency penalty to the CIDEr relevance reward (ablation)Captioner with dynamic memories, token penalty, and relevance reward · ActivityNet ae-testDiv@1: 67.81 -> 68.33Improved
Add CIDEr relevance reward without phrase-level penalty (ablation)Captioner with dynamic memories and token penalty · ActivityNet ae-testDiv@1: 68.42 -> 67.81Hurt
Add video reconstruction loss for keyframe selection (ablation)MLE-trained keyframe-aware captioner · ActivityNet ae-test, keyframe ratio 0.5CIDEr: 25.47 -> 26.80Improved
Add sparsity loss for keyframe selection (ablation)MLE-trained keyframe-aware captioner · ActivityNet ae-test, keyframe ratio 0.5CIDEr: 25.47 -> 26.02Improved
Use learned keyframe selection instead of uniform interval samplingKeyframe-aware video encoder · ActivityNet ae-testCIDErImproved
Reduce the keyframe selection ratioKeyframe-aware video encoder · ActivityNet ae-testCIDErMixed

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