AI Paper Atlas

Research map / Video / Video-language understanding

Visual Semantic Role Labeling for Video Understanding

Arka Sadhu, Tanmay Gupta, Mark Yatskar, Ram Nevatia, Aniruddha Kembhavi

CVPR 2021 · Video › Video-language understanding · approach: Long video understanding · 57 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 SlowFast rather than I3D for verb predictionVidSitu verb classification · VidSitu TestRec@5Improved
Pretrain on Kinetics (ablation)VidSitu verb classifiers · VidSituRec@5: ≈10 to 16 pointsImproved
Add a Fast pathway to Slow+NL (ablation)Slow+NL verb classifier · VidSitu TestAcc@1: 29.03 -> 46.37Improved
Add Non-Local blocks to I3D without Kinetics pretraining (ablation)I3D verb classifier · VidSitu TestAcc@1: 31.91 -> 31.43Hurt
Add Non-Local blocks to Kinetics-pretrained I3D (ablation)Kinetics-pretrained I3D verb classifier · VidSitu TestAcc@1: 29.87 -> 38.42Improved
Condition role prediction on video features (ablation)Semantic role prediction · VidSitu TestCIDEr: 36.48 -> 44.95Improved
Contextualize events with a transformer encoder (ablation)Vid TxDec role predictor · VidSitu TestCIDEr: 44.95 -> 47.25Improved
Use I3D rather than SlowFast visual features for role prediction (ablation)Vid TxEncDec · VidSitu TestCIDEr: 47.25 -> 48.51Improved
Add verb descriptions to video-only relation prediction (ablation)VidSitu event relation classifier · VidSitu TestMacro-Acc: 30.97 -> 32.89Improved
Add argument descriptions after including verb descriptions (ablation)VidSitu event relation classifier · VidSitu TestMacro-Acc: 32.89 -> 32.98No clear effect

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