AI Paper Atlas

Research map / Video / Video-language understanding

Explainable Video Entailment With Grounded Visual Evidence

Junwen Chen, Yu Kong

ICCV 2021 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 10 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
add golden negative entities (grounding loss Lg) (ablation)entity grounding · VIOLIN testaccuracy: 66.53 -> 68.39Improved
add golden negative entities (grounding loss Lg) (ablation)entity grounding · VIOLIN testfake accuracy: 48.01 -> 57.25Improved
add temporal grounding guidance to entailment judgment (ablation)entailment judgment · VIOLIN testaccuracy: 67.60 -> 68.39Improved
add contradiction judgment from entity grounding module (ablation)entity grounding · VIOLIN testaccuracy: 66.72 -> 68.39Improved
add explanation regularizer Lr (multi-task) (ablation)entailment judgment · VIOLIN testaccuracy: 67.32 -> 68.39Improved
train explanation with only human-written statements instead of also adversarial ones (ablation)explanation module · VIOLIN testaccuracy: 67.65 -> 68.39Improved
explain with words instead of constituents (ablation)explanation module · VIOLIN testexplanation accuracy: 72.42 -> 75.20Improved
add explanation regularizer Lr (ablation)entailment judgment · VIOLIN testreal accuracy: 80.63 -> 79.52Mixed
replace VIOLIN with grounded-evidence model (C3D)entailment model · VIOLIN testaccuracy: 67.23 -> 68.15Improved
replace VIOLIN with grounded-evidence model (Resnet)entailment model · VIOLIN testaccuracy: 67.60 -> 68.39Improved
replace VIOLIN with grounded-evidence model (Resnet)entailment model · VIOLIN testadversarially sampled accuracy: 84.49 -> 84.94Improved
replace VIOLIN with grounded-evidence model (C3D)entailment model · VIOLIN testfake accuracy: 57.73 -> 57.08No 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