AI Paper Atlas

Research map / Video / Video-language understanding

Asymmetric Relation Consistency Reasoning for Video Relation Grounding

Huan Li, Ping Wei, Jiapeng Li, Zeyu Ma, Jiahui Shang, Nanning Zheng

ECCV 2022 · Video › Video-language understanding · approach: Video question answering · 5 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 asymmetric (conditional) subject-object reasoning (ablation)ARC · ImageNet-VidVRD (average over sIoU 0.3/0.5/0.7)AccR: 24.86 -> 26.42Improved
add asymmetric reasoning (ablation)ARC · ImageNet-VidVRD (sIoU=0.7)AccR: 16.13 -> 20.44Improved
add relation consistency KL loss (ablation)ARC · ImageNet-VidVRD (average over sIoU 0.3/0.5/0.7)AccR: 23.61 -> 26.42Improved
add relation consistency KL loss (ablation)ARC · ImageNet-VidVRD (average over sIoU 0.3/0.5/0.7)AccS: 35.99 -> 39.66Improved
add relation consistency KL loss (ablation)ARC · ImageNet-VidVRD (sIoU=0.7)AccO: 31.13 -> 33.39Improved
add relation-aware temporal reasoning (RTR) (ablation)ARC · ImageNet-VidVRD (average over sIoU 0.3/0.5/0.7)AccR: 23.86 -> 26.42Improved
add RTR (helps average and strict thresholds, slightly lower at sIoU=0.3) (ablation)ARC · ImageNet-VidVRD (sIoU=0.3)AccR: 33.03 -> 32.53Mixed
use IoU linking cost in inferenceARC · ImageNet-VidVRD (average over sIoU 0.3/0.5/0.7)AccR: 23.75 -> 26.42Improved
use IoU linking cost in inferencevRGV · ImageNet-VidVRD (average over sIoU 0.3/0.5/0.7)AccR: 20.54 -> 24.58Improved
replace transformer baseline with ARCOur baseline · ImageNet-VidVRD (average over sIoU 0.3/0.5/0.7)AccR: 24.38 -> 26.42Improved
ARC vs vRGV in zero-shot evaluationARC · ImageNet-VidVRD (zero-shot)AccR: 10.27 -> 11.19Improved
ARC vs vRGV in zero-shot subject accuracyARC · ImageNet-VidVRD (zero-shot)AccS: 18.94 -> 17.34Hurt

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