AI Paper Atlas

Research map / Video / Video-language understanding

Learning Consistent Temporal Grounding between Related Tasks in Sports Coaching

Arushi Rai, Adriana Kovashka

ECCV 2026 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 1 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 dual-pathway self-consistency training (full method) (ablation)PerceptionLM-8B finetuned · Exactaccuracy: 84.5 -> 87.5Improved
add dual-pathway self-consistency training (full method) (ablation)PerceptionLM-8B finetuned · FitnessQAaccuracy: 74.1 -> 88.2Improved
add dual-pathway self-consistency training (full method) (ablation)PerceptionLM-8B finetuned · ExpertAFBERTScore: 37.5 -> 38.4Improved
redistribute attention proportionally over ground-truth keyframes (ablation)PerceptionLM-8B (manual head) · EgoExo4D split of VidDiffBenchaccuracy: 65.8 -> 71.8Improved
select heads by visual non-sink ratio instead of visual attention sum (ablation)keyframe attention redistribution · EgoExo4D split of VidDiffBenchaccuracy: 69.2 -> 73.4Improved
match unmatched heads with Hungarian algorithm instead of random assignment (ablation)head matching · Exactaccuracy: 83.0 -> 87.5Improved
match unmatched heads with Hungarian algorithm instead of discarding them (ablation)head matching · FitnessQAaccuracy: 81.3 -> 88.2Improved
share the same layer across pathways instead of flexible verification layer (ablation)L_consistency · Exactaccuracy: 83.0 -> 87.5Improved
use verification task instead of summarization as the related task (ablation)L_consistency · Exactaccuracy: 69.5 -> 87.5Improved
use K=5 heads instead of larger K (ablation)head selection · Exactaccuracy: 63.5 -> 87.5Improved
add L_consistency to L_ce and L_entropy (ablation)self-consistency training · Exactaccuracy: 77.5 -> 87.5Improved
add L_entropy to L_ce and L_consistency (ablation)self-consistency training · ExpertAFBERTScore: 36.8 -> 38.3Improved

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