AI Paper Atlas

Research map / Video / Video-language understanding

SkillSight: Efficient First-Person Skill Assessment with Gaze

Chi Hsuan Wu, Ashutosh Kumar, Kristen Grauman

CVPR 2026 · Video › Video-language understanding · approach: Egocentric video understanding · 6 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 gaze distillation from video+gaze teacher to gaze-only model (ablation)SkillSight-S · Ego-Exo4D overallaccuracy: 37.0 -> 44.4Improved
add gaze distillation (student) (ablation)SkillSight-S · Multi-Sense Badmintonaccuracy: 42.3 -> 47.0Improved
add distillation + action token to gaze-only transformer (ablation)SkillSight-S · Expert-Novice Socceraccuracy: 66.0 -> 72.6Improved
add gaze-guided components (gaze attention, crops, gaze trajectory) to video modelSkillSight-T · Ego-Exo4D overallaccuracy: 45.5 -> 50.1 (vs TimeSformer)Improved
add gaze-guided componentsSkillSight-T · Ego-Exo4D Boulderingaccuracy: 28.9 vs 28.0 (TimeSformer)Mixed
gaze-only student instead of video modelSkillSight-S · Ego-Exo4D overallaccuracy: 44.4 vs 45.5 (TimeSformer), 9.5 mW vs 697.5 mWMixed
use gaze+video student replaced by gaze-only vs EgoDistill/EgoTriggerSkillSight-S · Ego-Exo4D overallaccuracy: 44.4 vs 42.6 (EgoDistill)Improved
add naive gaze-crop or gaze-pooled processing (EgoExoLearn, Beholder) instead of full-contextEgoExoLearn, Beholder · Ego-Exo4D overallaccuracy: 42.3 and 34.1 vs 45.5 (TimeSformer video-only)Hurt
add gaze when slicing vegetables (cooking)SkillSight · Ego-Exo4D Cookingaccuracy: SkillSight-S 44.1 vs Gaze-only 40.2 below TimeSformer 56.6No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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