AI Paper Atlas

Research map / Video / Video-language understanding

EgoSAT: A Comprehensive Benchmark of Egocentric Streaming Interaction Understanding

Yijia Lei, Jinzhao Li, Yichi Zhang, Jiacheng Hua, Yin Li, Miao Liu

ECCV 2026 · Video › Video-language understanding · approach: Egocentric video understanding · 3 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 hand and gaze ROI-prioritised KV token caching (ablation)TimeChat-Online-7B · EgoSAT Now narration (MCQ)accuracy: 33.33 -> 36.47Improved
add hand and gaze ROI-prioritised KV token caching (ablation)TimeChat-Online-7B · EgoSAT Short-horizon retrieval (MCQ)accuracy: 37.84 -> 34.41Hurt
add hand and gaze ROI-prioritised KV token caching (ablation)TimeChat-Online-7B · EgoSAT Multi-step anticipation (MCQ)average accuracy: 26.01 -> 25.05Hurt
add hand and gaze ROI-prioritised KV token caching (ablation)TimeChat-Online-7B · EgoSAT Multi-step retrieval (MCQ)average accuracy: 31.63 -> 30.82Hurt
add lightweight LoRA task SFT on EgoSATTimeChat-Online-7B · EgoSAT Short-horizon anticipation (MCQ)accuracy: 29.72 -> 61.63Improved
add lightweight LoRA task SFT on EgoSATTimeChat-Online-7B · EgoSAT Now narration (MCQ)accuracy: 33.33 -> 45.59Improved
add lightweight LoRA task SFT on EgoSATROI-TimeChat-Online · EgoSAT Multi-step retrieval (MCQ)average accuracy: 30.82 -> 41.24Improved
add LoRA SFT with MCQ-only schemaTimeChat-Online-7B · EgoSAT Now state switchFg->bg accuracy: 0.00 -> 0.00No clear effect
remove visual input (blind text-only model) (ablation)Gemini 2.5 Pro · EgoSAT Short-horizon anticipation (MCQ)accuracy: 19.37 -> 29.92Improved
remove visual input (blind text-only model) (ablation)Qwen2.5-VL-32B · EgoSAT Short-horizon retrieval (MCQ)accuracy: 31.58 -> 50.86Improved
remove visual input (blind text-only model) (ablation)TimeChat-Online-7B · EgoSAT Short-horizon anticipation (MCQ)accuracy: 18.01 -> 29.72Improved
use offline Qwen2.5-VL-72B instead of online TimeChat-Online-7Bvideo LLM · EgoSAT Multi-step retrieval (MCQ)average accuracy: 31.63 -> 43.46Improved

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