AI Paper Atlas

Research map / Video / Video-language understanding

EgoEverything: A Benchmark for Human Behavior–Inspired Long-Context Egocentric Video Understanding in AR Environment

Qiance Tang, Ziqi Wang, Jieyu Lin, Ziyun Li, Barbara Salvo, Sai Qian Zhang

ECCV 2026 · Video › Video-language understanding · approach: Egocentric video understanding · 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
restrict input to gaze crop (GC) instead of full frame (ablation)Videollama3-7b · EgoEverything MCQaccuracy: 49.1 -> 42.4Hurt
mask out gaze region (GM) instead of full frame (ablation)Videollama3-7b · EgoEverything MCQaccuracy: 49.1 -> 35.2Hurt
average-downsample frames to 10% resolution instead of full resolution (ablation)Gemini 1.5 pro · EgoEverything MCQaccuracy: 63.1 -> 58.4Hurt
use average downsampling instead of gaze crop (ablation)Gemini 1.5 pro · EgoEverything MCQaccuracy: 52.7 -> 58.4Improved
use gaze crop instead of gaze mask (ablation)Gemini 1.5 pro · EgoEverything MCQaccuracy: 37.7 -> 52.7Improved
add VideoMindPalace scene-graph pipeline over base VLMGemini 1.5 pro · EgoEverything MCQaccuracy: 63.1 -> 33.2Hurt
add AMEGO scene-graph pipeline over base VLMVideollama3-7b · EgoEverything MCQaccuracy: 49.1 -> 19.5Hurt
add saliency-map gaze promptingVideollama3-7b · EgoEverything MCQaccuracy: 49.1 -> 51.19Improved
increase recall interval from smallest 10% to largest 10% (ablation)Videollama3-7b · EgoEverything MCQaccuracy: 49 -> 33.3Hurt
move target object from 100-200 px to 600-700 px from gaze (ablation)Videollama3-7b · EgoEverything MCQaccuracy: 54.8 -> 31.4Hurt
increase target object bounding-box area threshold (ablation)evaluated VLMs · EgoEverything MCQaccuracyImproved
remove video frames (text-only input) (ablation)Videollama3-7b, Gemini, LongVA · EgoEverything MCQaccuracyHurt

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