AI Paper Atlas

Research map / Video / Video-language understanding

LongEgoRefer: A Benchmark for Long-Form Egocentric Video Referring Expression Comprehension

Shunya Kato, Taiki Miyanishi, Shuhei Kurita, Mahiro Ukai, Nakamasa Inoue, Chenhui Chu

ECCV 2026 · Video › Video-language understanding · approach: Egocentric video understanding · 0 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
increase max input frames from 64 to 500 (ablation)GPT-5 · LongEgoRefer (Ego4D, 1,498 queries)tIoU@0.5: 3.60 -> 12.55Improved
increase reasoning effort from minimal to high (ablation)GPT-5 · LongEgoRefer (Ego4D, 1,498 queries)tIoU@0.5: 8.7 -> 12.61Improved
increase reasoning effort from medium to high (ablation)GPT-5 · LongEgoRefer (Ego4D, 1,498 queries)tIoU@0.5: 12.55 -> 12.61No clear effect
use oracle temporal segmentation instead of GPT-5 temporal grounding (ablation)Grounded SAM2 · LongEgoRefer (Ego4D, 1,498 queries)mvIoU: 7.89 -> 43.54Improved
use oracle first-frame box prompt with SAM2.1 Base instead of Grounding DINO box (ablation)SAM2.1 · LongEgoRefer (Ego4D, 1,498 queries)mvIoU: 43.54 -> 67.21Improved
use SAM2.1 Large instead of Base with oracle prompt (ablation)SAM2.1 · LongEgoRefer (Ego4D, 1,498 queries)mvIoU: 67.21 -> 67.82No clear effect
replace Grounded-SAM2 with SAM3 as spatial stage (ablation)GPT-5 pipeline · LongEgoRefer (Ego4D, 1,498 queries)mvIoU: 7.89 -> 3.86Hurt
replace Grounded-SAM2 with SAM3 as spatial stage (ablation)Gemini 2.5 Pro pipeline · LongEgoRefer (Ego4D, 1,498 queries)mvIoU: 5.49 -> 2.23Hurt
evaluate on 6-minute EgoTracks clips instead of full 45-minute videosGemini 2.5 Pro · EgoTracks vs Ego4DmtIoU: +12.24 mtIoUImproved
scale from Gemini 2.5 Flash to Gemini 2.5 ProGemini · LongEgoRefer (Ego4D, 1,498 queries)mvIoU: 2.21 -> 5.49Improved
increase target appearance rate from (0,1] to (2,25] (ablation)GPT-5 · LongEgoRefer (Ego4D, 1,498 queries)mvIoU: 5.16 -> 13.54Improved
lengthen referring expression from (0,50] to (70,110] words (ablation)GPT-5 · LongEgoRefer (Ego4D, 1,498 queries)mvIoU: 10.29 -> 6.05Hurt

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