AI Paper Atlas

Research map / Video / Video-language understanding

GuideMe: Benchmarking Multi-Domain Task Guidance and Intervention in Streaming Video

FANG LIU, Jinpeng Chen, Ke Xu, Yuhao LIU, Huankang Guan, Xudong LU, Yang Bo, Gerhard P. Hancke, Rui Liu, Rynson Lau

ECCV 2026 · Video › Video-language understanding · approach: Video LLMs with fine-grained understanding

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
evaluate on error events instead of instruction eventsGemini 3 Pro · GuideMe-TestsF1: 42.0 -> 33.8Hurt
evaluate on error events instead of instruction eventsDoubao-Seed-1.8 · GuideMe-TestsF1: 49.6 -> 41.9Hurt
fine-tune Qwen3-VL-8B on GuideMe train splitQwen3-VL-8B · GuideMe-TestsF1: 35.7 -> 39.7Improved
fine-tune Qwen3-VL-8B on GuideMe train splitQwen3-VL-8B · GuideMe-TestPartly Correct rate: 50.5 -> 35.3Hurt
fine-tune Qwen3-VL-8B on GuideMe train splitQwen3-VL-8B · GuideMe-Testbehavior Score: 31.9 -> 42.1Improved
scale Qwen3-VL from 8B to 30B-A3BQwen3-VL · GuideMe-TestsF1: 35.7 -> 35.6No clear effect
scale to Qwen3.5-397B-A17BQwen3-VL · GuideMe-TestsF1: 35.6 -> 21.7Hurt
use dense 1 s sampling instead of anchor-based sampling (ablation)Doubao-Seed-1.8 · GuideMe 100-video subsetbehavior Score: 38.6 -> 90.3Mixed
replace GT dialogue history with the model's own predictions (ablation)Doubao-Seed-1.8 · GuideMe 100-video subsetsF1: 36.9 -> 20.0Hurt
shrink sliding window from 60 s to 30 s (ablation)Gemini 3 Pro · anchor samplingbehavior Score: 44.8 -> 40.3Hurt
enlarge sliding window from 60 s to 120 s (ablation)Gemini 3 Pro · anchor samplingbehavior Score: 44.8 -> 47.6Improved
use 2 s sampling interval instead of 1 s (ablation)Gemini 3 Pro · dense samplingbehavior Score: 47.9 -> 40.8Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 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