AI Paper Atlas

Research map / Video / Video-language understanding

AXG-Reasoner: Error Detection and Explanation in Long Task Videos with Vision-Language Models

Shih-Po Lee, Ehsan Elhamifar

CVPR 2026 · Video › Video-language understanding · approach: Long video 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
add AXG subaction decomposition and keyframes to Qwen2.5-VLQwen2.5-VL-32B · EgoPER error explanation (GT segments)explanation similarity score (%): 3.6 -> 17.4Improved
add AXG to InternVL3.5InternVL3.5-14B · CaptainCook4D error explanation (GT segments)explanation similarity score (%): 18.0 -> 21.2Improved
use VideoTree keyframe selection instead of uniform samplingQwen2.5-VL-32B · EgoPER error explanation (GT segments)explanation similarity score (%): 3.6 -> 5.0No clear effect
add AXG with GTG2Vid TAS to Qwen2.5-VL for detectionQwen2.5-VL-32B · EgoPER error detection F1@0.5F1@0.5: 20.4 -> 33.4Improved
add AXG with GTG2Vid TAS to Qwen2.5-VL for detectionQwen2.5-VL-32B · CaptainCook4D error detection F1@0.5F1@0.5: 15.3 -> 28.5Improved
add AXG on GT action segmentsQwen2.5-VL-32B · EgoPER error detection (GT segments)F1: 56.7 -> 63.6Improved
add AXG on GT action segmentsQwen2.5-VL-32B · EgoPER normal-segment F1 (GT segments)F1 on normal segments (N.): 87.1 -> 80.1Hurt
increase number of subaction clusters K from 5 to 20 (ablation)AXG · EgoPER and CaptainCook4D taskserror explanation score: Burritos S 27.0 -> 30.0; Tea S 17.0 -> 19.0; Oatmeal S 20.0 -> 22.0Mixed
increase number of subaction clusters K from 5 to 20 (ablation)AXG · EgoPER Oatmeal (GT segments)error detection F1: 65.1 -> 61.3Hurt
use single-subaction AXG for temporal subaction segmentationInternVL3.5-14B · EgoPER actions with one subactionexplanation similarity score (%): 18.4 -> 25.0Improved
InternVL3.5 instead of Qwen2.5-VL as the VLM for explanationAXG · EgoPER error explanationexplanation similarity score (%): 17.4 -> 24.6Improved

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