AI Paper Atlas

Research map / Video / Action recognition

MistSense: Versatile Online Detection of Procedural and Execution Mistakes

Constantin Patsch, Yuankai Wu, Marsil Zakour, Driton Salihu, Eckehard Steinbach

ICCV 2025 · Video › Action recognition · approach: Action anticipation and latent actions · 5 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 pose modality via separate Hand Q-FormerMistSense RGB · Epic-tent-OF1-score: 59.8 -> 63.3Improved
add predicted hand pose to RGBMistSense · Holo AssistF1-score: 54.8 -> 55.7Improved
use separate Q-Formers instead of a shared Video Q-Former for RGB and hand (ablation)MistSense RGB+H(P) · Epic-tent-OF1-score: 60.8 -> 63.3Improved
add Hand Q-Former instead of late fusion (ablation)MistSense RGB+H(P) · Epic-tent-OF1-score: 57.8 -> 63.3Improved
add RGB features to hand-only input (ablation)MistSense · Epic-tent-OF1-score: 49.1 -> 63.3Improved
late fusion of hand features versus RGB only (ablation)MistSense · Epic-tent-OF1-score: 59.8 -> 57.8No clear effect
add hand pose to RGBMistSense · Holo Assistmistake recall: 21.1 -> 31.6Improved
add hand pose to RGBMistSense · Epic-tent-Omistake precision: 55.0 -> 45.4Mixed
use MistSense RGB instead of DODO baseline · Epic-tent-OF1-score: 46.5 -> 59.8Improved
use MistSense RGB instead of DODO baseline · Epic-tent-Omistake F1: 23.7 -> 29.8Improved
use MistSense RGB instead of GazeCompl, no eye gazeGazeCompl · Holo AssistF1-score: 51.0 -> 54.8Improved
use MistSense explanation module instead of Video-ChatGPTVideo-ChatGPT · Epic-tentCIDEr: 2.61 -> 3.09Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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