Mistake Attribution: Fine-Grained Mistake Understanding in Egocentric Videos

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Yayuan, Jain, Aadit, Bellos, Filippos, Corso, Jason J.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910073070026752
author Li, Yayuan
Jain, Aadit
Bellos, Filippos
Corso, Jason J.
author_facet Li, Yayuan
Jain, Aadit
Bellos, Filippos
Corso, Jason J.
contents We introduce Mistake Attribution (MATT), a new task for fine-grained understanding of human mistakes in egocentric videos. While prior work detects whether a mistake occurs, MATT attributes the mistake to what part of the instruction is violated (semantic role), when in the video the deviation becomes irreversible (the Point-of-No-Return, PNR), and where the mistake appears in the PNR frame. We develop MisEngine, a data engine that automatically constructs mistake samples from existing datasets with attribution-rich annotations. Applied to large egocentric corpora, MisEngine yields EPIC-KITCHENS-M and Ego4D-M -- two datasets up to two orders of magnitude larger than prior mistake datasets. We then present MisFormer, a unified attention-based model for mistake attribution across semantic, temporal, and spatial dimensions, trained with MisEngine supervision. A human study demonstrates the ecological validity of our MisEngine-constructed mistake samples, confirming that EPIC-KITCHENS-M and Ego4D-M can serve as reliable benchmarks for mistake understanding. Experiments on both our datasets and prior benchmarks show that MisFormer, as a single unified model, outperforms task-specific SOTA methods by at least 6.66%, 21.81%, 18.7%, and 3.00% in video-language understanding, temporal localization, hand-object interaction, and mistake detection, respectively. Project page: https://yayuanli.github.io/MATT/
format Preprint
id arxiv_https___arxiv_org_abs_2511_20525
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Mistake Attribution: Fine-Grained Mistake Understanding in Egocentric Videos
Li, Yayuan
Jain, Aadit
Bellos, Filippos
Corso, Jason J.
Computer Vision and Pattern Recognition
I.2.10; I.4.8; I.5.4
We introduce Mistake Attribution (MATT), a new task for fine-grained understanding of human mistakes in egocentric videos. While prior work detects whether a mistake occurs, MATT attributes the mistake to what part of the instruction is violated (semantic role), when in the video the deviation becomes irreversible (the Point-of-No-Return, PNR), and where the mistake appears in the PNR frame. We develop MisEngine, a data engine that automatically constructs mistake samples from existing datasets with attribution-rich annotations. Applied to large egocentric corpora, MisEngine yields EPIC-KITCHENS-M and Ego4D-M -- two datasets up to two orders of magnitude larger than prior mistake datasets. We then present MisFormer, a unified attention-based model for mistake attribution across semantic, temporal, and spatial dimensions, trained with MisEngine supervision. A human study demonstrates the ecological validity of our MisEngine-constructed mistake samples, confirming that EPIC-KITCHENS-M and Ego4D-M can serve as reliable benchmarks for mistake understanding. Experiments on both our datasets and prior benchmarks show that MisFormer, as a single unified model, outperforms task-specific SOTA methods by at least 6.66%, 21.81%, 18.7%, and 3.00% in video-language understanding, temporal localization, hand-object interaction, and mistake detection, respectively. Project page: https://yayuanli.github.io/MATT/
title Mistake Attribution: Fine-Grained Mistake Understanding in Egocentric Videos
topic Computer Vision and Pattern Recognition
I.2.10; I.4.8; I.5.4
url https://arxiv.org/abs/2511.20525