Intention-Guided Cognitive Reasoning for Egocentric Long-Term Action Anticipation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chu, Qiaohui, Zhang, Haoyu, Liu, Meng, Feng, Yisen, Shi, Haoxiang, Nie, Liqiang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912711706673152
author Chu, Qiaohui
Zhang, Haoyu
Liu, Meng
Feng, Yisen
Shi, Haoxiang
Nie, Liqiang
author_facet Chu, Qiaohui
Zhang, Haoyu
Liu, Meng
Feng, Yisen
Shi, Haoxiang
Nie, Liqiang
contents Long-term action anticipation from egocentric video is critical for applications such as human-computer interaction and assistive technologies, where anticipating user intent enables proactive and context-aware AI assistance. However, existing approaches suffer from three key limitations: 1) underutilization of fine-grained visual cues from hand-object interactions, 2) neglect of semantic dependencies between verbs and nouns, and 3) lack of explicit cognitive reasoning, limiting generalization and long-term forecasting ability. To overcome these challenges, we propose INSIGHT, a unified two-stage framework for egocentric action anticipation. In the first stage, INSIGHT focuses on extracting semantically rich features from hand-object interaction regions and enhances action representations using a verb-noun co-occurrence matrix. In the second stage, it introduces a reinforcement learning-based module that simulates explicit cognitive reasoning through a structured process: visual perception (think) -> intention inference (reason) -> action anticipation (answer). Extensive experiments on Ego4D, EPIC-Kitchens-55, and EGTEA Gaze+ benchmarks show that INSIGHT achieves state-of-the-art performance, demonstrating its effectiveness and strong generalization capability.
format Preprint
id arxiv_https___arxiv_org_abs_2508_01742
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Intention-Guided Cognitive Reasoning for Egocentric Long-Term Action Anticipation
Chu, Qiaohui
Zhang, Haoyu
Liu, Meng
Feng, Yisen
Shi, Haoxiang
Nie, Liqiang
Computer Vision and Pattern Recognition
Artificial Intelligence
Long-term action anticipation from egocentric video is critical for applications such as human-computer interaction and assistive technologies, where anticipating user intent enables proactive and context-aware AI assistance. However, existing approaches suffer from three key limitations: 1) underutilization of fine-grained visual cues from hand-object interactions, 2) neglect of semantic dependencies between verbs and nouns, and 3) lack of explicit cognitive reasoning, limiting generalization and long-term forecasting ability. To overcome these challenges, we propose INSIGHT, a unified two-stage framework for egocentric action anticipation. In the first stage, INSIGHT focuses on extracting semantically rich features from hand-object interaction regions and enhances action representations using a verb-noun co-occurrence matrix. In the second stage, it introduces a reinforcement learning-based module that simulates explicit cognitive reasoning through a structured process: visual perception (think) -> intention inference (reason) -> action anticipation (answer). Extensive experiments on Ego4D, EPIC-Kitchens-55, and EGTEA Gaze+ benchmarks show that INSIGHT achieves state-of-the-art performance, demonstrating its effectiveness and strong generalization capability.
title Intention-Guided Cognitive Reasoning for Egocentric Long-Term Action Anticipation
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2508.01742