Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yang, Xinyu, Jiang, Zheheng, Zhou, Feixiang, Zhu, Yihang, Lv, Na, Xing, Nan, Canagarajah, Nishan, Zhou, Huiyu
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2510.10682
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914340777492480
author Yang, Xinyu
Jiang, Zheheng
Zhou, Feixiang
Zhu, Yihang
Lv, Na
Xing, Nan
Canagarajah, Nishan
Zhou, Huiyu
author_facet Yang, Xinyu
Jiang, Zheheng
Zhou, Feixiang
Zhu, Yihang
Lv, Na
Xing, Nan
Canagarajah, Nishan
Zhou, Huiyu
contents Action understanding, encompassing action detection and anticipation, plays a crucial role in numerous practical applications. However, untrimmed videos are often characterized by substantial redundant information and noise. Moreover, in modeling action understanding, the influence of the agent's intention on the action is often overlooked. Motivated by these issues, we propose a novel framework called the State-Specific Model (SSM), designed to unify and enhance both action detection and anticipation tasks. In the proposed framework, the Critical State-Based Memory Compression module compresses frame sequences into critical states, reducing information redundancy. The Action Pattern Learning module constructs a state-transition graph with multi-dimensional edges to model action dynamics in complex scenarios, on the basis of which potential future cues can be generated to represent intention. Furthermore, our Cross-Temporal Interaction module models the mutual influence between intentions and past as well as current information through cross-temporal interactions, thereby refining present and future features and ultimately realizing simultaneous action detection and anticipation. Extensive experiments on multiple benchmark datasets -- including EPIC-Kitchens-100, THUMOS'14, TVSeries, and the introduced Parkinson's Disease Mouse Behaviour (PDMB) dataset -- demonstrate the superior performance of our proposed framework compared to other state-of-the-art approaches. These results highlight the importance of action dynamics learning and cross-temporal interactions, laying a foundation for future action understanding research.
format Preprint
id arxiv_https___arxiv_org_abs_2510_10682
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Action-Dynamics Modeling and Cross-Temporal Interaction for Online Action Understanding
Yang, Xinyu
Jiang, Zheheng
Zhou, Feixiang
Zhu, Yihang
Lv, Na
Xing, Nan
Canagarajah, Nishan
Zhou, Huiyu
Computer Vision and Pattern Recognition
Action understanding, encompassing action detection and anticipation, plays a crucial role in numerous practical applications. However, untrimmed videos are often characterized by substantial redundant information and noise. Moreover, in modeling action understanding, the influence of the agent's intention on the action is often overlooked. Motivated by these issues, we propose a novel framework called the State-Specific Model (SSM), designed to unify and enhance both action detection and anticipation tasks. In the proposed framework, the Critical State-Based Memory Compression module compresses frame sequences into critical states, reducing information redundancy. The Action Pattern Learning module constructs a state-transition graph with multi-dimensional edges to model action dynamics in complex scenarios, on the basis of which potential future cues can be generated to represent intention. Furthermore, our Cross-Temporal Interaction module models the mutual influence between intentions and past as well as current information through cross-temporal interactions, thereby refining present and future features and ultimately realizing simultaneous action detection and anticipation. Extensive experiments on multiple benchmark datasets -- including EPIC-Kitchens-100, THUMOS'14, TVSeries, and the introduced Parkinson's Disease Mouse Behaviour (PDMB) dataset -- demonstrate the superior performance of our proposed framework compared to other state-of-the-art approaches. These results highlight the importance of action dynamics learning and cross-temporal interactions, laying a foundation for future action understanding research.
title Action-Dynamics Modeling and Cross-Temporal Interaction for Online Action Understanding
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.10682