Decompose and Transfer: CoT-Prompting Enhanced Alignment for Open-Vocabulary Temporal Action Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Sa, Zhang, Wanqian, Wang, Lin, Chen, Xiaohua, Cui, Chenxu, Zhang, Jinchao, Li, Bo
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912981644738560
author Zhu, Sa
Zhang, Wanqian
Wang, Lin
Chen, Xiaohua
Cui, Chenxu
Zhang, Jinchao
Li, Bo
author_facet Zhu, Sa
Zhang, Wanqian
Wang, Lin
Chen, Xiaohua
Cui, Chenxu
Zhang, Jinchao
Li, Bo
contents Open-Vocabulary Temporal Action Detection (OV-TAD) aims to classify and localize action segments in untrimmed videos for unseen categories. Previous methods rely solely on global alignment between label-level semantics and visual features, which is insufficient to transfer temporal consistent visual knowledge from seen to unseen classes. To address this, we propose a Phase-wise Decomposition and Alignment (PDA) framework, which enables fine-grained action pattern learning for effective prior knowledge transfer. Specifically, we first introduce the CoT-Prompting Semantic Decomposition (CSD) module, which leverages the chain-of-thought (CoT) reasoning ability of large language models to automatically decompose action labels into coherent phase-level descriptions, emulating human cognitive processes. Then, Text-infused Foreground Filtering (TIF) module is introduced to adaptively filter action-relevant segments for each phase leveraging phase-wise semantic cues, producing semantically aligned visual representations. Furthermore, we propose the Adaptive Phase-wise Alignment (APA) module to perform phase-level visual-textual matching, and adaptively aggregates alignment results across phases for final prediction. This adaptive phase-wise alignment facilitates the capture of transferable action patterns and significantly enhances generalization to unseen actions. Extensive experiments on two OV-TAD benchmarks demonstrated the superiority of the proposed method.
format Preprint
id arxiv_https___arxiv_org_abs_2603_24030
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Decompose and Transfer: CoT-Prompting Enhanced Alignment for Open-Vocabulary Temporal Action Detection
Zhu, Sa
Zhang, Wanqian
Wang, Lin
Chen, Xiaohua
Cui, Chenxu
Zhang, Jinchao
Li, Bo
Computer Vision and Pattern Recognition
Multimedia
Open-Vocabulary Temporal Action Detection (OV-TAD) aims to classify and localize action segments in untrimmed videos for unseen categories. Previous methods rely solely on global alignment between label-level semantics and visual features, which is insufficient to transfer temporal consistent visual knowledge from seen to unseen classes. To address this, we propose a Phase-wise Decomposition and Alignment (PDA) framework, which enables fine-grained action pattern learning for effective prior knowledge transfer. Specifically, we first introduce the CoT-Prompting Semantic Decomposition (CSD) module, which leverages the chain-of-thought (CoT) reasoning ability of large language models to automatically decompose action labels into coherent phase-level descriptions, emulating human cognitive processes. Then, Text-infused Foreground Filtering (TIF) module is introduced to adaptively filter action-relevant segments for each phase leveraging phase-wise semantic cues, producing semantically aligned visual representations. Furthermore, we propose the Adaptive Phase-wise Alignment (APA) module to perform phase-level visual-textual matching, and adaptively aggregates alignment results across phases for final prediction. This adaptive phase-wise alignment facilitates the capture of transferable action patterns and significantly enhances generalization to unseen actions. Extensive experiments on two OV-TAD benchmarks demonstrated the superiority of the proposed method.
title Decompose and Transfer: CoT-Prompting Enhanced Alignment for Open-Vocabulary Temporal Action Detection
topic Computer Vision and Pattern Recognition
Multimedia
url https://arxiv.org/abs/2603.24030