Enregistré dans:
Détails bibliographiques
Auteurs principaux: Liu, Shuming, Zhao, Chen, Zohra, Fatimah, Soldan, Mattia, Pardo, Alejandro, Xu, Mengmeng, Alssum, Lama, Ramazanova, Merey, Alcázar, Juan León, Cioppa, Anthony, Giancola, Silvio, Hinojosa, Carlos, Ghanem, Bernard
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2502.20361
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915175834058752
author Liu, Shuming
Zhao, Chen
Zohra, Fatimah
Soldan, Mattia
Pardo, Alejandro
Xu, Mengmeng
Alssum, Lama
Ramazanova, Merey
Alcázar, Juan León
Cioppa, Anthony
Giancola, Silvio
Hinojosa, Carlos
Ghanem, Bernard
author_facet Liu, Shuming
Zhao, Chen
Zohra, Fatimah
Soldan, Mattia
Pardo, Alejandro
Xu, Mengmeng
Alssum, Lama
Ramazanova, Merey
Alcázar, Juan León
Cioppa, Anthony
Giancola, Silvio
Hinojosa, Carlos
Ghanem, Bernard
contents Temporal action detection (TAD) is a fundamental video understanding task that aims to identify human actions and localize their temporal boundaries in videos. Although this field has achieved remarkable progress in recent years, further progress and real-world applications are impeded by the absence of a standardized framework. Currently, different methods are compared under different implementation settings, evaluation protocols, etc., making it difficult to assess the real effectiveness of a specific technique. To address this issue, we propose \textbf{OpenTAD}, a unified TAD framework consolidating 16 different TAD methods and 9 standard datasets into a modular codebase. In OpenTAD, minimal effort is required to replace one module with a different design, train a feature-based TAD model in end-to-end mode, or switch between the two. OpenTAD also facilitates straightforward benchmarking across various datasets and enables fair and in-depth comparisons among different methods. With OpenTAD, we comprehensively study how innovations in different network components affect detection performance and identify the most effective design choices through extensive experiments. This study has led to a new state-of-the-art TAD method built upon existing techniques for each component. We have made our code and models available at https://github.com/sming256/OpenTAD.
format Preprint
id arxiv_https___arxiv_org_abs_2502_20361
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OpenTAD: A Unified Framework and Comprehensive Study of Temporal Action Detection
Liu, Shuming
Zhao, Chen
Zohra, Fatimah
Soldan, Mattia
Pardo, Alejandro
Xu, Mengmeng
Alssum, Lama
Ramazanova, Merey
Alcázar, Juan León
Cioppa, Anthony
Giancola, Silvio
Hinojosa, Carlos
Ghanem, Bernard
Computer Vision and Pattern Recognition
Temporal action detection (TAD) is a fundamental video understanding task that aims to identify human actions and localize their temporal boundaries in videos. Although this field has achieved remarkable progress in recent years, further progress and real-world applications are impeded by the absence of a standardized framework. Currently, different methods are compared under different implementation settings, evaluation protocols, etc., making it difficult to assess the real effectiveness of a specific technique. To address this issue, we propose \textbf{OpenTAD}, a unified TAD framework consolidating 16 different TAD methods and 9 standard datasets into a modular codebase. In OpenTAD, minimal effort is required to replace one module with a different design, train a feature-based TAD model in end-to-end mode, or switch between the two. OpenTAD also facilitates straightforward benchmarking across various datasets and enables fair and in-depth comparisons among different methods. With OpenTAD, we comprehensively study how innovations in different network components affect detection performance and identify the most effective design choices through extensive experiments. This study has led to a new state-of-the-art TAD method built upon existing techniques for each component. We have made our code and models available at https://github.com/sming256/OpenTAD.
title OpenTAD: A Unified Framework and Comprehensive Study of Temporal Action Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.20361