Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ma, Xiaoxuan, Li, Zishi, Shang, Qiuyan, Zhu, Wentao, Ci, Hai, Qiao, Yu, Wang, Yizhou
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2403.01543
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911315830767616
author Ma, Xiaoxuan
Li, Zishi
Shang, Qiuyan
Zhu, Wentao
Ci, Hai
Qiao, Yu
Wang, Yizhou
author_facet Ma, Xiaoxuan
Li, Zishi
Shang, Qiuyan
Zhu, Wentao
Ci, Hai
Qiao, Yu
Wang, Yizhou
contents Temporal repetition counting aims to quantify the repeated action cycles within a video. The majority of existing methods rely on the similarity correlation matrix to characterize the repetitiveness of actions, but their scalability is hindered due to the quadratic computational complexity. In this work, we introduce a novel approach that employs an action query representation to localize repeated action cycles with linear computational complexity. Based on this representation, we further develop two key components to tackle the essential challenges of temporal repetition counting. Firstly, to facilitate open-set action counting, we propose the dynamic update scheme on action queries. Unlike static action queries, this approach dynamically embeds video features into action queries, offering a more flexible and generalizable representation. Secondly, to distinguish between actions of interest and background noise actions, we incorporate inter-query contrastive learning to regularize the video representations corresponding to different action queries. As a result, our method significantly outperforms previous works, particularly in terms of long video sequences, unseen actions, and actions at various speeds. On the challenging RepCountA benchmark, we outperform the state-of-the-art method TransRAC by 26.5% in OBO accuracy, with a 22.7% mean error decrease and 94.1% computational burden reduction. Code is available at https://github.com/lizishi/DeTRC.
format Preprint
id arxiv_https___arxiv_org_abs_2403_01543
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Efficient Action Counting with Dynamic Queries
Ma, Xiaoxuan
Li, Zishi
Shang, Qiuyan
Zhu, Wentao
Ci, Hai
Qiao, Yu
Wang, Yizhou
Computer Vision and Pattern Recognition
Temporal repetition counting aims to quantify the repeated action cycles within a video. The majority of existing methods rely on the similarity correlation matrix to characterize the repetitiveness of actions, but their scalability is hindered due to the quadratic computational complexity. In this work, we introduce a novel approach that employs an action query representation to localize repeated action cycles with linear computational complexity. Based on this representation, we further develop two key components to tackle the essential challenges of temporal repetition counting. Firstly, to facilitate open-set action counting, we propose the dynamic update scheme on action queries. Unlike static action queries, this approach dynamically embeds video features into action queries, offering a more flexible and generalizable representation. Secondly, to distinguish between actions of interest and background noise actions, we incorporate inter-query contrastive learning to regularize the video representations corresponding to different action queries. As a result, our method significantly outperforms previous works, particularly in terms of long video sequences, unseen actions, and actions at various speeds. On the challenging RepCountA benchmark, we outperform the state-of-the-art method TransRAC by 26.5% in OBO accuracy, with a 22.7% mean error decrease and 94.1% computational burden reduction. Code is available at https://github.com/lizishi/DeTRC.
title Efficient Action Counting with Dynamic Queries
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2403.01543