Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chen, Shimin, Li, Wei, Gu, Jianyang, Chen, Chen, Guo, Yandong
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2411.00883
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912102404325376
author Chen, Shimin
Li, Wei
Gu, Jianyang
Chen, Chen
Guo, Yandong
author_facet Chen, Shimin
Li, Wei
Gu, Jianyang
Chen, Chen
Guo, Yandong
contents In the task of temporal action localization of ActivityNet-1.3 datasets, we propose to locate the temporal boundaries of each action and predict action class in untrimmed videos. We first apply VideoSwinTransformer as feature extractor to extract different features. Then we apply a unified network following Faster-TAD to simultaneously obtain proposals and semantic labels. Last, we ensemble the results of different temporal action detection models which complement each other. Faster-TAD simplifies the pipeline of TAD and gets remarkable performance, obtaining comparable results as those of multi-step approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2411_00883
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Technical Report for ActivityNet Challenge 2022 -- Temporal Action Localization
Chen, Shimin
Li, Wei
Gu, Jianyang
Chen, Chen
Guo, Yandong
Computer Vision and Pattern Recognition
In the task of temporal action localization of ActivityNet-1.3 datasets, we propose to locate the temporal boundaries of each action and predict action class in untrimmed videos. We first apply VideoSwinTransformer as feature extractor to extract different features. Then we apply a unified network following Faster-TAD to simultaneously obtain proposals and semantic labels. Last, we ensemble the results of different temporal action detection models which complement each other. Faster-TAD simplifies the pipeline of TAD and gets remarkable performance, obtaining comparable results as those of multi-step approaches.
title Technical Report for ActivityNet Challenge 2022 -- Temporal Action Localization
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.00883