Publications

Detailed Information

Weakly Supervised Action Localization by Sparse Temporal Pooling Network

DC Field Value Language
dc.contributor.authorPhuc Nguyen-
dc.contributor.authorLiu, Ting-
dc.contributor.authorPrasad, Gautam-
dc.contributor.authorHan, Bohyung-
dc.date.accessioned2023-04-19T04:08:21Z-
dc.date.available2023-04-19T04:08:21Z-
dc.date.created2022-10-24-
dc.date.issued2018-06-
dc.identifier.citation2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), pp.6752-6761-
dc.identifier.issn1063-6919-
dc.identifier.urihttps://hdl.handle.net/10371/190552-
dc.description.abstractWe propose a weakly supervised temporal action localization algorithm on untrimmed videos using convolutional neural networks. Our algorithm learns from video-level class labels and predicts temporal intervals of human actions with no requirement of temporal localization annotations. We design our network to identify a sparse subset of key segments associated with target actions in a video using an attention module and fuse the key segments through adaptive temporal pooling. Our loss function is comprised of two terms that minimize the video-level action classification error and enforce the sparsity of the segment selection. At inference time, we extract and score temporal proposals using temporal class activations and class-agnostic attentions to estimate the time intervals that correspond to target actions. The proposed algorithm attains state-of-the-art results on the THUMOS14 dataset and outstanding performance on ActivityNet1.3 even with its weak supervision.-
dc.language영어-
dc.publisherIEEE-
dc.titleWeakly Supervised Action Localization by Sparse Temporal Pooling Network-
dc.typeArticle-
dc.identifier.doi10.1109/CVPR.2018.00706-
dc.citation.journaltitle2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)-
dc.identifier.wosid000457843606094-
dc.identifier.scopusid2-s2.0-85062884279-
dc.citation.endpage6761-
dc.citation.startpage6752-
dc.description.isOpenAccessY-
dc.contributor.affiliatedAuthorHan, Bohyung-
dc.type.docTypeProceedings Paper-
dc.description.journalClass1-
Appears in Collections:
Files in This Item:
There are no files associated with this item.

Altmetrics

Item View & Download Count

  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Share