Publications
Detailed Information
Weakly Supervised Action Localization by Sparse Temporal Pooling Network
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Phuc Nguyen | - |
dc.contributor.author | Liu, Ting | - |
dc.contributor.author | Prasad, Gautam | - |
dc.contributor.author | Han, Bohyung | - |
dc.date.accessioned | 2023-04-19T04:08:21Z | - |
dc.date.available | 2023-04-19T04:08:21Z | - |
dc.date.created | 2022-10-24 | - |
dc.date.issued | 2018-06 | - |
dc.identifier.citation | 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), pp.6752-6761 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | https://hdl.handle.net/10371/190552 | - |
dc.description.abstract | We 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.language | 영어 | - |
dc.publisher | IEEE | - |
dc.title | Weakly Supervised Action Localization by Sparse Temporal Pooling Network | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/CVPR.2018.00706 | - |
dc.citation.journaltitle | 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) | - |
dc.identifier.wosid | 000457843606094 | - |
dc.identifier.scopusid | 2-s2.0-85062884279 | - |
dc.citation.endpage | 6761 | - |
dc.citation.startpage | 6752 | - |
dc.description.isOpenAccess | Y | - |
dc.contributor.affiliatedAuthor | Han, Bohyung | - |
dc.type.docType | Proceedings Paper | - |
dc.description.journalClass | 1 | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.