File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: PCG-TAL: Progressive Cross-Granularity Cooperation for Temporal Action Localization

TitlePCG-TAL: Progressive Cross-Granularity Cooperation for Temporal Action Localization
Authors
Keywordscross-granularity cooperation
cross-stream cooperation
Temporal action localization
Issue Date2021
Citation
IEEE Transactions on Image Processing, 2021, v. 30, p. 2103-2113 How to Cite?
AbstractThere are two major lines of works, i.e., anchor-based and frame-based approaches, in the field of temporal action localization. But each line of works is inherently limited to a certain detection granularity and cannot simultaneously achieve high recall rates with accurate action boundaries. In this work, we propose a progressive cross-granularity cooperation (PCG-TAL) framework to effectively take advantage of complementarity between the anchor-based and frame-based paradigms, as well as between two-view clues (i.e., appearance and motion). Specifically, our new Anchor-Frame Cooperation (AFC) module can effectively integrate both two-granularity and two-stream knowledge at the feature and proposal levels, as well as within each AFC module and across adjacent AFC modules. Specifically, the RGB-stream AFC module and the flow-stream AFC module are stacked sequentially to form a progressive localization framework. The whole framework can be learned in an end-to-end fashion, whilst the temporal action localization performance can be gradually boosted in a progressive manner. Our newly proposed framework outperforms the state-of-the-art methods on three benchmark datasets the THUMOS14, ActivityNet v1.3 and UCF-101-24, which clearly demonstrates the effectiveness of our framework.
Persistent Identifierhttp://hdl.handle.net/10722/321919
ISSN
2023 Impact Factor: 10.8
2023 SCImago Journal Rankings: 3.556
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorSu, Rui-
dc.contributor.authorXu, Dong-
dc.contributor.authorSheng, Lu-
dc.contributor.authorOuyang, Wanli-
dc.date.accessioned2022-11-03T02:22:21Z-
dc.date.available2022-11-03T02:22:21Z-
dc.date.issued2021-
dc.identifier.citationIEEE Transactions on Image Processing, 2021, v. 30, p. 2103-2113-
dc.identifier.issn1057-7149-
dc.identifier.urihttp://hdl.handle.net/10722/321919-
dc.description.abstractThere are two major lines of works, i.e., anchor-based and frame-based approaches, in the field of temporal action localization. But each line of works is inherently limited to a certain detection granularity and cannot simultaneously achieve high recall rates with accurate action boundaries. In this work, we propose a progressive cross-granularity cooperation (PCG-TAL) framework to effectively take advantage of complementarity between the anchor-based and frame-based paradigms, as well as between two-view clues (i.e., appearance and motion). Specifically, our new Anchor-Frame Cooperation (AFC) module can effectively integrate both two-granularity and two-stream knowledge at the feature and proposal levels, as well as within each AFC module and across adjacent AFC modules. Specifically, the RGB-stream AFC module and the flow-stream AFC module are stacked sequentially to form a progressive localization framework. The whole framework can be learned in an end-to-end fashion, whilst the temporal action localization performance can be gradually boosted in a progressive manner. Our newly proposed framework outperforms the state-of-the-art methods on three benchmark datasets the THUMOS14, ActivityNet v1.3 and UCF-101-24, which clearly demonstrates the effectiveness of our framework.-
dc.languageeng-
dc.relation.ispartofIEEE Transactions on Image Processing-
dc.subjectcross-granularity cooperation-
dc.subjectcross-stream cooperation-
dc.subjectTemporal action localization-
dc.titlePCG-TAL: Progressive Cross-Granularity Cooperation for Temporal Action Localization-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1109/TIP.2020.3044218-
dc.identifier.pmid33332270-
dc.identifier.scopuseid_2-s2.0-85098803049-
dc.identifier.volume30-
dc.identifier.spage2103-
dc.identifier.epage2113-
dc.identifier.eissn1941-0042-
dc.identifier.isiWOS:000613403600001-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats