FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381198912> ?p ?o ?g. }

• W4381198912 endingPage "16" @default.
• W4381198912 startingPage "1" @default.
• W4381198912 abstract "Weakly-supervised temporal action localization (WSTAL) aims to automatically identify and localize action instances in untrimmed videos with only video-level labels as supervision. In this task, there exist two challenges: (1) how to accurately discover the action categories in an untrimmed video (what to discover); (2) how to elaborately focus on the integral temporal interval of each action instance (where to focus). Empirically, to discover the action categories, discriminative semantic information should be extracted, while robust temporal contextual information is beneficial for complete action localization. However, most existing WSTAL methods ignore to explicitly and jointly model the semantic and temporal contextual correlation information for the above two challenges. In this paper, a <bold xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>S</b> emantic and <bold xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>T</b> emporal Contextual <bold xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>C</b> orrelation <bold xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>L</b> earning <bold xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>Net</b> work (STCL-Net) with the semantic (SCL) and temporal contextual correlation learning (TCL) modules is proposed, which achieves both accurate action discovery and complete action localization by modeling the semantic and temporal contextual correlation information for each snippet in the inter- and intra-video manners respectively. It is noteworthy that the two proposed modules are both designed in a unified dynamic correlation-embedding paradigm. Extensive experiments are performed on different benchmarks. On all the benchmarks, our proposed method exhibits superior or comparable performance in comparison to the existing state-of-the-art models, especially achieving gains as high as 7.2% in terms of the average mAP on THUMOS-14. In addition, comprehensive ablation studies also verify the effectiveness and robustness of each component in our model." @default.
• W4381198912 created "2023-06-20" @default.
• W4381198912 creator A5014526931 @default.
• W4381198912 creator A5022636178 @default.
• W4381198912 creator A5060774367 @default.
• W4381198912 date "2023-01-01" @default.
• W4381198912 modified "2023-10-16" @default.
• W4381198912 title "Semantic and Temporal Contextual Correlation Learning for Weakly-Supervised Temporal Action Localization" @default.
• W4381198912 cites W1927052826 @default.
• W4381198912 cites W2119031011 @default.
• W4381198912 cites W2142194269 @default.
• W4381198912 cites W2336403884 @default.
• W4381198912 cites W2337252826 @default.
• W4381198912 cites W2535977253 @default.
• W4381198912 cites W2766630207 @default.
• W4381198912 cites W2810912957 @default.
• W4381198912 cites W2884293275 @default.
• W4381198912 cites W2895361760 @default.
• W4381198912 cites W2948229620 @default.
• W4381198912 cites W2952435096 @default.
• W4381198912 cites W2962677524 @default.
• W4381198912 cites W2962709777 @default.
• W4381198912 cites W2962876901 @default.
• W4381198912 cites W2963045696 @default.
• W4381198912 cites W2963524571 @default.
• W4381198912 cites W2963919999 @default.
• W4381198912 cites W2964036161 @default.
• W4381198912 cites W2970724283 @default.
• W4381198912 cites W2972712288 @default.
• W4381198912 cites W2981998043 @default.
• W4381198912 cites W2983918066 @default.
• W4381198912 cites W2984619425 @default.
• W4381198912 cites W2986407524 @default.
• W4381198912 cites W2988098865 @default.
• W4381198912 cites W2989042503 @default.
• W4381198912 cites W2989506443 @default.
• W4381198912 cites W2990503944 @default.
• W4381198912 cites W2997706915 @default.
• W4381198912 cites W2998601171 @default.
• W4381198912 cites W2998702159 @default.
• W4381198912 cites W3009148386 @default.
• W4381198912 cites W3016459781 @default.
• W4381198912 cites W3034623254 @default.
• W4381198912 cites W3034687522 @default.
• W4381198912 cites W3035180180 @default.
• W4381198912 cites W3035585099 @default.
• W4381198912 cites W3095669214 @default.
• W4381198912 cites W3097664769 @default.
• W4381198912 cites W3100481960 @default.
• W4381198912 cites W3106041614 @default.
• W4381198912 cites W3107128832 @default.
• W4381198912 cites W3109986575 @default.
• W4381198912 cites W3110589170 @default.
• W4381198912 cites W3112040205 @default.
• W4381198912 cites W3168126734 @default.
• W4381198912 cites W3173212682 @default.
• W4381198912 cites W3173698268 @default.
• W4381198912 cites W3173874725 @default.
• W4381198912 cites W3174421047 @default.
• W4381198912 cites W3174511093 @default.
• W4381198912 cites W3175357208 @default.
• W4381198912 cites W3176212189 @default.
• W4381198912 cites W3176853098 @default.
• W4381198912 cites W3178036208 @default.
• W4381198912 cites W3182120198 @default.
• W4381198912 cites W3189379416 @default.
• W4381198912 cites W3189800722 @default.
• W4381198912 cites W3201832684 @default.
• W4381198912 cites W3203848195 @default.
• W4381198912 cites W3207172562 @default.
• W4381198912 cites W3207758636 @default.
• W4381198912 cites W3207927851 @default.
• W4381198912 cites W4214589115 @default.
• W4381198912 cites W4225505766 @default.
• W4381198912 cites W4226270831 @default.
• W4381198912 cites W4226500165 @default.
• W4381198912 cites W4301963599 @default.
• W4381198912 cites W4312421085 @default.
• W4381198912 cites W4312508181 @default.
• W4381198912 cites W4312578992 @default.
• W4381198912 cites W4313024697 @default.
• W4381198912 cites W4386076085 @default.
• W4381198912 doi "https://doi.org/10.1109/tpami.2023.3287208" @default.
• W4381198912 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37335790" @default.
• W4381198912 hasPublicationYear "2023" @default.
• W4381198912 type Work @default.
• W4381198912 citedByCount "0" @default.
• W4381198912 crossrefType "journal-article" @default.
• W4381198912 hasAuthorship W4381198912A5014526931 @default.
• W4381198912 hasAuthorship W4381198912A5022636178 @default.
• W4381198912 hasAuthorship W4381198912A5060774367 @default.
• W4381198912 hasConcept C119857082 @default.
• W4381198912 hasConcept C120665830 @default.
• W4381198912 hasConcept C121332964 @default.
• W4381198912 hasConcept C154945302 @default.
• W4381198912 hasConcept C192209626 @default.
• W4381198912 hasConcept C204321447 @default.
• W4381198912 hasConcept C2780791683 @default.

• next