Matches in SemOpenAlex for { <https://semopenalex.org/work/W4295308457> ?p ?o ?g. }
- W4295308457 endingPage "96387" @default.
- W4295308457 startingPage "96378" @default.
- W4295308457 abstract "Precisely localizing temporal intervals for each action segment in long raw videos is essential challenge in practical video content analysis (e.g., activity detection or video caption generation). Most of previous works often neglect the hierarchical action granularity and eventually fail to identify precise action boundaries. (e.g., embracing approaching or turning a screw in mechanical maintenance). In this paper, we introduce a simple yet efficient coarse-to-fine network (CFNet) to solve the challenging issue of temporal action localization by progressively refining action boundary at multiple action granularities. The proposed CFNet is mainly composed of three components: a coarse proposal module (CPM) to generate coarse action candidates, a fusion block (FB) to enhance feature representation by fusing the coarse candidate features and corresponding features of raw input frames, and a boundary transformer module (BTM) to further refine action boundaries. Specifically, CPM exploits framewise, matching and gated actionness curves to complement each other for coarse candidate generation at different levels, while FB is devised to enrich feature representation by fusing the last feature map of CPM and corresponding raw frame input. Finally, BTM learns long-term temporal dependency with a transformer structure to further refine action boundaries at a finer granularity. Thus, the fine-grained action intervals can be incrementally obtained. Compared with previous state-of-the-art techniques, the proposed coarse-to-fine network can asymptotically approach fine-grained action boundary. Comprehensive experiments are conducted on both publicly available THUMOS14 and ActivityNet-v1.3 datasets, and show the outstanding improvements of our method when compared with the prior methods on various video action parsing tasks." @default.
- W4295308457 created "2022-09-12" @default.
- W4295308457 creator A5000723482 @default.
- W4295308457 creator A5019641005 @default.
- W4295308457 creator A5053204257 @default.
- W4295308457 date "2022-01-01" @default.
- W4295308457 modified "2023-09-30" @default.
- W4295308457 title "Temporal Action Localization With Coarse-to-Fine Network" @default.
- W4295308457 cites W1927052826 @default.
- W4295308457 cites W2593722617 @default.
- W4295308457 cites W2597958930 @default.
- W4295308457 cites W2757143884 @default.
- W4295308457 cites W2883915488 @default.
- W4295308457 cites W2884969173 @default.
- W4295308457 cites W2907214745 @default.
- W4295308457 cites W2919115771 @default.
- W4295308457 cites W2948383821 @default.
- W4295308457 cites W2952435096 @default.
- W4295308457 cites W2962677524 @default.
- W4295308457 cites W2962876901 @default.
- W4295308457 cites W2963082988 @default.
- W4295308457 cites W2963247196 @default.
- W4295308457 cites W2963321993 @default.
- W4295308457 cites W2963563276 @default.
- W4295308457 cites W2964214371 @default.
- W4295308457 cites W2964216549 @default.
- W4295308457 cites W2964274041 @default.
- W4295308457 cites W2965102465 @default.
- W4295308457 cites W2971387592 @default.
- W4295308457 cites W2983918066 @default.
- W4295308457 cites W2997706915 @default.
- W4295308457 cites W2998582438 @default.
- W4295308457 cites W3018902719 @default.
- W4295308457 cites W3069380482 @default.
- W4295308457 cites W3080945469 @default.
- W4295308457 cites W3100481960 @default.
- W4295308457 cites W3104729221 @default.
- W4295308457 cites W3108812043 @default.
- W4295308457 cites W3128626728 @default.
- W4295308457 cites W3174569083 @default.
- W4295308457 cites W4205691354 @default.
- W4295308457 cites W4226380330 @default.
- W4295308457 cites W4280615592 @default.
- W4295308457 cites W639708223 @default.
- W4295308457 doi "https://doi.org/10.1109/access.2022.3205594" @default.
- W4295308457 hasPublicationYear "2022" @default.
- W4295308457 type Work @default.
- W4295308457 citedByCount "1" @default.
- W4295308457 countsByYear W42953084572022 @default.
- W4295308457 crossrefType "journal-article" @default.
- W4295308457 hasAuthorship W4295308457A5000723482 @default.
- W4295308457 hasAuthorship W4295308457A5019641005 @default.
- W4295308457 hasAuthorship W4295308457A5053204257 @default.
- W4295308457 hasBestOaLocation W42953084571 @default.
- W4295308457 hasConcept C111919701 @default.
- W4295308457 hasConcept C121332964 @default.
- W4295308457 hasConcept C134306372 @default.
- W4295308457 hasConcept C138885662 @default.
- W4295308457 hasConcept C153180895 @default.
- W4295308457 hasConcept C154945302 @default.
- W4295308457 hasConcept C165696696 @default.
- W4295308457 hasConcept C165801399 @default.
- W4295308457 hasConcept C17744445 @default.
- W4295308457 hasConcept C177774035 @default.
- W4295308457 hasConcept C19768560 @default.
- W4295308457 hasConcept C199539241 @default.
- W4295308457 hasConcept C2776359362 @default.
- W4295308457 hasConcept C2776401178 @default.
- W4295308457 hasConcept C2780791683 @default.
- W4295308457 hasConcept C31972630 @default.
- W4295308457 hasConcept C33923547 @default.
- W4295308457 hasConcept C38652104 @default.
- W4295308457 hasConcept C41008148 @default.
- W4295308457 hasConcept C41895202 @default.
- W4295308457 hasConcept C62354387 @default.
- W4295308457 hasConcept C62520636 @default.
- W4295308457 hasConcept C66322947 @default.
- W4295308457 hasConcept C94625758 @default.
- W4295308457 hasConceptScore W4295308457C111919701 @default.
- W4295308457 hasConceptScore W4295308457C121332964 @default.
- W4295308457 hasConceptScore W4295308457C134306372 @default.
- W4295308457 hasConceptScore W4295308457C138885662 @default.
- W4295308457 hasConceptScore W4295308457C153180895 @default.
- W4295308457 hasConceptScore W4295308457C154945302 @default.
- W4295308457 hasConceptScore W4295308457C165696696 @default.
- W4295308457 hasConceptScore W4295308457C165801399 @default.
- W4295308457 hasConceptScore W4295308457C17744445 @default.
- W4295308457 hasConceptScore W4295308457C177774035 @default.
- W4295308457 hasConceptScore W4295308457C19768560 @default.
- W4295308457 hasConceptScore W4295308457C199539241 @default.
- W4295308457 hasConceptScore W4295308457C2776359362 @default.
- W4295308457 hasConceptScore W4295308457C2776401178 @default.
- W4295308457 hasConceptScore W4295308457C2780791683 @default.
- W4295308457 hasConceptScore W4295308457C31972630 @default.
- W4295308457 hasConceptScore W4295308457C33923547 @default.
- W4295308457 hasConceptScore W4295308457C38652104 @default.
- W4295308457 hasConceptScore W4295308457C41008148 @default.
- W4295308457 hasConceptScore W4295308457C41895202 @default.