FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4328007341> ?p ?o ?g. }

• W4328007341 endingPage "5827" @default.
• W4328007341 startingPage "5814" @default.
• W4328007341 abstract "Video-based human-object interaction recognition is a challenging task since the state of objects as well as their correlations change constantly in the video. Existing methods mainly use 3DCNN or use separate components (e.g., GCN + RNN) to model the spatial correlation or the temporal correlation respectively, but ignore modeling spatio-temporal correlations simultaneously and long-term temporal dynamics of objects. In this paper, we propose a novel model, named Spatio-Temporal Interaction Graph Parsing Networks (STIGPN), for human-object interaction recognition in videos. STIGPN captures both spatial and temporal correlations simultaneously and thus can capture intra-frame and inter-frame dependencies efficiently and effectively. To model long-term temporal dynamics of objects, we introduce spatio-temporal feature enhancement, which can improve the detection of the salient human-object interaction pairs. We explore three types of spatio-temporal graph convolutions to simultaneously capture the spatio-temporal correlations and assess their effectiveness as the basic building block of STIGPN. Extensive experiments on CAD-120, Something-Else and Charades datasets show that our proposed solution leads to competitive results compared with the state-of-the-art methods. Code for STIGPN is available at: <uri xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>https://github.com/NingWang2049/STIGPN2</uri>" @default.
• W4328007341 created "2023-03-22" @default.
• W4328007341 creator A5000205091 @default.
• W4328007341 creator A5001104491 @default.
• W4328007341 creator A5022848316 @default.
• W4328007341 creator A5028794275 @default.
• W4328007341 creator A5032579154 @default.
• W4328007341 creator A5033573966 @default.
• W4328007341 creator A5065073978 @default.
• W4328007341 creator A5072444630 @default.
• W4328007341 creator A5077947981 @default.
• W4328007341 date "2023-10-01" @default.
• W4328007341 modified "2023-10-15" @default.
• W4328007341 title "Exploring Spatio–Temporal Graph Convolution for Video-Based Human–Object Interaction Recognition" @default.
• W4328007341 cites W1483019628 @default.
• W4328007341 cites W1522734439 @default.
• W4328007341 cites W2146055337 @default.
• W4328007341 cites W2214124602 @default.
• W4328007341 cites W2333112450 @default.
• W4328007341 cites W2337252826 @default.
• W4328007341 cites W2342662179 @default.
• W4328007341 cites W2461621749 @default.
• W4328007341 cites W2618799552 @default.
• W4328007341 cites W2625366777 @default.
• W4328007341 cites W2791307013 @default.
• W4328007341 cites W2806331055 @default.
• W4328007341 cites W2883275382 @default.
• W4328007341 cites W2888096830 @default.
• W4328007341 cites W2914868535 @default.
• W4328007341 cites W2941651142 @default.
• W4328007341 cites W2951702519 @default.
• W4328007341 cites W2955874753 @default.
• W4328007341 cites W2963076818 @default.
• W4328007341 cites W2963091558 @default.
• W4328007341 cites W2963165299 @default.
• W4328007341 cites W2963524571 @default.
• W4328007341 cites W2963563276 @default.
• W4328007341 cites W2963699792 @default.
• W4328007341 cites W2963722382 @default.
• W4328007341 cites W2964291233 @default.
• W4328007341 cites W2981773282 @default.
• W4328007341 cites W2982220924 @default.
• W4328007341 cites W2983465317 @default.
• W4328007341 cites W2986407524 @default.
• W4328007341 cites W2990503944 @default.
• W4328007341 cites W2996847713 @default.
• W4328007341 cites W3009916215 @default.
• W4328007341 cites W3010071343 @default.
• W4328007341 cites W3034257141 @default.
• W4328007341 cites W3034679267 @default.
• W4328007341 cites W3034951775 @default.
• W4328007341 cites W3047772167 @default.
• W4328007341 cites W3049318984 @default.
• W4328007341 cites W3081111248 @default.
• W4328007341 cites W3095013945 @default.
• W4328007341 cites W3095753865 @default.
• W4328007341 cites W3106925514 @default.
• W4328007341 cites W3112282513 @default.
• W4328007341 cites W3119381934 @default.
• W4328007341 cites W3128587100 @default.
• W4328007341 cites W3132408010 @default.
• W4328007341 cites W3166712493 @default.
• W4328007341 cites W3176070213 @default.
• W4328007341 cites W3202407433 @default.
• W4328007341 cites W3207158043 @default.
• W4328007341 cites W3209102402 @default.
• W4328007341 cites W3212645988 @default.
• W4328007341 cites W3215084804 @default.
• W4328007341 cites W4200017248 @default.
• W4328007341 cites W4313034743 @default.
• W4328007341 doi "https://doi.org/10.1109/tcsvt.2023.3259430" @default.
• W4328007341 hasPublicationYear "2023" @default.
• W4328007341 type Work @default.
• W4328007341 citedByCount "0" @default.
• W4328007341 crossrefType "journal-article" @default.
• W4328007341 hasAuthorship W4328007341A5000205091 @default.
• W4328007341 hasAuthorship W4328007341A5001104491 @default.
• W4328007341 hasAuthorship W4328007341A5022848316 @default.
• W4328007341 hasAuthorship W4328007341A5028794275 @default.
• W4328007341 hasAuthorship W4328007341A5032579154 @default.
• W4328007341 hasAuthorship W4328007341A5033573966 @default.
• W4328007341 hasAuthorship W4328007341A5065073978 @default.
• W4328007341 hasAuthorship W4328007341A5072444630 @default.
• W4328007341 hasAuthorship W4328007341A5077947981 @default.
• W4328007341 hasConcept C126042441 @default.
• W4328007341 hasConcept C132525143 @default.
• W4328007341 hasConcept C153180895 @default.
• W4328007341 hasConcept C154945302 @default.
• W4328007341 hasConcept C186644900 @default.
• W4328007341 hasConcept C2780719617 @default.
• W4328007341 hasConcept C2781238097 @default.
• W4328007341 hasConcept C31972630 @default.
• W4328007341 hasConcept C41008148 @default.
• W4328007341 hasConcept C76155785 @default.
• W4328007341 hasConcept C80444323 @default.
• W4328007341 hasConceptScore W4328007341C126042441 @default.
• W4328007341 hasConceptScore W4328007341C132525143 @default.
• W4328007341 hasConceptScore W4328007341C153180895 @default.

• next