Matches in SemOpenAlex for { <https://semopenalex.org/work/W2791656037> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W2791656037 abstract "Visual-semantic features play a vital role for crowded video understanding. Convolutional Neural Networks (CNNs) have experienced a significant breakthrough in learning representations from images. However, the learning of visualsemantic features, and how it can be effectively extracted for video analysis, still remains a challenging task. In this study, we propose a novel visual-semantic method to capture both appearance and dynamic representations. In particular, we propose a spatial context method, based on the fractional Fisher vector (FV) encoding on CNN features, which can be regarded as our main contribution. In addition, to capture temporal context information, we also applied fractional encoding method on dynamic images. Experimental results on the WWW crowed video dataset demonstrate that the proposed method outperform the state of the art." @default.
- W2791656037 created "2018-03-29" @default.
- W2791656037 creator A5028255512 @default.
- W2791656037 creator A5042908837 @default.
- W2791656037 date "2018-03-08" @default.
- W2791656037 modified "2023-09-28" @default.
- W2791656037 title "Deep visual-semantic for crowded video understanding" @default.
- W2791656037 doi "https://doi.org/10.1117/12.2285848" @default.
- W2791656037 hasPublicationYear "2018" @default.
- W2791656037 type Work @default.
- W2791656037 sameAs 2791656037 @default.
- W2791656037 citedByCount "0" @default.
- W2791656037 crossrefType "proceedings-article" @default.
- W2791656037 hasAuthorship W2791656037A5028255512 @default.
- W2791656037 hasAuthorship W2791656037A5042908837 @default.
- W2791656037 hasConcept C108583219 @default.
- W2791656037 hasConcept C125411270 @default.
- W2791656037 hasConcept C151730666 @default.
- W2791656037 hasConcept C153180895 @default.
- W2791656037 hasConcept C154945302 @default.
- W2791656037 hasConcept C162324750 @default.
- W2791656037 hasConcept C184337299 @default.
- W2791656037 hasConcept C187736073 @default.
- W2791656037 hasConcept C199360897 @default.
- W2791656037 hasConcept C2779343474 @default.
- W2791656037 hasConcept C2780451532 @default.
- W2791656037 hasConcept C31972630 @default.
- W2791656037 hasConcept C41008148 @default.
- W2791656037 hasConcept C81363708 @default.
- W2791656037 hasConcept C86803240 @default.
- W2791656037 hasConceptScore W2791656037C108583219 @default.
- W2791656037 hasConceptScore W2791656037C125411270 @default.
- W2791656037 hasConceptScore W2791656037C151730666 @default.
- W2791656037 hasConceptScore W2791656037C153180895 @default.
- W2791656037 hasConceptScore W2791656037C154945302 @default.
- W2791656037 hasConceptScore W2791656037C162324750 @default.
- W2791656037 hasConceptScore W2791656037C184337299 @default.
- W2791656037 hasConceptScore W2791656037C187736073 @default.
- W2791656037 hasConceptScore W2791656037C199360897 @default.
- W2791656037 hasConceptScore W2791656037C2779343474 @default.
- W2791656037 hasConceptScore W2791656037C2780451532 @default.
- W2791656037 hasConceptScore W2791656037C31972630 @default.
- W2791656037 hasConceptScore W2791656037C41008148 @default.
- W2791656037 hasConceptScore W2791656037C81363708 @default.
- W2791656037 hasConceptScore W2791656037C86803240 @default.
- W2791656037 hasLocation W27916560371 @default.
- W2791656037 hasOpenAccess W2791656037 @default.
- W2791656037 hasPrimaryLocation W27916560371 @default.
- W2791656037 hasRelatedWork W1947727767 @default.
- W2791656037 hasRelatedWork W2114558148 @default.
- W2791656037 hasRelatedWork W2186282052 @default.
- W2791656037 hasRelatedWork W2198618282 @default.
- W2791656037 hasRelatedWork W2573132524 @default.
- W2791656037 hasRelatedWork W2594156432 @default.
- W2791656037 hasRelatedWork W2931641530 @default.
- W2791656037 hasRelatedWork W2989132293 @default.
- W2791656037 hasRelatedWork W2997266077 @default.
- W2791656037 hasRelatedWork W3038017128 @default.
- W2791656037 hasRelatedWork W3047822367 @default.
- W2791656037 hasRelatedWork W3090779142 @default.
- W2791656037 hasRelatedWork W3130464934 @default.
- W2791656037 hasRelatedWork W3131812503 @default.
- W2791656037 hasRelatedWork W3162758083 @default.
- W2791656037 hasRelatedWork W3189670121 @default.
- W2791656037 hasRelatedWork W3198940792 @default.
- W2791656037 hasRelatedWork W3199288805 @default.
- W2791656037 hasRelatedWork W3205951953 @default.
- W2791656037 hasRelatedWork W3206577156 @default.
- W2791656037 isParatext "false" @default.
- W2791656037 isRetracted "false" @default.
- W2791656037 magId "2791656037" @default.
- W2791656037 workType "article" @default.