Matches in SemOpenAlex for { <https://semopenalex.org/work/W2617849324> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W2617849324 abstract "Predicting human interaction is challenging as the on-going activity has to be inferred based on a partially observed video. Essentially, a good algorithm should effectively model the mutual influence between the two interacting subjects. Also, only a small region in the scene is discriminative for identifying the on-going interaction. In this work, we propose a relative attention model to explicitly address these difficulties. Built on a tri-coupled deep recurrent structure representing both interacting subjects and global interaction status, the proposed network collects spatio-temporal information from each subject, rectified with global interaction information, yielding effective interaction representation. Moreover, the proposed network also unifies an attention module to assign higher importance to the regions which are relevant to the on-going action. Extensive experiments have been conducted on two public datasets, and the results demonstrate that the proposed relative attention network successfully predicts informative regions between interacting subjects, which in turn yields superior human interaction prediction accuracy." @default.
- W2617849324 created "2017-06-05" @default.
- W2617849324 creator A5014362734 @default.
- W2617849324 creator A5019708391 @default.
- W2617849324 creator A5048907728 @default.
- W2617849324 date "2017-05-26" @default.
- W2617849324 modified "2023-09-28" @default.
- W2617849324 title "Predicting Human Interaction via Relative Attention Model" @default.
- W2617849324 cites W109378472 @default.
- W2617849324 cites W1947481528 @default.
- W2617849324 cites W1983364832 @default.
- W2617849324 cites W2002979823 @default.
- W2617849324 cites W2064675550 @default.
- W2617849324 cites W2118527252 @default.
- W2617849324 cites W2147615062 @default.
- W2617849324 cites W2185953016 @default.
- W2617849324 cites W2198577854 @default.
- W2617849324 cites W2472970127 @default.
- W2617849324 cites W2472986212 @default.
- W2617849324 cites W2950094539 @default.
- W2617849324 cites W2952186347 @default.
- W2617849324 cites W2964308564 @default.
- W2617849324 cites W66452226 @default.
- W2617849324 doi "https://doi.org/10.48550/arxiv.1705.09467" @default.
- W2617849324 hasPublicationYear "2017" @default.
- W2617849324 type Work @default.
- W2617849324 sameAs 2617849324 @default.
- W2617849324 citedByCount "0" @default.
- W2617849324 crossrefType "posted-content" @default.
- W2617849324 hasAuthorship W2617849324A5014362734 @default.
- W2617849324 hasAuthorship W2617849324A5019708391 @default.
- W2617849324 hasAuthorship W2617849324A5048907728 @default.
- W2617849324 hasBestOaLocation W26178493241 @default.
- W2617849324 hasConcept C105795698 @default.
- W2617849324 hasConcept C107457646 @default.
- W2617849324 hasConcept C119857082 @default.
- W2617849324 hasConcept C121332964 @default.
- W2617849324 hasConcept C136764020 @default.
- W2617849324 hasConcept C152139883 @default.
- W2617849324 hasConcept C154945302 @default.
- W2617849324 hasConcept C17744445 @default.
- W2617849324 hasConcept C199539241 @default.
- W2617849324 hasConcept C2776359362 @default.
- W2617849324 hasConcept C2780791683 @default.
- W2617849324 hasConcept C2780806968 @default.
- W2617849324 hasConcept C2987082051 @default.
- W2617849324 hasConcept C2993807640 @default.
- W2617849324 hasConcept C33923547 @default.
- W2617849324 hasConcept C38764148 @default.
- W2617849324 hasConcept C41008148 @default.
- W2617849324 hasConcept C62520636 @default.
- W2617849324 hasConcept C94625758 @default.
- W2617849324 hasConcept C97931131 @default.
- W2617849324 hasConceptScore W2617849324C105795698 @default.
- W2617849324 hasConceptScore W2617849324C107457646 @default.
- W2617849324 hasConceptScore W2617849324C119857082 @default.
- W2617849324 hasConceptScore W2617849324C121332964 @default.
- W2617849324 hasConceptScore W2617849324C136764020 @default.
- W2617849324 hasConceptScore W2617849324C152139883 @default.
- W2617849324 hasConceptScore W2617849324C154945302 @default.
- W2617849324 hasConceptScore W2617849324C17744445 @default.
- W2617849324 hasConceptScore W2617849324C199539241 @default.
- W2617849324 hasConceptScore W2617849324C2776359362 @default.
- W2617849324 hasConceptScore W2617849324C2780791683 @default.
- W2617849324 hasConceptScore W2617849324C2780806968 @default.
- W2617849324 hasConceptScore W2617849324C2987082051 @default.
- W2617849324 hasConceptScore W2617849324C2993807640 @default.
- W2617849324 hasConceptScore W2617849324C33923547 @default.
- W2617849324 hasConceptScore W2617849324C38764148 @default.
- W2617849324 hasConceptScore W2617849324C41008148 @default.
- W2617849324 hasConceptScore W2617849324C62520636 @default.
- W2617849324 hasConceptScore W2617849324C94625758 @default.
- W2617849324 hasConceptScore W2617849324C97931131 @default.
- W2617849324 hasLocation W26178493241 @default.
- W2617849324 hasLocation W26178493242 @default.
- W2617849324 hasOpenAccess W2617849324 @default.
- W2617849324 hasPrimaryLocation W26178493241 @default.
- W2617849324 hasRelatedWork W2026121273 @default.
- W2617849324 hasRelatedWork W2102106825 @default.
- W2617849324 hasRelatedWork W2617849324 @default.
- W2617849324 hasRelatedWork W2801772698 @default.
- W2617849324 hasRelatedWork W2961085424 @default.
- W2617849324 hasRelatedWork W2962938888 @default.
- W2617849324 hasRelatedWork W2983744209 @default.
- W2617849324 hasRelatedWork W4206452239 @default.
- W2617849324 hasRelatedWork W4379919398 @default.
- W2617849324 hasRelatedWork W66955737 @default.
- W2617849324 isParatext "false" @default.
- W2617849324 isRetracted "false" @default.
- W2617849324 magId "2617849324" @default.
- W2617849324 workType "article" @default.