Matches in SemOpenAlex for { <https://semopenalex.org/work/W3195627504> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W3195627504 endingPage "108256" @default.
- W3195627504 startingPage "108256" @default.
- W3195627504 abstract "Head gesture videos recorded of a person bear rich information about the individual. Automatically understanding these videos can empower many useful human-centered applications in areas such as smart health, education, work safety and security. To understand a video’s content, low-level head gesture signals carried in the video that capture characteristics of both human postures and motions need to be translated into high-level semantic labels. To meet this aim, we propose a hierarchical model for learning to understand head gesture videos. Given a head gesture video of an arbitrary length, the model first segments the full-length video into multiple short clips for clip-based feature extraction. Multiple base feature extraction procedures are then independently tuned via a set of peripheral learning tasks without consuming any labels of the goal task. These independently derived base features are subsequently aggregated through a multi-task learning framework, coupled with a feature dimensionality reduction module, to optimally learn to accomplish the end video understanding task in an weakly supervised manner, utilizing the limited amount of video labels available of the goal task. Experimental results show that the hierarchical model is superior to multiple state-of-the-art peer methods in tackling versatile video understanding tasks." @default.
- W3195627504 created "2021-08-30" @default.
- W3195627504 creator A5008274291 @default.
- W3195627504 creator A5024124445 @default.
- W3195627504 creator A5046202286 @default.
- W3195627504 date "2022-01-01" @default.
- W3195627504 modified "2023-10-09" @default.
- W3195627504 title "A hierarchical model for learning to understand head gesture videos" @default.
- W3195627504 cites W1689711448 @default.
- W3195627504 cites W2041944868 @default.
- W3195627504 cites W2047875689 @default.
- W3195627504 cites W2050589246 @default.
- W3195627504 cites W2055816619 @default.
- W3195627504 cites W2064675550 @default.
- W3195627504 cites W2066005892 @default.
- W3195627504 cites W2079735306 @default.
- W3195627504 cites W2110119381 @default.
- W3195627504 cites W2168407388 @default.
- W3195627504 cites W2184544926 @default.
- W3195627504 cites W2610401274 @default.
- W3195627504 cites W2746907908 @default.
- W3195627504 cites W2769568664 @default.
- W3195627504 cites W2913340405 @default.
- W3195627504 cites W2963377935 @default.
- W3195627504 cites W2964167369 @default.
- W3195627504 cites W3019124755 @default.
- W3195627504 doi "https://doi.org/10.1016/j.patcog.2021.108256" @default.
- W3195627504 hasPublicationYear "2022" @default.
- W3195627504 type Work @default.
- W3195627504 sameAs 3195627504 @default.
- W3195627504 citedByCount "3" @default.
- W3195627504 countsByYear W31956275042023 @default.
- W3195627504 crossrefType "journal-article" @default.
- W3195627504 hasAuthorship W3195627504A5008274291 @default.
- W3195627504 hasAuthorship W3195627504A5024124445 @default.
- W3195627504 hasAuthorship W3195627504A5046202286 @default.
- W3195627504 hasConcept C119857082 @default.
- W3195627504 hasConcept C138885662 @default.
- W3195627504 hasConcept C154945302 @default.
- W3195627504 hasConcept C159437735 @default.
- W3195627504 hasConcept C162324750 @default.
- W3195627504 hasConcept C177264268 @default.
- W3195627504 hasConcept C187736073 @default.
- W3195627504 hasConcept C199360897 @default.
- W3195627504 hasConcept C207347870 @default.
- W3195627504 hasConcept C2776401178 @default.
- W3195627504 hasConcept C2780451532 @default.
- W3195627504 hasConcept C31972630 @default.
- W3195627504 hasConcept C41008148 @default.
- W3195627504 hasConcept C41895202 @default.
- W3195627504 hasConcept C52622490 @default.
- W3195627504 hasConceptScore W3195627504C119857082 @default.
- W3195627504 hasConceptScore W3195627504C138885662 @default.
- W3195627504 hasConceptScore W3195627504C154945302 @default.
- W3195627504 hasConceptScore W3195627504C159437735 @default.
- W3195627504 hasConceptScore W3195627504C162324750 @default.
- W3195627504 hasConceptScore W3195627504C177264268 @default.
- W3195627504 hasConceptScore W3195627504C187736073 @default.
- W3195627504 hasConceptScore W3195627504C199360897 @default.
- W3195627504 hasConceptScore W3195627504C207347870 @default.
- W3195627504 hasConceptScore W3195627504C2776401178 @default.
- W3195627504 hasConceptScore W3195627504C2780451532 @default.
- W3195627504 hasConceptScore W3195627504C31972630 @default.
- W3195627504 hasConceptScore W3195627504C41008148 @default.
- W3195627504 hasConceptScore W3195627504C41895202 @default.
- W3195627504 hasConceptScore W3195627504C52622490 @default.
- W3195627504 hasFunder F4320321001 @default.
- W3195627504 hasLocation W31956275041 @default.
- W3195627504 hasOpenAccess W3195627504 @default.
- W3195627504 hasPrimaryLocation W31956275041 @default.
- W3195627504 hasRelatedWork W1554778538 @default.
- W3195627504 hasRelatedWork W2057046019 @default.
- W3195627504 hasRelatedWork W2107891793 @default.
- W3195627504 hasRelatedWork W2234765641 @default.
- W3195627504 hasRelatedWork W2367741884 @default.
- W3195627504 hasRelatedWork W2526382347 @default.
- W3195627504 hasRelatedWork W2534909612 @default.
- W3195627504 hasRelatedWork W2941417316 @default.
- W3195627504 hasRelatedWork W3194595645 @default.
- W3195627504 hasRelatedWork W879554143 @default.
- W3195627504 hasVolume "121" @default.
- W3195627504 isParatext "false" @default.
- W3195627504 isRetracted "false" @default.
- W3195627504 magId "3195627504" @default.
- W3195627504 workType "article" @default.