Matches in SemOpenAlex for { <https://semopenalex.org/work/W3093072712> ?p ?o ?g. }
- W3093072712 abstract "Learning effective representations of visual data that generalize to a variety of downstream tasks has been a long quest for computer vision. Most representation learning approaches rely solely on visual data such as images or videos. In this paper, we explore a novel approach, where we use human interaction and attention cues to investigate whether we can learn better representations compared to visual-only representations. For this study, we collect a dataset of human interactions capturing body part movements and gaze in their daily lives. Our experiments show that our muscly-supervised representation that encodes interaction and attention cues outperforms a visual-only state-of-the-art method MoCo (He et al.,2020), on a variety of target tasks: scene classification (semantic), action recognition (temporal), depth estimation (geometric), dynamics prediction (physics) and walkable surface estimation (affordance). Our code and dataset are available at: this https URL." @default.
- W3093072712 created "2020-10-22" @default.
- W3093072712 creator A5026171268 @default.
- W3093072712 creator A5026693645 @default.
- W3093072712 creator A5066132653 @default.
- W3093072712 creator A5070375939 @default.
- W3093072712 creator A5075652753 @default.
- W3093072712 date "2020-10-16" @default.
- W3093072712 modified "2023-09-27" @default.
- W3093072712 title "What Can You Learn from Your Muscles? Learning Visual Representation from Human Interactions" @default.
- W3093072712 cites W125693051 @default.
- W3093072712 cites W1520997877 @default.
- W3093072712 cites W1550621568 @default.
- W3093072712 cites W1821462560 @default.
- W3093072712 cites W1903029394 @default.
- W3093072712 cites W2017814585 @default.
- W3093072712 cites W2101032778 @default.
- W3093072712 cites W2102605133 @default.
- W3093072712 cites W2108598243 @default.
- W3093072712 cites W2138621090 @default.
- W3093072712 cites W2151103935 @default.
- W3093072712 cites W2152790380 @default.
- W3093072712 cites W219040644 @default.
- W3093072712 cites W2194775991 @default.
- W3093072712 cites W2198618282 @default.
- W3093072712 cites W2212494831 @default.
- W3093072712 cites W2321533354 @default.
- W3093072712 cites W2326925005 @default.
- W3093072712 cites W2338684808 @default.
- W3093072712 cites W2342877626 @default.
- W3093072712 cites W2565639579 @default.
- W3093072712 cites W2575671312 @default.
- W3093072712 cites W2613718673 @default.
- W3093072712 cites W2732026016 @default.
- W3093072712 cites W2750549109 @default.
- W3093072712 cites W2789198060 @default.
- W3093072712 cites W2798512429 @default.
- W3093072712 cites W2798963049 @default.
- W3093072712 cites W2799064164 @default.
- W3093072712 cites W2799269579 @default.
- W3093072712 cites W2842511635 @default.
- W3093072712 cites W2944828972 @default.
- W3093072712 cites W2949128343 @default.
- W3093072712 cites W2950104027 @default.
- W3093072712 cites W2952865063 @default.
- W3093072712 cites W2962742544 @default.
- W3093072712 cites W2963265008 @default.
- W3093072712 cites W2963368541 @default.
- W3093072712 cites W2964121744 @default.
- W3093072712 cites W2964242760 @default.
- W3093072712 cites W2964269434 @default.
- W3093072712 cites W2969853371 @default.
- W3093072712 cites W2971155163 @default.
- W3093072712 cites W2990873191 @default.
- W3093072712 cites W2994779004 @default.
- W3093072712 cites W2998388430 @default.
- W3093072712 cites W3005680577 @default.
- W3093072712 cites W3009561768 @default.
- W3093072712 cites W3012540512 @default.
- W3093072712 cites W3034781633 @default.
- W3093072712 cites W3035524453 @default.
- W3093072712 cites W3036982689 @default.
- W3093072712 cites W3045266435 @default.
- W3093072712 cites W3046614818 @default.
- W3093072712 cites W343636949 @default.
- W3093072712 hasPublicationYear "2020" @default.
- W3093072712 type Work @default.
- W3093072712 sameAs 3093072712 @default.
- W3093072712 citedByCount "0" @default.
- W3093072712 crossrefType "posted-content" @default.
- W3093072712 hasAuthorship W3093072712A5026171268 @default.
- W3093072712 hasAuthorship W3093072712A5026693645 @default.
- W3093072712 hasAuthorship W3093072712A5066132653 @default.
- W3093072712 hasAuthorship W3093072712A5070375939 @default.
- W3093072712 hasAuthorship W3093072712A5075652753 @default.
- W3093072712 hasConcept C107457646 @default.
- W3093072712 hasConcept C119857082 @default.
- W3093072712 hasConcept C121332964 @default.
- W3093072712 hasConcept C136197465 @default.
- W3093072712 hasConcept C154945302 @default.
- W3093072712 hasConcept C177264268 @default.
- W3093072712 hasConcept C17744445 @default.
- W3093072712 hasConcept C194995250 @default.
- W3093072712 hasConcept C199360897 @default.
- W3093072712 hasConcept C199539241 @default.
- W3093072712 hasConcept C2776359362 @default.
- W3093072712 hasConcept C2776760102 @default.
- W3093072712 hasConcept C2777212361 @default.
- W3093072712 hasConcept C2779916870 @default.
- W3093072712 hasConcept C2780791683 @default.
- W3093072712 hasConcept C2987834672 @default.
- W3093072712 hasConcept C41008148 @default.
- W3093072712 hasConcept C59404180 @default.
- W3093072712 hasConcept C62520636 @default.
- W3093072712 hasConcept C94625758 @default.
- W3093072712 hasConceptScore W3093072712C107457646 @default.
- W3093072712 hasConceptScore W3093072712C119857082 @default.
- W3093072712 hasConceptScore W3093072712C121332964 @default.
- W3093072712 hasConceptScore W3093072712C136197465 @default.
- W3093072712 hasConceptScore W3093072712C154945302 @default.