VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text.
Resource URI: https://dblp.l3s.de/d2r/resource/publications/conf/nips/AkbariYQCCCG21
Home
|
Example Publications
Property
Value
dcterms:
bibliographicCitation
<
http://dblp.uni-trier.de/rec/bibtex/conf/nips/AkbariYQCCCG21
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Boqing_Gong
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Hassan_Akbari
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Liangzhe_Yuan
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Rui_Qian
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Shih-Fu_Chang
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Wei-Hong_Chuang
>
dc:
creator
<
https://dblp.l3s.de/d2r/resource/authors/Yin_Cui
>
foaf:
homepage
<
https://proceedings.neurips.cc/paper/2021/hash/cb3213ada48302953cb0f166464ab356-Abstract.html
>
dc:
identifier
DBLP conf/nips/AkbariYQCCCG21
(xsd:string)
dcterms:
issued
2021
(xsd:gYear)
rdfs:
label
VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text.
(xsd:string)
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Boqing_Gong
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Hassan_Akbari
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Liangzhe_Yuan
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Rui_Qian
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Shih-Fu_Chang
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Wei-Hong_Chuang
>
foaf:
maker
<
https://dblp.l3s.de/d2r/resource/authors/Yin_Cui
>
swrc:
pages
24206-24221
(xsd:string)
dcterms:
partOf
<
https://dblp.l3s.de/d2r/resource/publications/conf/nips/2021
>
owl:
sameAs
<
http://bibsonomy.org/uri/bibtexkey/conf/nips/AkbariYQCCCG21/dblp
>
owl:
sameAs
<
http://dblp.rkbexplorer.com/id/conf/nips/AkbariYQCCCG21
>
rdfs:
seeAlso
<
http://dblp.uni-trier.de/db/conf/nips/neurips2021.html#AkbariYQCCCG21
>
rdfs:
seeAlso
<
https://proceedings.neurips.cc/paper/2021/hash/cb3213ada48302953cb0f166464ab356-Abstract.html
>
swrc:
series
<
https://dblp.l3s.de/d2r/resource/conferences/nips
>
dc:
title
VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text.
(xsd:string)
dc:
type
<
http://purl.org/dc/dcmitype/Text
>
rdf:
type
swrc:InProceedings
rdf:
type
foaf:Document