Matches in SemOpenAlex for { <https://semopenalex.org/work/W2903314716> ?p ?o ?g. }
- W2903314716 abstract "Sign language recognition is a challenging and often underestimated problem comprising multi-modal articulators (handshape, orientation, movement, upper body and face) that integrate asynchronously on multiple streams. Learning powerful statistical models in such a scenario requires much data, particularly to apply recent advances of the field. However, labeled data is a scarce resource for sign language due to the enormous cost of transcribing these unwritten languages. We propose the first real-life large-scale sign language data set comprising over 25,000 annotated videos, which we thoroughly evaluate with state-of-the-art methods from sign and related action recognition. Unlike the current state-of-the-art, the data set allows to investigate the generalization to unseen individuals (signer-independent test) in a realistic setting with over 200 signers. Previous work mostly deals with limited vocabulary tasks, while here, we cover a large class count of 1000 signs in challenging and unconstrained real-life recording conditions. We further propose I3D, known from video classifications, as a powerful and suitable architecture for sign language recognition, outperforming the current state-of-the-art by a large margin. The data set is publicly available to the community." @default.
- W2903314716 created "2018-12-11" @default.
- W2903314716 creator A5022551740 @default.
- W2903314716 creator A5032345007 @default.
- W2903314716 date "2018-12-03" @default.
- W2903314716 modified "2023-09-27" @default.
- W2903314716 title "MS-ASL: A Large-Scale Data Set and Benchmark for Understanding American Sign Language." @default.
- W2903314716 cites W107615642 @default.
- W2903314716 cites W1487456012 @default.
- W2903314716 cites W1506441995 @default.
- W2903314716 cites W1522734439 @default.
- W2903314716 cites W1545990416 @default.
- W2903314716 cites W1547391644 @default.
- W2903314716 cites W1579818084 @default.
- W2903314716 cites W159724101 @default.
- W2903314716 cites W1639784222 @default.
- W2903314716 cites W1686810756 @default.
- W2903314716 cites W1836465849 @default.
- W2903314716 cites W1947481528 @default.
- W2903314716 cites W1950788856 @default.
- W2903314716 cites W196736872 @default.
- W2903314716 cites W1969724184 @default.
- W2903314716 cites W1971252500 @default.
- W2903314716 cites W1981073134 @default.
- W2903314716 cites W1989626015 @default.
- W2903314716 cites W2016053056 @default.
- W2903314716 cites W2025808439 @default.
- W2903314716 cites W2064675550 @default.
- W2903314716 cites W2066601700 @default.
- W2903314716 cites W2075048802 @default.
- W2903314716 cites W2095687464 @default.
- W2903314716 cites W2097117768 @default.
- W2903314716 cites W2102170500 @default.
- W2903314716 cites W2104874772 @default.
- W2903314716 cites W2108598243 @default.
- W2903314716 cites W2113512957 @default.
- W2903314716 cites W2114663654 @default.
- W2903314716 cites W2121480453 @default.
- W2903314716 cites W2121996250 @default.
- W2903314716 cites W2125834953 @default.
- W2903314716 cites W2126579184 @default.
- W2903314716 cites W2126721694 @default.
- W2903314716 cites W2134983583 @default.
- W2903314716 cites W2145855310 @default.
- W2903314716 cites W2152988638 @default.
- W2903314716 cites W2156303437 @default.
- W2903314716 cites W2157548127 @default.
- W2903314716 cites W2160897043 @default.
- W2903314716 cites W2161755782 @default.
- W2903314716 cites W2163541894 @default.
- W2903314716 cites W2168068018 @default.
- W2903314716 cites W2170936593 @default.
- W2903314716 cites W2188882108 @default.
- W2903314716 cites W2250670799 @default.
- W2903314716 cites W2251285937 @default.
- W2903314716 cites W2307035320 @default.
- W2903314716 cites W2308045930 @default.
- W2903314716 cites W2342662179 @default.
- W2903314716 cites W2401084598 @default.
- W2903314716 cites W24089286 @default.
- W2903314716 cites W2471695703 @default.
- W2903314716 cites W2559085405 @default.
- W2903314716 cites W2577700712 @default.
- W2903314716 cites W2587277634 @default.
- W2903314716 cites W2607014458 @default.
- W2903314716 cites W2609211631 @default.
- W2903314716 cites W2746301562 @default.
- W2903314716 cites W2755802490 @default.
- W2903314716 cites W2796633859 @default.
- W2903314716 cites W2799020610 @default.
- W2903314716 cites W2895638065 @default.
- W2903314716 cites W2898283777 @default.
- W2903314716 cites W2904106524 @default.
- W2903314716 cites W2908497602 @default.
- W2903314716 cites W2941870244 @default.
- W2903314716 cites W2951183276 @default.
- W2903314716 cites W2963524571 @default.
- W2903314716 cites W2964253156 @default.
- W2903314716 cites W2964304707 @default.
- W2903314716 cites W3106250896 @default.
- W2903314716 cites W438884741 @default.
- W2903314716 cites W63415270 @default.
- W2903314716 cites W2109752280 @default.
- W2903314716 hasPublicationYear "2018" @default.
- W2903314716 type Work @default.
- W2903314716 sameAs 2903314716 @default.
- W2903314716 citedByCount "10" @default.
- W2903314716 countsByYear W29033147162019 @default.
- W2903314716 countsByYear W29033147162020 @default.
- W2903314716 countsByYear W29033147162021 @default.
- W2903314716 crossrefType "posted-content" @default.
- W2903314716 hasAuthorship W2903314716A5022551740 @default.
- W2903314716 hasAuthorship W2903314716A5032345007 @default.
- W2903314716 hasConcept C119857082 @default.
- W2903314716 hasConcept C121332964 @default.
- W2903314716 hasConcept C13280743 @default.
- W2903314716 hasConcept C134306372 @default.
- W2903314716 hasConcept C138885662 @default.
- W2903314716 hasConcept C139676723 @default.
- W2903314716 hasConcept C154945302 @default.