Matches in SemOpenAlex for { <https://semopenalex.org/work/W2884454321> ?p ?o ?g. }
- W2884454321 endingPage "552" @default.
- W2884454321 startingPage "536" @default.
- W2884454321 abstract "Visual keyword spotting (KWS) is the problem of estimating whether a text query occurs in a given recording using only video information. This paper focuses on visual KWS for words unseen during training, a real-world, practical setting which so far has received no attention by the community. To this end, we devise an end-to-end architecture comprising (a) a state-of-the-art visual feature extractor based on spatiotemporal Residual Networks, (b) a grapheme-to-phoneme model based on sequence-to-sequence neural networks, and (c) a stack of recurrent neural networks which learn how to correlate visual features with the keyword representation. Different to prior works on KWS, which try to learn word representations merely from sequences of graphemes (i.e. letters), we propose the use of a grapheme-to-phoneme encoder-decoder model which learns how to map words to their pronunciation. We demonstrate that our system obtains very promising visual-only KWS results on the challenging LRS2 database, for keywords unseen during training. We also show that our system outperforms a baseline which addresses KWS via automatic speech recognition (ASR), while it drastically improves over other recently proposed ASR-free KWS methods." @default.
- W2884454321 created "2018-08-03" @default.
- W2884454321 creator A5024224610 @default.
- W2884454321 creator A5061939508 @default.
- W2884454321 date "2018-01-01" @default.
- W2884454321 modified "2023-10-15" @default.
- W2884454321 title "Zero-Shot Keyword Spotting for Visual Speech Recognition In-the-wild" @default.
- W2884454321 cites W114193738 @default.
- W2884454321 cites W1494198834 @default.
- W2884454321 cites W1503933356 @default.
- W2884454321 cites W1526392145 @default.
- W2884454321 cites W1553469512 @default.
- W2884454321 cites W2015143272 @default.
- W2884454321 cites W2034940213 @default.
- W2884454321 cites W2064675550 @default.
- W2884454321 cites W2171061940 @default.
- W2884454321 cites W2250539671 @default.
- W2884454321 cites W2293968535 @default.
- W2884454321 cites W2296681920 @default.
- W2884454321 cites W2302255633 @default.
- W2884454321 cites W2327501763 @default.
- W2884454321 cites W2365880764 @default.
- W2884454321 cites W2462496837 @default.
- W2884454321 cites W2508907749 @default.
- W2884454321 cites W2510945575 @default.
- W2884454321 cites W2521999726 @default.
- W2884454321 cites W2545177271 @default.
- W2884454321 cites W2578392894 @default.
- W2884454321 cites W2594690981 @default.
- W2884454321 cites W2596142952 @default.
- W2884454321 cites W2597757402 @default.
- W2884454321 cites W2748659049 @default.
- W2884454321 cites W2766219058 @default.
- W2884454321 cites W2790326622 @default.
- W2884454321 cites W2799956544 @default.
- W2884454321 cites W2806872492 @default.
- W2884454321 cites W2891226622 @default.
- W2884454321 cites W2952746495 @default.
- W2884454321 cites W2962780374 @default.
- W2884454321 cites W2963030892 @default.
- W2884454321 cites W2963299674 @default.
- W2884454321 cites W2963356069 @default.
- W2884454321 cites W2963528589 @default.
- W2884454321 cites W2963654155 @default.
- W2884454321 cites W2963658982 @default.
- W2884454321 cites W2964283370 @default.
- W2884454321 doi "https://doi.org/10.1007/978-3-030-01225-0_32" @default.
- W2884454321 hasPublicationYear "2018" @default.
- W2884454321 type Work @default.
- W2884454321 sameAs 2884454321 @default.
- W2884454321 citedByCount "26" @default.
- W2884454321 countsByYear W28844543212018 @default.
- W2884454321 countsByYear W28844543212019 @default.
- W2884454321 countsByYear W28844543212020 @default.
- W2884454321 countsByYear W28844543212021 @default.
- W2884454321 countsByYear W28844543212022 @default.
- W2884454321 countsByYear W28844543212023 @default.
- W2884454321 crossrefType "book-chapter" @default.
- W2884454321 hasAuthorship W2884454321A5024224610 @default.
- W2884454321 hasAuthorship W2884454321A5061939508 @default.
- W2884454321 hasBestOaLocation W28844543212 @default.
- W2884454321 hasConcept C111919701 @default.
- W2884454321 hasConcept C118505674 @default.
- W2884454321 hasConcept C121332964 @default.
- W2884454321 hasConcept C138885662 @default.
- W2884454321 hasConcept C153180895 @default.
- W2884454321 hasConcept C154945302 @default.
- W2884454321 hasConcept C204321447 @default.
- W2884454321 hasConcept C2776401178 @default.
- W2884454321 hasConcept C2776779415 @default.
- W2884454321 hasConcept C2778112365 @default.
- W2884454321 hasConcept C2779506182 @default.
- W2884454321 hasConcept C2781213101 @default.
- W2884454321 hasConcept C28490314 @default.
- W2884454321 hasConcept C30080830 @default.
- W2884454321 hasConcept C41008148 @default.
- W2884454321 hasConcept C41895202 @default.
- W2884454321 hasConcept C54355233 @default.
- W2884454321 hasConcept C62520636 @default.
- W2884454321 hasConcept C86803240 @default.
- W2884454321 hasConcept C90805587 @default.
- W2884454321 hasConceptScore W2884454321C111919701 @default.
- W2884454321 hasConceptScore W2884454321C118505674 @default.
- W2884454321 hasConceptScore W2884454321C121332964 @default.
- W2884454321 hasConceptScore W2884454321C138885662 @default.
- W2884454321 hasConceptScore W2884454321C153180895 @default.
- W2884454321 hasConceptScore W2884454321C154945302 @default.
- W2884454321 hasConceptScore W2884454321C204321447 @default.
- W2884454321 hasConceptScore W2884454321C2776401178 @default.
- W2884454321 hasConceptScore W2884454321C2776779415 @default.
- W2884454321 hasConceptScore W2884454321C2778112365 @default.
- W2884454321 hasConceptScore W2884454321C2779506182 @default.
- W2884454321 hasConceptScore W2884454321C2781213101 @default.
- W2884454321 hasConceptScore W2884454321C28490314 @default.
- W2884454321 hasConceptScore W2884454321C30080830 @default.
- W2884454321 hasConceptScore W2884454321C41008148 @default.
- W2884454321 hasConceptScore W2884454321C41895202 @default.
- W2884454321 hasConceptScore W2884454321C54355233 @default.