Matches in SemOpenAlex for { <https://semopenalex.org/work/W4318940682> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4318940682 endingPage "4656" @default.
- W4318940682 startingPage "4645" @default.
- W4318940682 abstract "Abstract Continuous sign language recognition (CSLR) is an essential task for communication between hearing-impaired and people without limitations, which aims at aligning low-density video sequences with high-density text sequences. The current methods for CSLR were mainly based on convolutional neural networks. However, these methods perform poorly in balancing spatial and temporal features during visual feature extraction, making them difficult to improve the accuracy of recognition. To address this issue, we designed an end-to-end CSLR network: Spatial–Temporal Transformer Network (STTN). The model encodes and decodes the sign language video as a predicted sequence that is aligned with a given text sequence. First, since the image sequences are too long for the model to handle directly, we chunk the sign language video frames, i.e., ”image to patch”, which reduces the computational complexity. Second, global features of the sign language video are modeled at the beginning of the model, and the spatial action features of the current video frame and the semantic features of consecutive frames in the temporal dimension are extracted separately, giving rise to fully extracting visual features. Finally, the model uses a simple cross-entropy loss to align video and text. We extensively evaluated the proposed network on two publicly available datasets, CSL and RWTH-PHOENIX-Weather multi-signer 2014 (PHOENIX-2014), which demonstrated the superior performance of our work in CSLR task compared to the state-of-the-art methods." @default.
- W4318940682 created "2023-02-03" @default.
- W4318940682 creator A5002219612 @default.
- W4318940682 creator A5006766331 @default.
- W4318940682 creator A5050277723 @default.
- W4318940682 creator A5067608694 @default.
- W4318940682 date "2023-02-03" @default.
- W4318940682 modified "2023-09-25" @default.
- W4318940682 title "Spatial–temporal transformer for end-to-end sign language recognition" @default.
- W4318940682 cites W2157331557 @default.
- W4318940682 cites W2188882108 @default.
- W4318940682 cites W2759302818 @default.
- W4318940682 cites W2781400102 @default.
- W4318940682 cites W2807840688 @default.
- W4318940682 cites W2895488603 @default.
- W4318940682 cites W2908497602 @default.
- W4318940682 cites W2941870244 @default.
- W4318940682 cites W2964110616 @default.
- W4318940682 cites W2964253156 @default.
- W4318940682 cites W2997931247 @default.
- W4318940682 cites W3009828227 @default.
- W4318940682 cites W3034765865 @default.
- W4318940682 cites W3092042812 @default.
- W4318940682 cites W3096609285 @default.
- W4318940682 cites W3109271037 @default.
- W4318940682 cites W3147467731 @default.
- W4318940682 cites W3160382762 @default.
- W4318940682 cites W3170841864 @default.
- W4318940682 cites W3203359574 @default.
- W4318940682 cites W3203480968 @default.
- W4318940682 cites W4224216771 @default.
- W4318940682 cites W4307123709 @default.
- W4318940682 doi "https://doi.org/10.1007/s40747-023-00977-w" @default.
- W4318940682 hasPublicationYear "2023" @default.
- W4318940682 type Work @default.
- W4318940682 citedByCount "0" @default.
- W4318940682 crossrefType "journal-article" @default.
- W4318940682 hasAuthorship W4318940682A5002219612 @default.
- W4318940682 hasAuthorship W4318940682A5006766331 @default.
- W4318940682 hasAuthorship W4318940682A5050277723 @default.
- W4318940682 hasAuthorship W4318940682A5067608694 @default.
- W4318940682 hasBestOaLocation W43189406821 @default.
- W4318940682 hasConcept C121332964 @default.
- W4318940682 hasConcept C138885662 @default.
- W4318940682 hasConcept C153180895 @default.
- W4318940682 hasConcept C154945302 @default.
- W4318940682 hasConcept C165801399 @default.
- W4318940682 hasConcept C28490314 @default.
- W4318940682 hasConcept C31972630 @default.
- W4318940682 hasConcept C41008148 @default.
- W4318940682 hasConcept C41895202 @default.
- W4318940682 hasConcept C522192633 @default.
- W4318940682 hasConcept C52622490 @default.
- W4318940682 hasConcept C62520636 @default.
- W4318940682 hasConcept C66322947 @default.
- W4318940682 hasConcept C81363708 @default.
- W4318940682 hasConceptScore W4318940682C121332964 @default.
- W4318940682 hasConceptScore W4318940682C138885662 @default.
- W4318940682 hasConceptScore W4318940682C153180895 @default.
- W4318940682 hasConceptScore W4318940682C154945302 @default.
- W4318940682 hasConceptScore W4318940682C165801399 @default.
- W4318940682 hasConceptScore W4318940682C28490314 @default.
- W4318940682 hasConceptScore W4318940682C31972630 @default.
- W4318940682 hasConceptScore W4318940682C41008148 @default.
- W4318940682 hasConceptScore W4318940682C41895202 @default.
- W4318940682 hasConceptScore W4318940682C522192633 @default.
- W4318940682 hasConceptScore W4318940682C52622490 @default.
- W4318940682 hasConceptScore W4318940682C62520636 @default.
- W4318940682 hasConceptScore W4318940682C66322947 @default.
- W4318940682 hasConceptScore W4318940682C81363708 @default.
- W4318940682 hasFunder F4320321001 @default.
- W4318940682 hasIssue "4" @default.
- W4318940682 hasLocation W43189406821 @default.
- W4318940682 hasOpenAccess W4318940682 @default.
- W4318940682 hasPrimaryLocation W43189406821 @default.
- W4318940682 hasRelatedWork W1964120219 @default.
- W4318940682 hasRelatedWork W2144059113 @default.
- W4318940682 hasRelatedWork W2146076056 @default.
- W4318940682 hasRelatedWork W2406522397 @default.
- W4318940682 hasRelatedWork W2767651786 @default.
- W4318940682 hasRelatedWork W2811390910 @default.
- W4318940682 hasRelatedWork W2912288872 @default.
- W4318940682 hasRelatedWork W2913302899 @default.
- W4318940682 hasRelatedWork W3003836766 @default.
- W4318940682 hasRelatedWork W4312376745 @default.
- W4318940682 hasVolume "9" @default.
- W4318940682 isParatext "false" @default.
- W4318940682 isRetracted "false" @default.
- W4318940682 workType "article" @default.