Matches in SemOpenAlex for { <https://semopenalex.org/work/W2015551990> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W2015551990 abstract "Recently, great progress has been made in sign language recognition. Most approaches are based on the Hidden Markov Model (HMM) with various features, such as motion trajectory. Recognition for sign sentences is obtained from optimal path by Viterbi algorithm, however, some wrong jumps are usually caused by transitional movements between signs. To address the problem, in this paper, we propose an approach consisting of two stages: offline training and online recognition. In the offline training stage, we propose a threshold matrix and rate thresholds. Each element of the threshold matrix describes the minimal probability when a segment belongs to a sign, and rate thresholds are defined as the average probability for signs. So, if certain segment's evaluation is smaller than all the thresholds, it is regarded as a transitional movement and then it should be removed. In the online recognition stage, coarse segmentation, based on the threshold matrix, records the time interval for fine segmentation, and fine segmentation, based on Dynamic Time Warping(DTW) and Length-Root method, determines the endpoint for each candidate sign and selects the most possible one. The final recognition is obtained by concatenating the most possible signs. We evaluate our approach with Kinect-based dataset and the experiments demonstrate the effectiveness of our approach." @default.
- W2015551990 created "2016-06-24" @default.
- W2015551990 creator A5046805800 @default.
- W2015551990 creator A5051680690 @default.
- W2015551990 creator A5078141810 @default.
- W2015551990 date "2014-07-10" @default.
- W2015551990 modified "2023-10-01" @default.
- W2015551990 title "A Threshold-based HMM-DTW Approach for Continuous Sign Language Recognition" @default.
- W2015551990 cites W2120701504 @default.
- W2015551990 cites W2125838338 @default.
- W2015551990 cites W2154790436 @default.
- W2015551990 cites W2157904315 @default.
- W2015551990 cites W2162298316 @default.
- W2015551990 doi "https://doi.org/10.1145/2632856.2632931" @default.
- W2015551990 hasPublicationYear "2014" @default.
- W2015551990 type Work @default.
- W2015551990 sameAs 2015551990 @default.
- W2015551990 citedByCount "39" @default.
- W2015551990 countsByYear W20155519902015 @default.
- W2015551990 countsByYear W20155519902016 @default.
- W2015551990 countsByYear W20155519902018 @default.
- W2015551990 countsByYear W20155519902019 @default.
- W2015551990 countsByYear W20155519902020 @default.
- W2015551990 countsByYear W20155519902021 @default.
- W2015551990 countsByYear W20155519902022 @default.
- W2015551990 countsByYear W20155519902023 @default.
- W2015551990 crossrefType "proceedings-article" @default.
- W2015551990 hasAuthorship W2015551990A5046805800 @default.
- W2015551990 hasAuthorship W2015551990A5051680690 @default.
- W2015551990 hasAuthorship W2015551990A5078141810 @default.
- W2015551990 hasConcept C121332964 @default.
- W2015551990 hasConcept C1276947 @default.
- W2015551990 hasConcept C134306372 @default.
- W2015551990 hasConcept C13662910 @default.
- W2015551990 hasConcept C138885662 @default.
- W2015551990 hasConcept C139676723 @default.
- W2015551990 hasConcept C153180895 @default.
- W2015551990 hasConcept C154945302 @default.
- W2015551990 hasConcept C199360897 @default.
- W2015551990 hasConcept C23224414 @default.
- W2015551990 hasConcept C2777735758 @default.
- W2015551990 hasConcept C28490314 @default.
- W2015551990 hasConcept C33923547 @default.
- W2015551990 hasConcept C41008148 @default.
- W2015551990 hasConcept C41895202 @default.
- W2015551990 hasConcept C522192633 @default.
- W2015551990 hasConcept C60582962 @default.
- W2015551990 hasConcept C88516994 @default.
- W2015551990 hasConcept C89600930 @default.
- W2015551990 hasConceptScore W2015551990C121332964 @default.
- W2015551990 hasConceptScore W2015551990C1276947 @default.
- W2015551990 hasConceptScore W2015551990C134306372 @default.
- W2015551990 hasConceptScore W2015551990C13662910 @default.
- W2015551990 hasConceptScore W2015551990C138885662 @default.
- W2015551990 hasConceptScore W2015551990C139676723 @default.
- W2015551990 hasConceptScore W2015551990C153180895 @default.
- W2015551990 hasConceptScore W2015551990C154945302 @default.
- W2015551990 hasConceptScore W2015551990C199360897 @default.
- W2015551990 hasConceptScore W2015551990C23224414 @default.
- W2015551990 hasConceptScore W2015551990C2777735758 @default.
- W2015551990 hasConceptScore W2015551990C28490314 @default.
- W2015551990 hasConceptScore W2015551990C33923547 @default.
- W2015551990 hasConceptScore W2015551990C41008148 @default.
- W2015551990 hasConceptScore W2015551990C41895202 @default.
- W2015551990 hasConceptScore W2015551990C522192633 @default.
- W2015551990 hasConceptScore W2015551990C60582962 @default.
- W2015551990 hasConceptScore W2015551990C88516994 @default.
- W2015551990 hasConceptScore W2015551990C89600930 @default.
- W2015551990 hasLocation W20155519901 @default.
- W2015551990 hasOpenAccess W2015551990 @default.
- W2015551990 hasPrimaryLocation W20155519901 @default.
- W2015551990 hasRelatedWork W1505908888 @default.
- W2015551990 hasRelatedWork W159541246 @default.
- W2015551990 hasRelatedWork W2034068554 @default.
- W2015551990 hasRelatedWork W2077204442 @default.
- W2015551990 hasRelatedWork W2109713757 @default.
- W2015551990 hasRelatedWork W2130658921 @default.
- W2015551990 hasRelatedWork W2140001811 @default.
- W2015551990 hasRelatedWork W2341398492 @default.
- W2015551990 hasRelatedWork W2533715784 @default.
- W2015551990 hasRelatedWork W2625129494 @default.
- W2015551990 isParatext "false" @default.
- W2015551990 isRetracted "false" @default.
- W2015551990 magId "2015551990" @default.
- W2015551990 workType "article" @default.