Gesture spotting and recognition using salience detection and concatenated hidden markov models
We developed a gesture salience based hand tracking method, and a gesture spotting and recognition method based on concatenated hidden Markov models. A 3-fold cross validation using the ChAirGest development data set with 10 users gives an F1 score of 0.907 and an accurate temporal segmentation rate...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
2014
|
| Online Access: | http://hdl.handle.net/1721.1/86128 https://orcid.org/0000-0001-5232-7281 |
| _version_ | 1826197672256602112 |
|---|---|
| author | Yin, Ying Davis, Randall |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Yin, Ying Davis, Randall |
| author_sort | Yin, Ying |
| collection | MIT |
| description | We developed a gesture salience based hand tracking method, and a gesture spotting and recognition method based on concatenated hidden Markov models. A 3-fold cross validation using the ChAirGest development data set with 10 users gives an F1 score of 0.907 and an accurate temporal segmentation rate (ATSR) of 0.923. The average final score is 0.9116. Compared with using the hand joint position from the Kinect SDK, using our hand tracking method gives a 3.7% absolute increase in the recognition F1 score. |
| first_indexed | 2024-09-23T10:51:22Z |
| format | Article |
| id | mit-1721.1/86128 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T10:51:22Z |
| publishDate | 2014 |
| record_format | dspace |
| spelling | mit-1721.1/861282022-09-27T15:29:02Z Gesture spotting and recognition using salience detection and concatenated hidden markov models Yin, Ying Davis, Randall Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Yin, Ying Davis, Randall We developed a gesture salience based hand tracking method, and a gesture spotting and recognition method based on concatenated hidden Markov models. A 3-fold cross validation using the ChAirGest development data set with 10 users gives an F1 score of 0.907 and an accurate temporal segmentation rate (ATSR) of 0.923. The average final score is 0.9116. Compared with using the hand joint position from the Kinect SDK, using our hand tracking method gives a 3.7% absolute increase in the recognition F1 score. 2014-04-11T19:22:35Z 2014-04-11T19:22:35Z 2013-12 Article http://purl.org/eprint/type/ConferencePaper 9781450321297 http://hdl.handle.net/1721.1/86128 Ying Yin and Randall Davis. 2013. Gesture spotting and recognition using salience detection and concatenated hidden markov models. In Proceedings of the 15th ACM on International conference on multimodal interaction (ICMI '13). ACM, New York, NY, USA, 489-494. https://orcid.org/0000-0001-5232-7281 en_US http://dx.doi.org/10.1145/2522848.2532588 Proceedings of the 15th ACM on International conference on multimodal interaction (ICMI '13) Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf MIT web domain |
| spellingShingle | Yin, Ying Davis, Randall Gesture spotting and recognition using salience detection and concatenated hidden markov models |
| title | Gesture spotting and recognition using salience detection and concatenated hidden markov models |
| title_full | Gesture spotting and recognition using salience detection and concatenated hidden markov models |
| title_fullStr | Gesture spotting and recognition using salience detection and concatenated hidden markov models |
| title_full_unstemmed | Gesture spotting and recognition using salience detection and concatenated hidden markov models |
| title_short | Gesture spotting and recognition using salience detection and concatenated hidden markov models |
| title_sort | gesture spotting and recognition using salience detection and concatenated hidden markov models |
| url | http://hdl.handle.net/1721.1/86128 https://orcid.org/0000-0001-5232-7281 |
| work_keys_str_mv | AT yinying gesturespottingandrecognitionusingsaliencedetectionandconcatenatedhiddenmarkovmodels AT davisrandall gesturespottingandrecognitionusingsaliencedetectionandconcatenatedhiddenmarkovmodels |