Probability‐based method for boosting human action recognition using scene context
In this study, the authors investigate the possibility of boosting action recognition performance by exploiting the associated scene context. Towards this end, the authors model a scene as a mid‐level ‘middle layer’ in order to bridge action descriptors and action categories. This is achieved via a...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2016-09-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2015.0420 |
| _version_ | 1797684927837241344 |
|---|---|
| author | Hong‐Bo Zhang Qing Lei Duan‐Sheng Chen Bi‐Neng Zhong Jialin Peng Ji‐Xiang Du Song‐Zhi Su |
| author_facet | Hong‐Bo Zhang Qing Lei Duan‐Sheng Chen Bi‐Neng Zhong Jialin Peng Ji‐Xiang Du Song‐Zhi Su |
| author_sort | Hong‐Bo Zhang |
| collection | DOAJ |
| description | In this study, the authors investigate the possibility of boosting action recognition performance by exploiting the associated scene context. Towards this end, the authors model a scene as a mid‐level ‘middle layer’ in order to bridge action descriptors and action categories. This is achieved via a scene topic model, in which hybrid visual descriptors, including spatial–temporal action features and scene descriptors, are first extracted from a video sequence. Then, the authors learn a joint probability distribution between scene and action using a naive Bayes nearest neighbour algorithm, which is adopted to jointly infer the action categories online by combining off‐the‐shelf action recognition algorithms. The authors demonstrate the advantages of their approach by comparing it with state‐of‐the‐art approaches using several action recognition benchmarks. |
| first_indexed | 2024-03-12T00:36:53Z |
| format | Article |
| id | doaj.art-1b12e7bad87e45bab8b071340ebc5d31 |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:36:53Z |
| publishDate | 2016-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-1b12e7bad87e45bab8b071340ebc5d312023-09-15T09:26:26ZengWileyIET Computer Vision1751-96321751-96402016-09-0110652853610.1049/iet-cvi.2015.0420Probability‐based method for boosting human action recognition using scene contextHong‐Bo Zhang0Qing Lei1Duan‐Sheng Chen2Bi‐Neng Zhong3Jialin Peng4Ji‐Xiang Du5Song‐Zhi Su6Department of Computer Science and TechnologyHuaqiao UniversityFujianPeople's Republic of ChinaDepartment of Computer Science and TechnologyHuaqiao UniversityFujianPeople's Republic of ChinaDepartment of Computer Science and TechnologyHuaqiao UniversityFujianPeople's Republic of ChinaDepartment of Computer Science and TechnologyHuaqiao UniversityFujianPeople's Republic of ChinaDepartment of Computer Science and TechnologyHuaqiao UniversityFujianPeople's Republic of ChinaDepartment of Computer Science and TechnologyHuaqiao UniversityFujianPeople's Republic of ChinaDepartment of Information Science and TechnologyXiamen UniversityFujianPeople's Republic of ChinaIn this study, the authors investigate the possibility of boosting action recognition performance by exploiting the associated scene context. Towards this end, the authors model a scene as a mid‐level ‘middle layer’ in order to bridge action descriptors and action categories. This is achieved via a scene topic model, in which hybrid visual descriptors, including spatial–temporal action features and scene descriptors, are first extracted from a video sequence. Then, the authors learn a joint probability distribution between scene and action using a naive Bayes nearest neighbour algorithm, which is adopted to jointly infer the action categories online by combining off‐the‐shelf action recognition algorithms. The authors demonstrate the advantages of their approach by comparing it with state‐of‐the‐art approaches using several action recognition benchmarks.https://doi.org/10.1049/iet-cvi.2015.0420probability based methodboosting human action recognitionassociated scene contextbridge action descriptorsaction categorieshybrid visual descriptors |
| spellingShingle | Hong‐Bo Zhang Qing Lei Duan‐Sheng Chen Bi‐Neng Zhong Jialin Peng Ji‐Xiang Du Song‐Zhi Su Probability‐based method for boosting human action recognition using scene context IET Computer Vision probability based method boosting human action recognition associated scene context bridge action descriptors action categories hybrid visual descriptors |
| title | Probability‐based method for boosting human action recognition using scene context |
| title_full | Probability‐based method for boosting human action recognition using scene context |
| title_fullStr | Probability‐based method for boosting human action recognition using scene context |
| title_full_unstemmed | Probability‐based method for boosting human action recognition using scene context |
| title_short | Probability‐based method for boosting human action recognition using scene context |
| title_sort | probability based method for boosting human action recognition using scene context |
| topic | probability based method boosting human action recognition associated scene context bridge action descriptors action categories hybrid visual descriptors |
| url | https://doi.org/10.1049/iet-cvi.2015.0420 |
| work_keys_str_mv | AT hongbozhang probabilitybasedmethodforboostinghumanactionrecognitionusingscenecontext AT qinglei probabilitybasedmethodforboostinghumanactionrecognitionusingscenecontext AT duanshengchen probabilitybasedmethodforboostinghumanactionrecognitionusingscenecontext AT binengzhong probabilitybasedmethodforboostinghumanactionrecognitionusingscenecontext AT jialinpeng probabilitybasedmethodforboostinghumanactionrecognitionusingscenecontext AT jixiangdu probabilitybasedmethodforboostinghumanactionrecognitionusingscenecontext AT songzhisu probabilitybasedmethodforboostinghumanactionrecognitionusingscenecontext |