Spatiotemporal squeeze-and-excitation residual multiplier network for video action recognition
Aiming at the shortcomings of shallow networks and general deep models in two-stream network structure,which could not effectively learn spatial and temporal information,a squeeze-and-excitation residual network was proposed for action recognition with a spatial stream and a temporal stream.Meanwhil...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2019-10-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2019194/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841539382844063744 |
|---|---|
| author | Huilan LUO Kang TONG |
| author_facet | Huilan LUO Kang TONG |
| author_sort | Huilan LUO |
| collection | DOAJ |
| description | Aiming at the shortcomings of shallow networks and general deep models in two-stream network structure,which could not effectively learn spatial and temporal information,a squeeze-and-excitation residual network was proposed for action recognition with a spatial stream and a temporal stream.Meanwhile,the long-term temporal dependence was captured by injecting the identity mapping kernel into the network as a temporal filter.Spatiotemporal feature multiplication fusion was used to further enhance the interaction between spatial information and temporal information of squeeze-and-excitation residual networks.Simultaneously,the influence of spatial-temporal stream multiplication fusion methods,times and locations on the performance of action recognition was studied.Given the limitations of performance achieved by a single model,three different strategies were proposed to generate multiple models,and the final recognition result was obtained by integrating these models through averaging and weighted averaging.The experimental results on the HMDB51 and UCF101 datasets show that the proposed spatiotemporal squeeze-and-excitation residual multiplier networks can effectively improve the performance of action recognition. |
| format | Article |
| id | doaj-art-cbc0f45563c549109400839e81f96fa9 |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2019-10-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-cbc0f45563c549109400839e81f96fa92025-01-14T07:17:59ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2019-10-014018919859730530Spatiotemporal squeeze-and-excitation residual multiplier network for video action recognitionHuilan LUOKang TONGAiming at the shortcomings of shallow networks and general deep models in two-stream network structure,which could not effectively learn spatial and temporal information,a squeeze-and-excitation residual network was proposed for action recognition with a spatial stream and a temporal stream.Meanwhile,the long-term temporal dependence was captured by injecting the identity mapping kernel into the network as a temporal filter.Spatiotemporal feature multiplication fusion was used to further enhance the interaction between spatial information and temporal information of squeeze-and-excitation residual networks.Simultaneously,the influence of spatial-temporal stream multiplication fusion methods,times and locations on the performance of action recognition was studied.Given the limitations of performance achieved by a single model,three different strategies were proposed to generate multiple models,and the final recognition result was obtained by integrating these models through averaging and weighted averaging.The experimental results on the HMDB51 and UCF101 datasets show that the proposed spatiotemporal squeeze-and-excitation residual multiplier networks can effectively improve the performance of action recognition.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2019194/action recognitionspatiotemporal streamsqueeze-and-excitation residual networkmultiplication fusionmulti-model ensemble |
| spellingShingle | Huilan LUO Kang TONG Spatiotemporal squeeze-and-excitation residual multiplier network for video action recognition Tongxin xuebao action recognition spatiotemporal stream squeeze-and-excitation residual network multiplication fusion multi-model ensemble |
| title | Spatiotemporal squeeze-and-excitation residual multiplier network for video action recognition |
| title_full | Spatiotemporal squeeze-and-excitation residual multiplier network for video action recognition |
| title_fullStr | Spatiotemporal squeeze-and-excitation residual multiplier network for video action recognition |
| title_full_unstemmed | Spatiotemporal squeeze-and-excitation residual multiplier network for video action recognition |
| title_short | Spatiotemporal squeeze-and-excitation residual multiplier network for video action recognition |
| title_sort | spatiotemporal squeeze and excitation residual multiplier network for video action recognition |
| topic | action recognition spatiotemporal stream squeeze-and-excitation residual network multiplication fusion multi-model ensemble |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2019194/ |
| work_keys_str_mv | AT huilanluo spatiotemporalsqueezeandexcitationresidualmultipliernetworkforvideoactionrecognition AT kangtong spatiotemporalsqueezeandexcitationresidualmultipliernetworkforvideoactionrecognition |