{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:17:34Z","timestamp":1750220254196,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,1,15]],"date-time":"2022-01-15T00:00:00Z","timestamp":1642204800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,1,15]]},"DOI":"10.1145\/3523150.3523167","type":"proceedings-article","created":{"date-parts":[[2022,4,13]],"date-time":"2022-04-13T21:39:55Z","timestamp":1649885995000},"page":"105-110","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Action Recognition Based on Person-Object Relationship Spatio-Temporal Graph"],"prefix":"10.1145","author":[{"given":"Tianxiao","family":"Wang","sequence":"first","affiliation":[{"name":"Wuhan University Science and Technology, China"}]},{"given":"Jun","family":"Liu","sequence":"additional","affiliation":[{"name":"Wuhan University Science and Technology, China"}]}],"member":"320","published-online":{"date-parts":[[2022,4,13]]},"reference":[{"key":"e_1_3_2_1_1_1","article-title":"A review of action recognition based on Convolutional Neural Network[J].","volume":"2021","author":"Jiaxin Yang","year":"1827","unstructured":"Jiaxin Yang , Fang Wang, Jieru Yang . A review of action recognition based on Convolutional Neural Network[J]. Journal of Physics: Conference Series , 2021 , 1827 (1). Jiaxin Yang, Fang Wang,Jieru Yang. A review of action recognition based on Convolutional Neural Network[J].Journal of Physics: Conference Series,2021,1827(1).","journal-title":"Journal of Physics: Conference Series"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2014.04.011"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2010.10.002"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Tran D Bourdev L Fergus R Learning spatio-temporal features with 3d convolutional networks[C]:Proceedings of the IEEE international conference on computer vision. 2015: 4489-4497.  Tran D Bourdev L Fergus R Learning spatio-temporal features with 3d convolutional networks[C]:Proceedings of the IEEE international conference on computer vision. 2015: 4489-4497.","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Hara K Kataoka H Satoh Y. Can spatiotemporal 3d cnns retrace the history of 2d cnns and imagenet[C]:Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 2018: 6546-6555.  Hara K Kataoka H Satoh Y. Can spatiotemporal 3d cnns retrace the history of 2d cnns and imagenet[C]:Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 2018: 6546-6555.","DOI":"10.1109\/CVPR.2018.00685"},{"key":"e_1_3_2_1_6_1","first-page":"6299","article-title":"Quo vadis, action recognition a new model and the kinetics dataset[C]","volume":"2017","author":"Carreira J","unstructured":"Carreira J , Zisserman A . Quo vadis, action recognition a new model and the kinetics dataset[C] : Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017 : 6299 - 6308 . Carreira J, Zisserman A. Quo vadis, action recognition a new model and the kinetics dataset[C]:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017: 6299-6308.","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_7_1","volume-title":"Two-stream convolutional networks for action recognition in videos[J]. arXiv preprint arXiv:1406.2199","author":"Simonyan K","year":"2014","unstructured":"Simonyan K , Zisserman A. Two-stream convolutional networks for action recognition in videos[J]. arXiv preprint arXiv:1406.2199 , 2014 . Simonyan K, Zisserman A. Two-stream convolutional networks for action recognition in videos[J]. arXiv preprint arXiv:1406.2199, 2014."},{"key":"e_1_3_2_1_8_1","volume-title":"Temporal segment networks: Towards good practices for deep action Recognition [C]. European conference on computer vision","author":"Wang L","year":"2016","unstructured":"Wang L , Xiong Y , Wang Z , Temporal segment networks: Towards good practices for deep action Recognition [C]. European conference on computer vision . Springer , Cham , 2016 : 20-36. Wang L, Xiong Y, Wang Z, Temporal segment networks: Towards good practices for deep action Recognition [C]. European conference on computer vision. Springer, Cham, 2016: 20-36."},{"volume-title":"2018 25th IEEE International Conference on Image Processing (ICIP). IEEE","author":"Song L","key":"e_1_3_2_1_9_1","unstructured":"Song L , Weng L , Wang L , Two -stream designed 2d 3d residual networks with lstms for action recognition in videos[C] . 2018 25th IEEE International Conference on Image Processing (ICIP). IEEE , 2018: 808-812. Song L, Weng L, Wang L, Two-stream designed 2d 3d residual networks with lstms for action recognition in videos[C]. 2018 25th IEEE International Conference on Image Processing (ICIP). IEEE, 2018: 808-812."},{"key":"e_1_3_2_1_10_1","volume-title":"Semi-supervised classification with graph convolutional networks[J]. arXiv preprint arXiv: 1609.02907","author":"Kipf T N","year":"2016","unstructured":"Kipf T N , Welling M. Semi-supervised classification with graph convolutional networks[J]. arXiv preprint arXiv: 1609.02907 , 2016 . Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks[J]. arXiv preprint arXiv: 1609.02907, 2016."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Wang X Gupta A. Videos as space-time region graphs[C] Proceedings of the European conference on computer vision (ECCV). 2018: 399-417.  Wang X Gupta A. Videos as space-time region graphs[C] Proceedings of the European conference on computer vision (ECCV). 2018: 399-417.","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"e_1_3_2_1_12_1","first-page":"10424","article-title":"Video relationship reasoning using gated spatio-temporal energy graph[C]","volume":"2019","author":"Tsai Y H H","unstructured":"Tsai Y H H , Divvala S , Morency L P , Video relationship reasoning using gated spatio-temporal energy graph[C] : Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2019 : 10424 - 10433 . Tsai Y H H, Divvala S, Morency L P, Video relationship reasoning using gated spatio-temporal energy graph[C]: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2019: 10424-10433.","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_13_1","volume-title":"Faster rcnn: Towards real-time object detection with region proposal networks[J]. Advances in neural information processing systems","author":"Ren S","year":"2015","unstructured":"Ren S , He K , Girshick R , Faster rcnn: Towards real-time object detection with region proposal networks[J]. Advances in neural information processing systems , 2015 , 28: 91-99. Ren S, He K, Girshick R, Faster rcnn: Towards real-time object detection with region proposal networks[J]. Advances in neural information processing systems, 2015, 28: 91-99."},{"key":"e_1_3_2_1_14_1","volume-title":"Yolov3: An incremental improvement[J]. arXiv preprint arXiv:1804.02767","author":"Redmon J","year":"2018","unstructured":"Redmon J , Farhadi A. Yolov3: An incremental improvement[J]. arXiv preprint arXiv:1804.02767 , 2018 . Redmon J, Farhadi A. Yolov3: An incremental improvement[J]. arXiv preprint arXiv:1804.02767, 2018."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Ilg E Mayer N Saikia T Flownet 2.0: Evolution of optical flow estimation with deep networks[C]:Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 2462-2470.  Ilg E Mayer N Saikia T Flownet 2.0: Evolution of optical flow estimation with deep networks[C]:Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 2462-2470.","DOI":"10.1109\/CVPR.2017.179"},{"volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 2015:  4694-4702","author":"Yue-Hei Ng J","key":"e_1_3_2_1_16_1","unstructured":"Yue-Hei Ng J , Hausknecht M , Vijayanarasimhan S , Beyond short snippets: Deep networks for video classification[C] . Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 4694-4702 . Yue-Hei Ng J, Hausknecht M, Vijayanarasimhan S, Beyond short snippets: Deep networks for video classification[C]. Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 4694-4702."},{"key":"e_1_3_2_1_17_1","volume-title":"International journal of computer vision","author":"Shi Q","year":"2011","unstructured":"Shi Q , Cheng L , Wang L , Human action segmentation and recognition using discriminative semimarkov models[J] . International journal of computer vision , 2011 , 93(1): 22-32. Shi Q, Cheng L, Wang L, Human action segmentation and recognition using discriminative semimarkov models[J]. International journal of computer vision, 2011, 93(1): 22-32."},{"key":"e_1_3_2_1_18_1","volume-title":"A dataset of 101 human action classes from videos in the wild[J]","author":"Soomro K","year":"2012","unstructured":"Soomro K , Zamir A R , Shah M. A dataset of 101 human action classes from videos in the wild[J] . Center for Research in Computer Vision, 2012 , 2(11). Soomro K, Zamir A R, Shah M. A dataset of 101 human action classes from videos in the wild[J]. Center for Research in Computer Vision, 2012, 2(11)."},{"issue":"5","key":"e_1_3_2_1_19_1","first-page":"6","article-title":"A large video database for human motion recognition[C]","volume":"4","author":"Jhuang H","year":"2011","unstructured":"Jhuang H , Garrote H , Poggio E , A large video database for human motion recognition[C] . Proc. of IEEE International Conference on Computer Vision . 2011 , 4 ( 5 ): 6 . Jhuang H, Garrote H, Poggio E, A large video database for human motion recognition[C]. Proc. of IEEE International Conference on Computer Vision. 2011, 4(5): 6.","journal-title":"Proc. of IEEE International Conference on Computer Vision"},{"key":"e_1_3_2_1_20_1","first-page":"6016","article-title":"End-to-end learning of motion representation for video understanding[C]","volume":"2018","author":"Fan L","unstructured":"Fan L , Huang W , Gan C , End-to-end learning of motion representation for video understanding[C] : Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018 : 6016 - 6025 . Fan L, Huang W, Gan C, End-to-end learning of motion representation for video understanding[C]:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 6016-6025.","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_21_1","volume-title":"Gan W","author":"Jiang B","year":"2019","unstructured":"Jiang B , Wang M M , Gan W , Stm : Spatio-temporal and motion encoding for action recognition[C]:Proceedings of the IEEE\/CVF International Conference on Computer Vision . 2019 : 2000-2009. Jiang B, Wang M M, Gan W, Stm: Spatio-temporal and motion encoding for action recognition[C]:Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2019: 2000-2009."},{"key":"e_1_3_2_1_22_1","first-page":"12056","article-title":"Learning spatio-temporal representation with local and global diffusion[C]","volume":"2019","author":"Qiu Z","unstructured":"Qiu Z , Yao T , Ngo C W , Learning spatio-temporal representation with local and global diffusion[C] : Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2019 : 12056 - 12065 . Qiu Z, Yao T, Ngo C W, Learning spatio-temporal representation with local and global diffusion[C]:Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2019: 12056-12065.","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition."}],"event":{"name":"ICMLSC 2022: 2022 The 6th International Conference on Machine Learning and Soft Computing","acronym":"ICMLSC 2022","location":"Haikou China"},"container-title":["2022 The 6th International Conference on Machine Learning and Soft Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3523150.3523167","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3523150.3523167","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:44Z","timestamp":1750188644000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3523150.3523167"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,15]]},"references-count":22,"alternative-id":["10.1145\/3523150.3523167","10.1145\/3523150"],"URL":"https:\/\/doi.org\/10.1145\/3523150.3523167","relation":{},"subject":[],"published":{"date-parts":[[2022,1,15]]},"assertion":[{"value":"2022-04-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}