{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:16:31Z","timestamp":1750220191680,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,9,23]],"date-time":"2022-09-23T00:00:00Z","timestamp":1663891200000},"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":[[2022,9,23]]},"DOI":"10.1145\/3573942.3574077","type":"proceedings-article","created":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T23:45:42Z","timestamp":1684280742000},"page":"664-671","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A Dual-Task Deep Neural Network for Scene and Action Recognition Based on 3D SENet and 3D SEResNet"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5661-8200","authenticated-orcid":false,"given":"Zhouzhou","family":"Wei","sequence":"first","affiliation":[{"name":"Xi'an University of Posts and Telecommunications, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9516-1947","authenticated-orcid":false,"given":"Yuelei","family":"Xiao","sequence":"additional","affiliation":[{"name":"Xi'an University of Posts and Telecommunications, China and \rShaanxi Provincial Information Engineering Research Institute, China"}]}],"member":"320","published-online":{"date-parts":[[2023,5,16]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2019.2942739"},{"key":"e_1_3_2_1_2_1","unstructured":"Khurram Soomro Amir Roshan Zamir and Mubarak Shah.2012. UCF101: A Dataset of 101 Human Action Classes From Videos in The Wild. Retrieved Match 28 2022 from https:\/\/www.crcv.ucf.edu\/data\/UCF101.php."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2913372"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","unstructured":"H. Wang and C. Schmid.2013.Action Recognition with Improved Trajectories 2013 IEEE International Conference on Computer Vision Sydney NSW Australia (Dce.2013) 3551-3558. https:\/\/doi.org\/10.1109\/ICCV.2013.441","DOI":"10.1109\/ICCV.2013.441"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2911997"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/11744023_32"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2018.2791180"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2015.510"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1409.2329"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","unstructured":"Aude Oliva. 2005. Gist of the Scene.\u00a0Neurobiology of Attention 251-256.https:\/\/doi.org\/10.1016\/b978-012375731-9\/50045-8","DOI":"10.1016\/b978-012375731-9"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2010.224"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/iros.2018.8593736"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.2989863"},{"key":"e_1_3_2_1_21_1","volume-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Girdhar Rohit","year":"2022","unstructured":"Rohit Girdhar and Mannat Singh and Nikhila Ravi and Laurens van der Maaten and Armand Joulin and Ishan Misra. 2022.Omnivore: A Single Model for Many Visual Modalities. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. New Orleans, Louisiana.(June 2022), https:\/\/arxiv.org\/abs\/2201.08377"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.4400"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the 27th International Conference on International Conference on Machine Learning Omnipress","author":"Nair Vinod","year":"2010","unstructured":"Vinod Nair and Geoffrey E. Hinton. 2010. Rectified linear units improve restricted boltzmann machines. Proceedings of the 27th International Conference on International Conference on Machine Learning Omnipress, Madison, WI, USA.(June 2010), 807\u2013814. https:\/\/dl.acm.org\/doi\/10.5555\/3104322.3104425"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-59497-3_175"},{"key":"e_1_3_2_1_25_1","volume-title":"Dropout: a simple way to prevent neural networks from overfitting. (January","author":"Srivastava Nitish","year":"2014","unstructured":"Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. (January 2014), 1929\u20131958. https:\/\/dl.acm.org\/doi\/abs\/10.5555\/2627435.2670313"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","unstructured":"L\u00e9on Bottou. 2010. Large-Scale Machine Learning with Stochastic Gradient Descent.\u00a0Proceedings of COMPSTAT.(2010)177-186. https:\/\/doi.org\/10.1007\/978-3-7908-2604-3_16","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.243"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00675"},{"key":"e_1_3_2_1_29_1","unstructured":"Kay Will and Carreira Joao and Simonyan Karen and Zhang The Kinetics Human Action Video Dataset. Retrieved Match 28 2022 from https:\/\/www.deepmind.com\/open-source\/kinetics"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","unstructured":"Hilde Kuehne Hueihan Jhuang Rainer Stiefelhagen and Thomas Serre. 2012. HMDB51: A Large Video Database for Human MotionRecognition.\u00a0High Performance Computing in Science and Engineering \u201812 571-582. https:\/\/doi.org\/10.1007\/978-3-642-33374-3_41","DOI":"10.1007\/978-3-642-33374-3_41"}],"event":{"name":"AIPR 2022: 2022 5th International Conference on Artificial Intelligence and Pattern Recognition","acronym":"AIPR 2022","location":"Xiamen China"},"container-title":["Proceedings of the 2022 5th International Conference on Artificial Intelligence and Pattern Recognition"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3573942.3574077","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3573942.3574077","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:32Z","timestamp":1750186952000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3573942.3574077"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,23]]},"references-count":29,"alternative-id":["10.1145\/3573942.3574077","10.1145\/3573942"],"URL":"https:\/\/doi.org\/10.1145\/3573942.3574077","relation":{},"subject":[],"published":{"date-parts":[[2022,9,23]]},"assertion":[{"value":"2023-05-16","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}