{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T12:37:21Z","timestamp":1770467841091,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,17]],"date-time":"2023-10-17T00:00:00Z","timestamp":1697500800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515012894"],"award-info":[{"award-number":["2023A1515012894"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key R&D Project of Guangzhou Science and Technology Plan","award":["2023B01J0002"],"award-info":[{"award-number":["2023B01J0002"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,17]]},"DOI":"10.1145\/3627915.3627926","type":"proceedings-article","created":{"date-parts":[[2023,12,21]],"date-time":"2023-12-21T12:07:00Z","timestamp":1703160420000},"page":"1-5","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["A Novel Video Understanding Network Based on Poolformer and Transformer"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6632-1154","authenticated-orcid":false,"given":"Shiqiang","family":"Shu","sequence":"first","affiliation":[{"name":"School of Computer Science & Engineering, South China University of Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6295-7447","authenticated-orcid":false,"given":"Hewei","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science & Engineering, South China University of Technology, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8772-9299","authenticated-orcid":false,"given":"Jingxi","family":"Yu","sequence":"additional","affiliation":[{"name":"Ira A. Fulton Schools of Engineering, Arizona State University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,12,21]]},"reference":[{"key":"e_1_3_2_1_1_1","article-title":"Two-Stream Convolutional Networks for Hyperspectral Target Detection","author":"Zhu Dehui","year":"2021","unstructured":"Dehui Zhu, Bo Du, Liangpei Zhang (2021). Two-Stream Convolutional Networks for Hyperspectral Target Detection. IEEE Transactions on Geoscience and Remote Sensing, v 59, n 8, August 2021: 6907-6921.","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017","volume":"4733","author":"Jo\u00e3o Carreira","year":"2017","unstructured":"Carreira Jo\u00e3o, Zisserman Andrew, (2017). Quo Vadis, action recognition? A new model and the kinetics dataset. Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Volume 2017-January: 4724-4733."},{"key":"e_1_3_2_1_3_1","first-page":"5999","article-title":"Attention is all you need","author":"Ashish Vaswani","year":"2017","unstructured":"Vaswani Ashish, Shazeer Noam, Parmar Niki, (2017). Attention is all you need. Advances in Neural Information Processing Systems. 5999-6009.","journal-title":"Advances in Neural Information Processing Systems."},{"key":"e_1_3_2_1_4_1","volume-title":"Is space-time attention all you need for video understanding? arXiv preprint arXiv:2103.15691","author":"Gedas Bertasius","year":"2021","unstructured":"Bertasius Gedas, Wang Heng, Torresani Lorenzo, (2021). Is space-time attention all you need for video understanding? arXiv preprint arXiv:2103.15691."},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the IEEE International Conference on Computer Vision. 6816-6826","author":"Anurag Arnab","year":"2021","unstructured":"Arnab Anurag, Dehghani Mostafa, Heigold Georg, (2021). ViViT: A video vision transformer. Proceedings of the IEEE International Conference on Computer Vision. 6816-6826."},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 3192-3201","author":"Ze Liu","year":"2022","unstructured":"Liu Ze, Ning Jia, Cao Yue, (2022). Video Swin Transformer. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 3192-3201."},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 10809-10819","author":"Weihao Yu","year":"2022","unstructured":"Yu Weihao, Luo Mi, Zhou Pan, (2022). MetaFormer is Actually What You Need for Vision. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 10809-10819."},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 4694-4782","author":"Yue-Hei Ng Joe","year":"2015","unstructured":"Ng Joe Yue-Hei, Hausknecht Matthew, Vijayanarasimhan Sudheendra, (2015). Beyond short snippets: Deep networks for video classification. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 4694-4782."},{"key":"e_1_3_2_1_9_1","first-page":"4489","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","volume":"2015","author":"Du Tran","year":"2015","unstructured":"Tran Du, Bourdev Lubomir, Fergus Rob, (2015). Learning spatiotemporal features with 3D convolutional networks. Proceedings of the IEEE International Conference on Computer Vision, Volume 2015 International Conference on Computer Vision, ICCV 2015, 4489-4497."},{"key":"e_1_3_2_1_10_1","volume-title":"proceedings of the IEEE International Conference on Computer Vision, 5533\u20135541","author":"Qiu Z., Yao","year":"2017","unstructured":"Qiu Z., Yao T. and Mei T. (2017). Learning spatio-temporal representation with pseudo-3d residual networks. In proceedings of the IEEE International Conference on Computer Vision, 5533\u20135541."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 15979-15988","author":"Kaiming He","year":"2022","unstructured":"He Kaiming, Chen Xinlei, Xie Saining, (2022). Masked Autoencoders Are Scalable Vision Learners. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 15979-15988."},{"key":"e_1_3_2_1_14_1","volume-title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training. arXiv preprint arXiv: 2021:2103.15691","author":"Zhan Tong","year":"2021","unstructured":"Tong Zhan, Song Yibing, Wang Jue, (2021). VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training. arXiv preprint arXiv: 2021:2103.15691."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","first-page":"2740","DOI":"10.1109\/TPAMI.2018.2868668","article-title":"Temporal Segment Networks for Action Recognition in Videos","volume":"2019","author":"Limin Wang","year":"2019","unstructured":"Wang Limin, Xiong Yuanjun, Wang Zhe, (2019). Temporal Segment Networks for Action Recognition in Videos. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2019: 2740-2755.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence."},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the IEEE International Conference on Computer Vision, 6201-6210","author":"Christoph Feichtenhofer","year":"2019","unstructured":"Feichtenhofer Christoph, Fan Haoqi, Malik Jitendra, (2019). Slowfast networks for video recognition. Proceedings of the IEEE International Conference on Computer Vision, 6201-6210."},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the IEEE International Conference on Computer Vision. 618-626","author":"Ramprasaath Selvaraju","year":"2017","unstructured":"Selvaraju Ramprasaath, Cogswell Michael, Das Abhishek, (2017). Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. Proceedings of the IEEE International Conference on Computer Vision. 618-626."}],"event":{"name":"CSAE 2023: The 7th International Conference on Computer Science and Application Engineering","location":"Virtual Event China","acronym":"CSAE 2023"},"container-title":["Proceedings of the 7th International Conference on Computer Science and Application Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627915.3627926","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627915.3627926","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T21:47:04Z","timestamp":1755899224000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627915.3627926"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,17]]},"references-count":17,"alternative-id":["10.1145\/3627915.3627926","10.1145\/3627915"],"URL":"https:\/\/doi.org\/10.1145\/3627915.3627926","relation":{},"subject":[],"published":{"date-parts":[[2023,10,17]]},"assertion":[{"value":"2023-12-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}