{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T18:54:59Z","timestamp":1770749699378,"version":"3.50.0"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,24]],"date-time":"2023-11-24T00:00:00Z","timestamp":1700784000000},"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":[[2023,11,24]]},"DOI":"10.1145\/3638682.3638691","type":"proceedings-article","created":{"date-parts":[[2024,5,22]],"date-time":"2024-05-22T15:32:08Z","timestamp":1716391928000},"page":"57-63","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A Video Classification Algorithm Based on Visual-Audio Cross-Attention"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9783-8410","authenticated-orcid":false,"given":"Xuchao","family":"Gong","sequence":"first","affiliation":[{"name":"Information Technology Service Center of Shengli Petroleum Management Bureau, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2555-3458","authenticated-orcid":false,"given":"Yahui","family":"Wu","sequence":"additional","affiliation":[{"name":"Sense Time group Inc., China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5376-8325","authenticated-orcid":false,"given":"Zhen","family":"Wang","sequence":"additional","affiliation":[{"name":"Information Technology Service Center of Shengli Petroleum Management Bureau, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2220-5808","authenticated-orcid":false,"given":"Hongjie","family":"Duan","sequence":"additional","affiliation":[{"name":"Information Technology Service Center of Shengli Petroleum Management Bureau, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,5,22]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Touvron H","unstructured":"Touvron H, Cord M, Douze M, Training data-efficient image transformers & distillation through attention[C]. International Conference on Machine Learning. PMLR, 2021: 10347-10357."},{"key":"e_1_3_2_1_2_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale[J]. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy A","year":"2020","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, An image is worth 16x16 words: Transformers for image recognition at scale[J]. arXiv preprint arXiv:2010.11929, 2020."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2021: 10012-10022","author":"Liu Z","unstructured":"Liu Z, Lin Y, Cao Y, Swin transformer: Hierarchical vision transformer using shifted windows[C]. Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2021: 10012-10022."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2021: 558-567","author":"Yuan L","unstructured":"Yuan L, Chen Y, Wang T, Tokens-to-token vit: Training vision transformers from scratch on imagenet[C]. Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2021: 558-567."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Arnab A Dehghani M Heigold G Vivit: A video vision transformer[C]. Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2021: 6836-6846.","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"e_1_3_2_1_6_1","volume-title":"Is space-time attention all you need for video understanding[J]. arXiv preprint arXiv:2102.05095","author":"Bertasius G","year":"2021","unstructured":"Bertasius G, Wang H, Torresani L. Is space-time attention all you need for video understanding[J]. arXiv preprint arXiv:2102.05095, 2021, 2(3): 1-4."},{"key":"e_1_3_2_1_7_1","volume-title":"Video swin transformer[J]. arXiv preprint arXiv:2106.13230","author":"Liu Z","year":"2021","unstructured":"Liu Z, Ning J, Cao Y, Video swin transformer[J]. arXiv preprint arXiv:2106.13230, 2021."},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the IEEE international conference on computer vision. 2015: 4489-4497","author":"Tran D","unstructured":"Tran D, Bourdev L, Fergus R, Learning spatiotemporal features with 3d convolutional networks[C]. Proceedings of the IEEE international conference on computer vision. 2015: 4489-4497."},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the IEEE International Conference on Computer Vision. 2017: 5533-5541","author":"Qiu Z","unstructured":"Qiu Z, Yao T, Mei T. Learning spatio-temporal representation with pseudo-3d residual networks[C]. Proceedings of the IEEE International Conference on Computer Vision. 2017: 5533-5541."},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the European conference on computer vision (ECCV). 2018: 305-321","author":"Xie S","unstructured":"Xie S, Sun C, Huang J, Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification[C]. Proceedings of the European conference on computer vision (ECCV). 2018: 305-321."},{"key":"e_1_3_2_1_11_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Kim W","unstructured":"Kim W, Son B, Kim I. Vilt: Vision-and-language transformer without convolution or region supervision[C]. International Conference on Machine Learning. PMLR, 2021: 5583-5594."},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017: 6299-6308","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."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 2018: 6450-6459","author":"Tran D","unstructured":"Tran D, Wang H, Torresani L, A closer look at spatiotemporal convolutions for action recognition[C]. Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 2018: 6450-6459."},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7794-7803","author":"Wang X","unstructured":"Wang X, Girshick R, Gupta A, Non-local neural networks[C]. Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7794-7803."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 1933-1941","author":"Feichtenhofer C","unstructured":"Feichtenhofer C, Pinz A, Zisserman A. Convolutional two-stream network fusion for video action recognition[C]. Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 1933-1941."},{"key":"e_1_3_2_1_17_1","first-page":"3163","volume":"2021","author":"Neimark D","unstructured":"Neimark D, Bar O, Zohar M, Video transformer network[C]\/\/Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2021: 3163-3172.","journal-title":"Computer Vision."},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2021: 6824-6835","author":"Fan H","unstructured":"Fan H, Xiong B, Mangalam K, Multiscale vision transformers[C]. Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2021: 6824-6835."},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7132-7141","author":"Hu J","unstructured":"Hu J, Shen L, Sun G. Squeeze-and-excitation networks[C]. Proceedings of the IEEE conference on computer vision and pattern recognition. 2018: 7132-7141."},{"key":"e_1_3_2_1_20_1","volume-title":"Iqbal T","author":"Kong Q","year":"2020","unstructured":"Kong Q, Cao Y, Iqbal T, Panns: Large-scale pretrained audio neural networks for audio pattern recognition[J]. IEEE\/ACM Transactions on Audio, Speech, and Language Processing, 2020, 28: 2880-2894."},{"key":"e_1_3_2_1_21_1","volume-title":"Rethinking CNN models for audio classification[J]. arXiv preprint arXiv:2007.11154","author":"Palanisamy K","year":"2020","unstructured":"Palanisamy K, Singhania D, Yao A. Rethinking CNN models for audio classification[J]. arXiv preprint arXiv:2007.11154, 2020."},{"key":"e_1_3_2_1_22_1","volume-title":"Lee K","author":"Devlin J","year":"1810","unstructured":"Devlin J, Chang M W, Lee K, Bert: Pre-training of deep bidirectional transformers for language understanding[J]. arXiv preprint arXiv:1810.04805, 2018."},{"key":"e_1_3_2_1_23_1","volume-title":"Qian R","author":"Akbari H","year":"2021","unstructured":"Akbari H, Yuan L, Qian R, Vatt: Transformers for multimodal self-supervised learning from raw video, audio and text[J]. Advances in Neural Information Processing Systems, 2021, 20-34."},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2019: 5552-5561","author":"Tran D","unstructured":"Tran D, Wang H, Torresani L, Video classification with channel-separated convolutional networks[C]. Proceedings of the IEEE\/CVF International Conference on Computer Vision. 2019: 5552-5561."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2021: 16020-16030","author":"Kondratyuk D","unstructured":"Kondratyuk D, Yuan L, Li Y, Movinets: Mobile video networks for efficient video recognition[C]. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2021: 16020-16030."},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2019: 12056-12065","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."},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision. 2019: 6202-6211","author":"Feichtenhofer C","unstructured":"Feichtenhofer C, Fan H, Malik J, Slowfast networks for video recognition[C]. Proceedings of the IEEE\/CVF international conference on computer vision. 2019: 6202-6211."},{"key":"e_1_3_2_1_28_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2020: 203-213","author":"Feichtenhofer C.","unstructured":"Feichtenhofer C. X3d: Expanding architectures for efficient video recognition[C]. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2020: 203-213."},{"key":"e_1_3_2_1_29_1","volume-title":"Neumann M","author":"Wang X","year":"2020","unstructured":"Wang X, Xiong X, Neumann M, Attentionnas: Spatiotemporal attention cell search for video classification[C]. European Conference on Computer Vision. Springer, Cham, 2020: 449-465."}],"event":{"name":"VSIP 2023: 2023 the 5th International Conference on Video, Signal and Image Processing","location":"Harbin China","acronym":"VSIP 2023"},"container-title":["Proceedings of the 2023 5th International Conference on Video, Signal and Image Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3638682.3638691","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3638682.3638691","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T02:00:35Z","timestamp":1755914435000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3638682.3638691"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,24]]},"references-count":29,"alternative-id":["10.1145\/3638682.3638691","10.1145\/3638682"],"URL":"https:\/\/doi.org\/10.1145\/3638682.3638691","relation":{},"subject":[],"published":{"date-parts":[[2023,11,24]]},"assertion":[{"value":"2024-05-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}