{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:16:33Z","timestamp":1750220193172,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":26,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.61741216, 61402367"],"award-info":[{"award-number":["No.61741216, 61402367"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["No. 2018YFC08242- 04"],"award-info":[{"award-number":["No. 2018YFC08242- 04"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017620","name":"Shaanxi Science and Technology Co-ordination and Innovation Project of China","doi-asserted-by":"publisher","award":["No.2016KTTSGY01- 03"],"award-info":[{"award-number":["No.2016KTTSGY01- 03"]}],"id":[{"id":"10.13039\/501100017620","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,9,23]]},"DOI":"10.1145\/3573942.3574104","type":"proceedings-article","created":{"date-parts":[[2023,5,16]],"date-time":"2023-05-16T23:45:42Z","timestamp":1684280742000},"page":"846-851","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-instance learning anomaly event detection based on Transformer"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8279-4075","authenticated-orcid":false,"given":"Feifei","family":"Qin","sequence":"first","affiliation":[{"name":"School of Computer, 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":"School of Modern Posts, Xi'an University of Posts and Telecommunications, China and \rBig Data Industry Application Research Department, Shaanxi Provincial Information Engineering Research Institute, China"}]}],"member":"320","published-online":{"date-parts":[[2023,5,16]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"A World With a Billion Cameras Watching You Is Just Around the . Retrieved May 1 2022 from https:\/\/www.wsj.com\/articles\/a-billion-surveillance-cameras-forecast-to-be-watching-within-two-years-11575565402"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","unstructured":"Waqas Sultani Chen Chen and Mubarak Shah. 2018. Real-World Anomaly Detection in Surveillance Videos.\u00a02018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. DOI:https:\/\/doi.org\/10.1109\/cvpr.2018.00678","DOI":"10.1109\/cvpr.2018.00678"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","unstructured":"Alexey Dosovitskiy \u00a0Lucas Beyer \u00a0Alexander Kolesnikov \u00a0Dirk Weissenborn \u00a0Xiaohua Zhai \u00a0Thomas Unterthiner \u00a0Mostafa Dehghani \u00a0Matthias Minderer \u00a0Georg Heigold \u00a0Sylvain Gelly \u00a0Jakob Uszkoreit \u00a0Neil Houlsby. 2021. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv:2010.11929. Retrieved from https:\/\/doi.org\/10.48550\/arXiv.2010.11929","DOI":"10.48550\/arXiv.2010.11929"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","unstructured":"Joao Carreira and Andrew Zisserman. 2017. Quo Vadis Action Recognition? A New Model and the Kinetics Dataset.\u00a02017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). DOI:https:\/\/doi.org\/10.1109\/cvpr.2017.502","DOI":"10.1109\/cvpr.2017.502"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-021-02356-9"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.86"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-59081-3_23"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","unstructured":"Trong Nguyen Nguyen and Jean Meunier. 2019. Anomaly Detection in Video Sequence With Appearance-Motion Correspondence.\u00a02019 IEEE\/CVF International Conference on Computer Vision (ICCV). DOI:https:\/\/doi.org\/10.1109\/iccv.2019.00136","DOI":"10.1109\/iccv.2019.00136"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","unstructured":"Herman Prawiro Jian-Wei Peng Tse-Yu Pan and Min-Chun Hu. 2020. Abnormal Event Detection in Surveillance Videos Using Two-Stream Decoder.\u00a02020 IEEE International Conference on Multimedia & Expo Workshops (ICMEW). DOI:https:\/\/doi.org\/10.1109\/icmew46912.2020.9105987","DOI":"10.1109\/icmew46912.2020.9105987"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","unstructured":"Boyang Wan Yuming Fang Xue Xia and Jiajie Mei. 2020. Weakly Supervised Video Anomaly Detection via Center-Guided Discriminative Learning.\u00a02020 IEEE International Conference on Multimedia and Expo (ICME). DOI:https:\/\/doi.org\/10.1109\/icme46284.2020.9102722","DOI":"10.1109\/icme46284.2020.9102722"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","unstructured":"Xiao Jinsheng Shen Mengyao Jiang Mingjun Lei Junfeng Bao Zhenyu. 2021. Detection of abnormal behavior in surveillance video with packet attention mechanism. Journal of Automation: 1-10[2021-12-18]. https:\/\/doi.org\/10.16383\/j.aas.c190805","DOI":"10.16383\/j.aas.c190805"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","unstructured":"Shikha Dubey Abhijeet Boragule and Moongu Jeon. 2019. 3D ResNet with Ranking Loss Function for Abnormal Activity Detection in Videos.\u00a02019 International Conference on Control Automation and Information Sciences (ICCAIS). DOI:https:\/\/doi.org\/10.1109\/iccais46528.2019.9074586","DOI":"10.1109\/iccais46528.2019.9074586"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","unstructured":"Yu Tian Guansong Pang Yuanhong Chen Rajvinder Singh Johan W. Verjans and Gustavo Carneiro. 2021. Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learning.\u00a02021 IEEE\/CVF International Conference on Computer Vision (ICCV). DOI:https:\/\/doi.org\/10.1109\/iccv48922.2021.00493","DOI":"10.1109\/iccv48922.2021.00493"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","unstructured":"Zhenghua Zhang Zhangjie Gong and Qingqing Hong. 2021. A Survey on: Application of Transformer in Computer Vision.\u00a0The Proceedings of The 8th International Conference on Intelligent Systems and Image Processing 2021\u00a0(2021). DOI:https:\/\/doi.org\/10.12792\/icisip2021.006","DOI":"10.12792\/icisip2021.006"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00986"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","unstructured":"Will Kay \u00a0Joao Carreira \u00a0Karen Simonyan \u00a0Brian Zhang \u00a0Chloe Hillier \u00a0Sudheendra Vijayanarasimhan \u00a0Fabio Viola \u00a0Tim Green \u00a0Trevor Back \u00a0Paul Natsev \u00a0Mustafa Suleyman and Andrew Zisserman. 2017.The kinetics human action video dataset. arXiv.1705.06950. Retrieved from https:\/\/doi.org\/10.48550\/arXiv.1705.06950","DOI":"10.48550\/arXiv.1705.06950"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","unstructured":"Weichao Zhang Guanjun Wang Mengxing Huang Hongyu Wang and Shaoping Wen. 2021. Generative Adversarial Networks for Abnormal Event Detection in Videos Based on Self-Attention Mechanism.\u00a0IEEE Access 9 124847-124860. DOI:https:\/\/doi.org\/10.1109\/access.2021.3110798","DOI":"10.1109\/access.2021.3110798"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems(NIPS). Curran Associates Inc.","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of the 31st International Conference on Neural Information Processing Systems(NIPS). Curran Associates Inc., Red Hook, NY, USA, 6000\u20136010."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","unstructured":"Wen Liu Weixin Luo Dongze Lian and Shenghua Gao. 2018. Future Frame Prediction for Anomaly Detection - A New Baseline.\u00a02018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. DOI:https:\/\/doi.org\/10.1109\/cvpr.2018.00684","DOI":"10.1109\/cvpr.2018.00684"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","unstructured":"Jia-Xing Zhong Nannan Li Weijie Kong Shan Liu Thomas H. Li and Ge Li. 2019. Graph Convolutional Label Noise Cleaner: Train a Plug-And-Play Action Classifier for Anomaly Detection.\u00a02019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). DOI:https:\/\/doi.org\/10.1109\/cvpr.2019.00133","DOI":"10.1109\/cvpr.2019.00133"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","unstructured":"Jiangong Zhang Laiyun Qing and Jun Miao. 2019. Temporal Convolutional Network with Complementary Inner Bag Loss for Weakly Supervised Anomaly Detection.\u00a02019 IEEE International Conference on Image Processing (ICIP). DOI:https:\/\/doi.org\/10.1109\/icip.2019.8803657.","DOI":"10.1109\/icip.2019.8803657"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2007.01548"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","unstructured":"Peng Wu Jing Liu Yujia Shi Yujia Sun Fangtao Shao Zhaoyang Wu and Zhiwei Yang. 2020. Not only Look But Also Listen: Learning Multimodal Violence Detection Under Weak Supervision.\u00a0Computer Vision \u2013 ECCV 2020\u00a0(2020) 322-339. DOI:https:\/\/doi.org\/10.1007\/978-3-030-58577-8_20","DOI":"10.1007\/978-3-030-58577-8_20"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","unstructured":"Paul Michel \u00a0Omer Levy \u00a0and Graham Neubig. 2019. Are Sixteen Heads Really Better than One? arXiv:1905.10650 Retrieved from https:\/\/doi.org\/10.48550\/arXiv.1905.10650","DOI":"10.48550\/arXiv.1905.10650"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","unstructured":"Snehashis Majhi Srijan Das and Francois Bremond. 2021. DAM: Dissimilarity Attention Module for Weakly-supervised Video Anomaly Detection.\u00a02021 17th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). DOI:https:\/\/doi.org\/10.1109\/avss52988.2021.9663810","DOI":"10.1109\/avss52988.2021.9663810"}],"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\/3573942.3574104","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3573942.3574104","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:33Z","timestamp":1750186953000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3573942.3574104"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,23]]},"references-count":26,"alternative-id":["10.1145\/3573942.3574104","10.1145\/3573942"],"URL":"https:\/\/doi.org\/10.1145\/3573942.3574104","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"}}]}}