{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:08:55Z","timestamp":1765343335550,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFB3305900"],"award-info":[{"award-number":["2022YFB3305900"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62394345, 62103151"],"award-info":[{"award-number":["62394345, 62103151"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["222202517006"],"award-info":[{"award-number":["222202517006"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"The Programme of Introducing Talents of Discipline to Universities (the 111 Project)","award":["B17017"],"award-info":[{"award-number":["B17017"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754742","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:55Z","timestamp":1761377215000},"page":"43-51","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Video Anomaly Detection via Scene-Dependent Memory Assisted Inter-Frame RGB Difference Reconstruction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-3946-9494","authenticated-orcid":false,"given":"Han","family":"Hu","sequence":"first","affiliation":[{"name":"East China University of Science and Technology, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2676-6341","authenticated-orcid":false,"given":"Wenli","family":"Du","sequence":"additional","affiliation":[{"name":"East China University of Science and Technology, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3863-9187","authenticated-orcid":false,"given":"Bing","family":"Wang","sequence":"additional","affiliation":[{"name":"East China University of Science and Technology, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548199"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01953"},{"key":"e_1_3_2_1_3_1","volume-title":"Scene-dependent prediction in latent space for video anomaly detection and anticipation","author":"Cao Congqi","year":"2024","unstructured":"Congqi Cao, Hanwen Zhang, Yue Lu, Peng Wang, and Yanning Zhang. 2024. Scene-dependent prediction in latent space for video anomaly detection and anticipation. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19898"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01734"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01379"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01255"},{"volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision. 1705-1714","author":"Gong Dong","key":"e_1_3_2_1_9_1","unstructured":"Dong Gong, Lingqiao Liu, Vuong Le, Budhaditya Saha, Moussa Reda Mansour, Svetha Venkatesh, and Anton van den Hengel. 2019. Memorizing normality to detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection. In Proceedings of the IEEE\/CVF international conference on computer vision. 1705-1714."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01780"},{"key":"e_1_3_2_1_11_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3325451"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00684"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01333"},{"key":"e_1_3_2_1_15_1","volume-title":"Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983","author":"Loshchilov Ilya","year":"2016","unstructured":"Ilya Loshchilov and Frank Hutter. 2016. Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)."},{"key":"e_1_3_2_1_16_1","volume-title":"International conference on learning representations.","author":"Lotter William","year":"2017","unstructured":"William Lotter, Gabriel Kreiman, and David Cox. 2017. Deep predictive coding networks for video prediction and unsupervised learning. In International conference on learning representations."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.338"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.45"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00775"},{"key":"e_1_3_2_1_20_1","volume-title":"Deep multi-scale video prediction beyond mean square error. arXiv preprint arXiv:1511.05440","author":"Mathieu Michael","year":"2015","unstructured":"Michael Mathieu, Camille Couprie, and Yann LeCun. 2015. Deep multi-scale video prediction beyond mean square error. arXiv preprint arXiv:1511.05440 (2015)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01438"},{"key":"e_1_3_2_1_22_1","unstructured":"Adam Paszke Sam Gross Soumith Chintala Gregory Chanan Edward Yang Zachary DeVito Zeming Lin Alban Desmaison Luca Antiga and Adam Lerer. 2017. Automatic differentiation in pytorch. (2017)."},{"key":"e_1_3_2_1_23_1","volume-title":"Predictive coding in the visual cortex: a functional interpretation of some extra-classical receptive-field effects. Nature neuroscience","author":"Rao Rajesh PN","year":"1999","unstructured":"Rajesh PN Rao and Dana H Ballard. 1999. Predictive coding in the visual cortex: a functional interpretation of some extra-classical receptive-field effects. Nature neuroscience, Vol. 2, 1 (1999), 79-87."},{"key":"e_1_3_2_1_24_1","volume-title":"Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767","author":"Redmon Joseph","year":"2018","unstructured":"Joseph Redmon and Ali Farhadi. 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01513"},{"key":"e_1_3_2_1_26_1","first-page":"234","volume-title":"Munich","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention-MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18. Springer, 234-241."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00948"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413887"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25334"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02188"},{"key":"e_1_3_2_1_31_1","volume-title":"International conference on machine learning. PMLR, 6105-6114","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning. PMLR, 6105-6114."},{"key":"e_1_3_2_1_32_1","volume-title":"Image quality assessment: from error visibility to structural similarity","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, Vol. 13, 4 (2004), 600-612."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413529"},{"key":"e_1_3_2_1_34_1","volume-title":"International conference on learning representations.","author":"Weston Jason","year":"2015","unstructured":"Jason Weston, Sumit Chopra, and Antoine Bordes. 2015. Memory networks. In International conference on learning representations."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00509"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01402"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350899"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01561"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3531772"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01646"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_1"},{"key":"e_1_3_2_1_42_1","volume-title":"Fairmot: On the fairness of detection and re-identification in multiple object tracking. International journal of computer vision","author":"Zhang Yifu","year":"2021","unstructured":"Yifu Zhang, Chunyu Wang, Xinggang Wang, Wenjun Zeng, and Wenyu Liu. 2021. Fairmot: On the fairness of detection and re-identification in multiple object tracking. International journal of computer vision, Vol. 129 (2021), 3069-3087."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754742","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T05:03:55Z","timestamp":1765343035000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754742"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":42,"alternative-id":["10.1145\/3746027.3754742","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754742","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}