{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,25]],"date-time":"2026-10-25T10:51:11Z","timestamp":1792925471507,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Establishment of Key Laboratory of Shenzhen Science and Technology Innovation Committee","award":["ZDSYS20190902093015527"],"award-info":[{"award-number":["ZDSYS20190902093015527"]}]},{"name":"Shenzhen Fundamental Research Fund","award":["JCYJ20210324132212030"],"award-info":[{"award-number":["JCYJ20210324132212030"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3548082","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T11:42:46Z","timestamp":1665402166000},"page":"521-530","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":28,"title":["Pixel-Level Anomaly Detection via Uncertainty-aware Prototypical Transformer"],"prefix":"10.1145","author":[{"given":"Chao","family":"Huang","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengliang","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen & Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihao","family":"Wu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Wen","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiuping","family":"Jiang","sequence":"additional","affiliation":[{"name":"Ningbo University, Ningbo, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Xu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen & Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2015.2434398"},{"key":"e_1_3_2_2_2_1","volume-title":"BEiT: BERT Pre-Training of Image Transformers. arXiv preprint arXiv:2106.08254","author":"Bao Hangbo","year":"2021","unstructured":"Hangbo Bao , Li Dong , and Furu Wei . 2021. BEiT: BERT Pre-Training of Image Transformers. arXiv preprint arXiv:2106.08254 ( 2021 ). Hangbo Bao, Li Dong, and Furu Wei. 2021. BEiT: BERT Pre-Training of Image Transformers. arXiv preprint arXiv:2106.08254 (2021)."},{"key":"e_1_3_2_2_3_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision. 4182--4191","author":"Bergmann P.","unstructured":"P. Bergmann , M. Fauser , D. Sattlegger , and C. Steger . 2020. Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings . In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 4182--4191 . P. Bergmann, M. Fauser, D. Sattlegger, and C. Steger. 2020. Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 4182--4191."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2015.02.007"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093610"},{"key":"e_1_3_2_2_6_1","volume-title":"Semantics Disentangling for Generalized Zero-Shot Learning. In IEEE\/CVF International Conference on Computer Vision (ICCV).","author":"Chen Zhi","year":"2021","unstructured":"Zhi Chen , Yadan Luo , Ruihong Qiu , Sen Wang , Zi Huang , Jingjing Li , and Zheng Zhang . 2021 a. Semantics Disentangling for Generalized Zero-Shot Learning. In IEEE\/CVF International Conference on Computer Vision (ICCV). Zhi Chen, Yadan Luo, Ruihong Qiu, Sen Wang, Zi Huang, Jingjing Li, and Zheng Zhang. 2021a. Semantics Disentangling for Generalized Zero-Shot Learning. In IEEE\/CVF International Conference on Computer Vision (ICCV)."},{"key":"e_1_3_2_2_7_1","volume-title":"Proceedings of the 28th ACM International Conference on Multimedia.","author":"Chen Zhi","year":"2021","unstructured":"Zhi Chen , Yadan Luo , Sen Wang , Ruihong Qiu , Jingjing Li , and Zi Huang . 2021 b. Mitigating Generation Shifts for Generalized Zero-Shot Learning . In Proceedings of the 28th ACM International Conference on Multimedia. Zhi Chen, Yadan Luo, Sen Wang, Ruihong Qiu, Jingjing Li, and Zi Huang. 2021b. Mitigating Generation Shifts for Generalized Zero-Shot Learning. In Proceedings of the 28th ACM International Conference on Multimedia."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413813"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01490-8"},{"key":"e_1_3_2_2_10_1","volume-title":"SSI","volume":"6","author":"Fan Deng-Ping","year":"2021","unstructured":"Deng-Ping Fan , Ge-Peng Ji , Xuebin Qin , and Ming-Ming Cheng . 2021 . Cognitive vision inspired object segmentation metric and loss function . SSI , Vol. 6 (2021). Deng-Ping Fan, Ge-Peng Ji, Xuebin Qin, and Ming-Ming Cheng. 2021. Cognitive vision inspired object segmentation metric and loss function. SSI, Vol. 6 (2021)."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59725-2_26"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32239-7_34"},{"key":"e_1_3_2_2_13_1","volume-title":"Masked autoencoders are scalable vision learners. arXiv preprint arXiv:2111.06377","author":"He Kaiming","year":"2021","unstructured":"Kaiming He , Xinlei Chen , Saining Xie , Yanghao Li , Piotr Doll\u00e1r , and Ross Girshick . 2021. Masked autoencoders are scalable vision learners. arXiv preprint arXiv:2111.06377 ( 2021 ). Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Doll\u00e1r, and Ross Girshick. 2021. Masked autoencoders are scalable vision learners. arXiv preprint arXiv:2111.06377 (2021)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3159538"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3122801"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3127716"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_32"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISM46123.2019.00049"},{"key":"e_1_3_2_2_20_1","volume-title":"Bayesian segnet: Model uncertainty in deep convolutional encoder-decoder architectures for scene understanding. arXiv preprint arXiv:1511.02680","author":"Kendall Alex","year":"2015","unstructured":"Alex Kendall , Vijay Badrinarayanan , and Roberto Cipolla . 2015. Bayesian segnet: Model uncertainty in deep convolutional encoder-decoder architectures for scene understanding. arXiv preprint arXiv:1511.02680 ( 2015 ). Alex Kendall, Vijay Badrinarayanan, and Roberto Cipolla. 2015. Bayesian segnet: Model uncertainty in deep convolutional encoder-decoder architectures for scene understanding. arXiv preprint arXiv:1511.02680 (2015)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475375"},{"key":"e_1_3_2_2_22_1","volume-title":"International Conference on Learning Representations.","author":"Kolesnikov Alexander","year":"2021","unstructured":"Alexander Kolesnikov , Alexey Dosovitskiy , Dirk Weissenborn , Georg Heigold , Jakob Uszkoreit , Lucas Beyer , Matthias Minderer , Mostafa Dehghani , Neil Houlsby , Sylvain Gelly , 2021 . An image is worth 16x16 words: Transformers for image recognition at scale . In International Conference on Learning Representations. Alexander Kolesnikov, Alexey Dosovitskiy, Dirk Weissenborn, Georg Heigold, Jakob Uszkoreit, Lucas Beyer, Matthias Minderer, Mostafa Dehghani, Neil Houlsby, Sylvain Gelly, et al. 2021. An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csda.2019.106816"},{"key":"e_1_3_2_2_24_1","volume-title":"Hierarchical clustering multi-task learning for joint human action grouping and recognition","author":"Liu An-An","year":"2016","unstructured":"An-An Liu , Yu-Ting Su , Wei-Zhi Nie , and Mohan Kankanhalli . 2016. Hierarchical clustering multi-task learning for joint human action grouping and recognition . IEEE transactions on pattern analysis and machine intelligence, Vol. 39 , 1 ( 2016 ), 102--114. An-An Liu, Yu-Ting Su, Wei-Zhi Nie, and Mohan Kankanhalli. 2016. Hierarchical clustering multi-task learning for joint human action grouping and recognition. IEEE transactions on pattern analysis and machine intelligence, Vol. 39, 1 (2016), 102--114."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3086066"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01517"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2014.2314959"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.39"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01438"},{"key":"e_1_3_2_2_30_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).  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_2_31_1","volume-title":"BDG-Net: Boundary Distribution Guided Network for Accurate Polyp Segmentation. arXiv preprint arXiv:2201.00767","author":"Qiu Zihuan","year":"2022","unstructured":"Zihuan Qiu , Zhichuan Wang , Miaomiao Zhang , Ziyong Xu , Jie Fan , and Linfeng Xu. 2022. BDG-Net: Boundary Distribution Guided Network for Accurate Polyp Segmentation. arXiv preprint arXiv:2201.00767 ( 2022 ). Zihuan Qiu, Zhichuan Wang, Miaomiao Zhang, Ziyong Xu, Jie Fan, and Linfeng Xu. 2022. BDG-Net: Boundary Distribution Guided Network for Accurate Polyp Segmentation. arXiv preprint arXiv:2201.00767 (2022)."},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00283"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-013-0926-3"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2015.2487997"},{"key":"e_1_3_2_2_36_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems. 5998--6008.  Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems. 5998--6008."},{"key":"e_1_3_2_2_37_1","volume-title":"A benchmark for endoluminal scene segmentation of colonoscopy images. Journal of Healthcare Engineering","author":"V\u00e1zquez David","year":"2017","unstructured":"David V\u00e1zquez , Jorge Bernal , F Javier S\u00e1nchez , Gloria Fern\u00e1ndez-Esparrach , Antonio M L\u00f3pez , Adriana Romero , Michal Drozdzal , and Aaron Courville . 2017. A benchmark for endoluminal scene segmentation of colonoscopy images. Journal of Healthcare Engineering ( 2017 ). David V\u00e1zquez, Jorge Bernal, F Javier S\u00e1nchez, Gloria Fern\u00e1ndez-Esparrach, Antonio M L\u00f3pez, Adriana Romero, Michal Drozdzal, and Aaron Courville. 2017. A benchmark for endoluminal scene segmentation of colonoscopy images. Journal of Healthcare Engineering (2017)."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00032"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00433"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00411"},{"key":"e_1_3_2_2_41_1","volume-title":"Duplex Contextual Relation Network for Polyp Segmentation. arXiv preprint arXiv:2103.06725","author":"Yin Zijin","year":"2021","unstructured":"Zijin Yin , Kongming Liang , Zhanyu Ma , and Jun Guo . 2021. Duplex Contextual Relation Network for Polyp Segmentation. arXiv preprint arXiv:2103.06725 ( 2021 ). Zijin Yin, Kongming Liang, Zhanyu Ma, and Jun Guo. 2021. Duplex Contextual Relation Network for Polyp Segmentation. arXiv preprint arXiv:2103.06725 (2021)."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3175092"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3073564"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59725-2_25"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3018790"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2018.2802944"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3144352"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00889-5_1"}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","location":"Lisboa Portugal","acronym":"MM '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548082","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3548082","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T15:00:18Z","timestamp":1750172418000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548082"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":49,"alternative-id":["10.1145\/3503161.3548082","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3548082","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}