{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T20:24:37Z","timestamp":1774556677190,"version":"3.50.1"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031164361","type":"print"},{"value":"9783031164378","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-16437-8_9","type":"book-chapter","created":{"date-parts":[[2022,9,15]],"date-time":"2022-09-15T18:13:04Z","timestamp":1663265584000},"page":"88-98","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["Contrastive Transformer-Based Multiple Instance Learning for\u00a0Weakly Supervised Polyp Frame Detection"],"prefix":"10.1007","author":[{"given":"Yu","family":"Tian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guansong","family":"Pang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fengbei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuyuan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanhong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johan","family":"Verjans","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gustavo","family":"Carneiro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,9,16]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: ViViT: a video vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"issue":"1","key":"9_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-020-00622-y","volume":"7","author":"H Borgli","year":"2020","unstructured":"Borgli, H., et al.: HyperKvasir, a comprehensive multi-class image and video dataset for gastrointestinal endoscopy. Sci. Data 7(1), 1\u201314 (2020)","journal-title":"Sci. Data"},{"key":"9_CR3","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., Tian, Y., Pang, G., Carneiro, G.: Deep one-class classification via interpolated gaussian descriptor. arXiv preprint arXiv:2101.10043 (2021)","DOI":"10.1609\/aaai.v36i1.19915"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1251\u20131258 (2017)","DOI":"10.1109\/CVPR.2017.195"},{"key":"9_CR6","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Feng, J.C., Hong, F.T., Zheng, W.S.: MIST: multiple instance self-training framework for video anomaly detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14009\u201314018 (2021)","DOI":"10.1109\/CVPR46437.2021.01379"},{"key":"9_CR8","doi-asserted-by":"crossref","unstructured":"Gong, D., et al.: Memorizing normality to detect anomaly: memory-augmented deep autoencoder for unsupervised anomaly detection. In: ICCV, pp. 1705\u20131714 (2019)","DOI":"10.1109\/ICCV.2019.00179"},{"key":"9_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1007\/978-3-030-87193-2_14","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"G-P Ji","year":"2021","unstructured":"Ji, G.-P., et al.: Progressively normalized self-attention network for video polyp segmentation. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12901, pp. 142\u2013152. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87193-2_14"},{"key":"9_CR10","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"9_CR11","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Li, S., Liu, F., Jiao, L.: Self-training multi-sequence learning with transformer for weakly supervised video anomaly detection. In: Proceedings of the AAAI, Virtual 24 (2022)","DOI":"10.1609\/aaai.v36i2.20028"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Li, W., Vasconcelos, N.: Multiple instance learning for soft bags via top instances. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4277\u20134285 (2015)","DOI":"10.1109\/CVPR.2015.7299056"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: Photoshopping colonoscopy video frames. In: ISBI, pp. 1\u20135 (2020)","DOI":"10.1109\/ISBI45749.2020.9098406"},{"key":"9_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/978-3-030-87240-3_37","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"Y Ma","year":"2021","unstructured":"Ma, Y., Chen, X., Cheng, K., Li, Y., Sun, B.: LDPolypVideo benchmark: a large-scale colonoscopy video dataset of diverse polyps. In: de Bruijne, M. (ed.) MICCAI 2021. LNCS, vol. 12905, pp. 387\u2013396. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87240-3_37"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Pang, G., van den Hengel, A., Shen, C., Cao, L.: Toward deep supervised anomaly detection: reinforcement learning from partially labeled anomaly data. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 1298\u20131308 (2021)","DOI":"10.1145\/3447548.3467417"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Pang, G., Shen, C., van den Hengel, A.: Deep anomaly detection with deviation networks. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 353\u2013362 (2019)","DOI":"10.1145\/3292500.3330871"},{"key":"9_CR18","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Wallach, H., Larochelle, H., Beygelzimer, A., d Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems 32, pp. 8024\u20138035. Curran Associates, Inc. (2019). http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf"},{"issue":"4","key":"9_CR19","doi-asserted-by":"publisher","first-page":"891","DOI":"10.1016\/j.gie.2020.02.042","volume":"92","author":"LZCT Pu","year":"2020","unstructured":"Pu, L.Z.C.T., et al.: Computer-aided diagnosis for characterisation of colorectal lesions: a comprehensive software including serrated lesions. Gastrointest. Endosc. 92(4), 891\u2013899 (2020)","journal-title":"Gastrointest. Endosc."},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Sultani, W., Chen, C., Shah, M.: Real-world anomaly detection in surveillance videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6479\u20136488 (2018)","DOI":"10.1109\/CVPR.2018.00678"},{"key":"9_CR21","unstructured":"Tian, Y., Liu, F., et al.: Self-supervised multi-class pre-training for unsupervised anomaly detection and segmentation in medical images. arXiv preprint arXiv:2109.01303 (2021)"},{"key":"9_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1007\/978-3-030-59725-2_27","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","author":"Yu Tian","year":"2020","unstructured":"Tian, Yu., Maicas, G., Pu, L.Z.C.T., Singh, R., Verjans, J.W., Carneiro, G.: Few-shot anomaly detection for polyp frames from colonoscopy. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12266, pp. 274\u2013284. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59725-2_27"},{"key":"9_CR23","unstructured":"Tian, Y., et al.: Detecting, localising and classifying polyps from colonoscopy videos using deep learning. arXiv preprint arXiv:2101.03285 (2021)"},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Tian, Y., Pang, G., Chen, Y., Singh, R., Verjans, J.W., Carneiro, G.: Weakly-supervised video anomaly detection with robust temporal feature magnitude learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4975\u20134986 (2021)","DOI":"10.1109\/ICCV48922.2021.00493"},{"key":"9_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1007\/978-3-030-87240-3_13","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"Yu Tian","year":"2021","unstructured":"Tian, Yu., et al.: Constrained contrastive distribution learning for unsupervised anomaly detection and localisation in medical images. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12905, pp. 128\u2013140. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87240-3_13"},{"key":"9_CR26","doi-asserted-by":"crossref","unstructured":"Tian, Y., et al.: One-stage five-class polyp detection and classification. In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), pp. 70\u201373. IEEE (2019)","DOI":"10.1109\/ISBI.2019.8759521"},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Wan, B., Fang, Y., Xia, X., Mei, J.: Weakly supervised video anomaly detection via center-guided discriminative learning. In: 2020 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136 (2020)","DOI":"10.1109\/ICME46284.2020.9102722"},{"key":"9_CR28","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: CvT: introducing convolutions to vision transformers. arXiv preprint arXiv:2103.15808 (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"9_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1007\/978-3-030-58577-8_20","volume-title":"Computer Vision \u2013 ECCV 2020","author":"P Wu","year":"2020","unstructured":"Wu, P., et al.: Not only look, but also listen: learning multimodal violence detection under weak supervision. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 322\u2013339. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_20"},{"key":"9_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1007\/978-3-030-58542-6_22","volume-title":"Computer Vision \u2013 ECCV 2020","author":"MZ Zaheer","year":"2020","unstructured":"Zaheer, M.Z., Mahmood, A., Astrid, M., Lee, S.-I.: CLAWS: clustering assisted weakly supervised learning with normalcy suppression for anomalous event detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12367, pp. 358\u2013376. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58542-6_22"},{"key":"9_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, C., Cao, M., Yang, D., Chen, J., Zou, Y.: Cola: weakly-supervised temporal action localization with snippet contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16010\u201316019 (2021)","DOI":"10.1109\/CVPR46437.2021.01575"},{"key":"9_CR32","doi-asserted-by":"crossref","unstructured":"Zhong, J.X., Li, N., Kong, W., Liu, S., Li, T.H., Li, G.: Graph convolutional label noise cleaner: train a plug-and-play action classifier for anomaly detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1237\u20131246 (2019)","DOI":"10.1109\/CVPR.2019.00133"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-16437-8_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T14:02:50Z","timestamp":1710252170000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-16437-8_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031164361","9783031164378"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-16437-8_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"16 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft Conference","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1831","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"574","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"31% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}