{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T22:59:07Z","timestamp":1777157947774,"version":"3.51.4"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031733369","type":"print"},{"value":"9783031733376","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73337-6_21","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T23:02:27Z","timestamp":1730329347000},"page":"367-383","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["VP-SAM: Taming Segment Anything Model for\u00a0Video Polyp Segmentation via\u00a0Disentanglement and\u00a0Spatio-Temporal Side Network"],"prefix":"10.1007","author":[{"given":"Zhixue","family":"Fang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuzhi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huisi","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin","family":"Qin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"issue":"1","key":"21_CR1","doi-asserted-by":"publisher","first-page":"64","DOI":"10.5009\/gnl.2012.6.1.64","volume":"6","author":"SB Ahn","year":"2012","unstructured":"Ahn, S.B., Han, D.S., Bae, J.H., Byun, T.J., Kim, J.P., Eun, C.S.: The miss rate for colorectal adenoma determined by quality-adjusted, back-to-back colonoscopies. Gut Liver 6(1), 64 (2012)","journal-title":"Gut Liver"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Athar, A., Hermans, A., Luiten, J., Ramanan, D., Leibe, B.: TarViS: a unified approach for target-based video segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18738\u201318748 (2023)","DOI":"10.1109\/CVPR52729.2023.01797"},{"key":"21_CR3","doi-asserted-by":"crossref","unstructured":"Bernal, J., S\u00e1nchez, F.J., Fern\u00e1ndez-Esparrach, G., Gil, D., Rodr\u00edguez, C., Vilari\u00f1o, F.: WM-DOVA maps for accurate polyp highlighting in colonoscopy: validation vs. saliency maps from physicians. Comput. Med. Imaging Graph. 43, 99\u2013111 (2015)","DOI":"10.1016\/j.compmedimag.2015.02.007"},{"issue":"9","key":"21_CR4","doi-asserted-by":"publisher","first-page":"3166","DOI":"10.1016\/j.patcog.2012.03.002","volume":"45","author":"J Bernal","year":"2012","unstructured":"Bernal, J., S\u00e1nchez, J., Vilarino, F.: Towards automatic polyp detection with a polyp appearance model. Pattern Recogn. 45(9), 3166\u20133182 (2012)","journal-title":"Pattern Recogn."},{"issue":"6","key":"21_CR5","doi-asserted-by":"publisher","first-page":"366","DOI":"10.3322\/caac.20038","volume":"59","author":"MM Center","year":"2009","unstructured":"Center, M.M., Jemal, A., Smith, R.A., Ward, E.: Worldwide variations in colorectal cancer. CA Cancer J. Clin. 59(6), 366\u2013378 (2009)","journal-title":"CA Cancer J. Clin."},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Chen, C., et\u00a0al.: MA-SAM: modality-agnostic SAM adaptation for 3D medical image segmentation. arXiv preprint arXiv:2309.08842 (2023)","DOI":"10.1016\/j.media.2024.103310"},{"key":"21_CR7","unstructured":"Cheng, J., et\u00a0al.: SAM-Med2D. arXiv preprint arXiv:2308.16184 (2023)"},{"key":"21_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"720","DOI":"10.1007\/978-3-030-87193-2_68","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"M Cheng","year":"2021","unstructured":"Cheng, M., Kong, Z., Song, G., Tian, Y., Liang, Y., Chen, J.: Learnable oriented-derivative network for polyp segmentation. In: de Bruijne, M., et al. (eds.) MICCAI 2021, Part I 24. LNCS, vol. 12901, pp. 720\u2013730. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87193-2_68"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Dai, J., et al.: Deformable convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 764\u2013773 (2017)","DOI":"10.1109\/ICCV.2017.89"},{"key":"21_CR10","unstructured":"Dong, B., Wang, W., Fan, D.P., Li, J., Fu, H., Shao, L.: Polyp-PVT: polyp segmentation with pyramid vision transformers. arXiv preprint arXiv:2108.06932 (2021)"},{"key":"21_CR11","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"21_CR12","doi-asserted-by":"crossref","unstructured":"Fan, D.P., Ji, G.P., Sun, G., Cheng, M.M., Shen, J., Shao, L.: Camouflaged object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2777\u20132787 (2020)","DOI":"10.1109\/CVPR42600.2020.00285"},{"key":"21_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/978-3-030-32239-7_34","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019","author":"Y Fang","year":"2019","unstructured":"Fang, Y., Chen, C., Yuan, Y., Tong, K.: Selective feature aggregation network with area-boundary constraints for polyp segmentation. In: Shen, D., et al. (eds.) MICCAI 2019, Part I 22. LNCS, vol. 11764, pp. 302\u2013310. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32239-7_34"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Gong, S., et al.: 3DSAM-adapter: holistic adaptation of SAM from 2D to 3D for promptable medical image segmentation. arXiv preprint arXiv:2306.13465 (2023)","DOI":"10.1016\/j.media.2024.103324"},{"key":"21_CR15","doi-asserted-by":"publisher","first-page":"2763","DOI":"10.1109\/TMI.2023.3264513","volume":"42","author":"A He","year":"2023","unstructured":"He, A., Wang, K., Li, T., Du, C., Xia, S., Fu, H.: H2Former: an efficient hierarchical hybrid transformer for medical image segmentation. IEEE Trans. Med. Imaging 42, 2763\u20132775 (2023)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"21_CR16","unstructured":"He, S., Bao, R., Li, J., Grant, P.E., Ou, Y.: Accuracy of segment-anything model (SAM) in medical image segmentation tasks. arXiv preprint arXiv:2304.09324 (2023)"},{"key":"21_CR17","unstructured":"Huang, Y., et\u00a0al.: Segment anything model for medical images? arXiv preprint arXiv:2304.14660 (2023)"},{"issue":"3","key":"21_CR18","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1136\/gut.2003.029868","volume":"53","author":"D Hurlstone","year":"2004","unstructured":"Hurlstone, D., Cross, S., Slater, R., Sanders, D., Brown, S.: Detecting diminutive colorectal lesions at colonoscopy: a randomised controlled trial of pan-colonic versus targeted chromoscopy. Gut 53(3), 376\u2013380 (2004)","journal-title":"Gut"},{"key":"21_CR19","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":"21_CR20","doi-asserted-by":"crossref","unstructured":"Ji, G.P., Fan, D.P., Xu, P., Cheng, M.M., Zhou, B., Van\u00a0Gool, L.: Sam struggles in concealed scenes\u2013empirical study on \u201csegment anything\u201d. arXiv preprint arXiv:2304.06022 (2023)","DOI":"10.1007\/s11432-023-3881-x"},{"issue":"6","key":"21_CR21","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/s11633-022-1371-y","volume":"19","author":"GP Ji","year":"2022","unstructured":"Ji, G.P., et al.: Video polyp segmentation: a deep learning perspective. Mach. Intell. Res. 19(6), 531\u2013549 (2022)","journal-title":"Mach. Intell. Res."},{"key":"21_CR22","doi-asserted-by":"crossref","unstructured":"Ji, W., Li, J., Bi, Q., Li, W., Cheng, L.: Segment anything is not always perfect: an investigation of SAM on different real-world applications. arXiv preprint arXiv:2304.05750 (2023)","DOI":"10.1007\/s11633-024-1526-0"},{"key":"21_CR23","unstructured":"Kim, S., et\u00a0al.: MediViSTA-SAM: zero-shot medical video analysis with spatio-temporal SAM adaptation. arXiv preprint arXiv:2309.13539 (2023)"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Kim, T., Lee, H., Kim, D.: UACANet: uncertainty augmented context attention for polyp segmentation. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 2167\u20132175 (2021)","DOI":"10.1145\/3474085.3475375"},{"key":"21_CR25","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"21_CR26","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1109\/TIP.2021.3130490","volume":"31","author":"TN Le","year":"2021","unstructured":"Le, T.N., et al.: Camouflaged instance segmentation in-the-wild: dataset, method, and benchmark suite. IEEE Trans. Image Process. 31, 287\u2013300 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"21_CR27","doi-asserted-by":"publisher","unstructured":"Li, S., Sui, X., Luo, X., Xu, X., Liu, Y., Goh, R.: Medical image segmentation using squeeze-and-expansion transformers. In: Zhou, Z.H. (ed.) Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21, August 2021, pp. 807\u2013815. International Joint Conferences on Artificial Intelligence Organization (2021). https:\/\/doi.org\/10.24963\/ijcai.2021\/112, main Track","DOI":"10.24963\/ijcai.2021\/112"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Li, Y., Hu, M., Yang, X.: Polyp-SAM: transfer SAM for polyp segmentation. arXiv preprint arXiv:2305.00293 (2023)","DOI":"10.1117\/12.3006809"},{"key":"21_CR29","unstructured":"Lin, X., Xiang, Y., Zhang, L., Yang, X., Yan, Z., Yu, L.: SAMUS: adapting segment anything model for clinically-friendly and generalizable ultrasound image segmentation. arXiv preprint arXiv:2309.06824 (2023)"},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Luo, N., Pan, Y., Sun, R., Zhang, T., Xiong, Z., Wu, F.: Camouflaged instance segmentation via explicit de-camouflaging. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17918\u201317927 (2023)","DOI":"10.1109\/CVPR52729.2023.01718"},{"issue":"1","key":"21_CR31","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","volume":"15","author":"J Ma","year":"2024","unstructured":"Ma, J., He, Y., Li, F., Han, L., You, C., Wang, B.: Segment anything in medical images. Nat. Commun. 15(1), 654 (2024)","journal-title":"Nat. Commun."},{"key":"21_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1007\/978-3-030-87193-2_60","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"T-C Nguyen","year":"2021","unstructured":"Nguyen, T.-C., Nguyen, T.-P., Diep, G.-H., Tran-Dinh, A.-H., Nguyen, T.V., Tran, M.-T.: CCBANet: cascading context and balancing attention for polyp segmentation. In: de Bruijne, M., et al. (eds.) MICCAI 2021, Part I 24. LNCS, vol. 12901, pp. 633\u2013643. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87193-2_60"},{"key":"21_CR33","unstructured":"Pan, J., Lin, Z., Zhu, X., Shao, J., Li, H.: ST-adapter: parameter-efficient image-to-video transfer learning. In: Advances in Neural Information Processing Systems, vol. 35, pp. 26462\u201326477 (2022)"},{"key":"21_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1007\/978-3-030-59725-2_29","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","author":"JG-B Puyal","year":"2020","unstructured":"Puyal, J.G.-B., et al.: Endoscopic polyp segmentation using a hybrid 2D\/3D CNN. In: Martel, A.L., et al. (eds.) MICCAI 2020, Part VI 23. LNCS, vol. 12266, pp. 295\u2013305. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59725-2_29"},{"key":"21_CR35","unstructured":"Raghu, M., Unterthiner, T., Kornblith, S., Zhang, C., Dosovitskiy, A.: Do vision transformers see like convolutional neural networks? In: Advances in Neural Information Processing Systems, vol. 34, pp. 12116\u201312128 (2021)"},{"key":"21_CR36","unstructured":"Raji\u010d, F., Ke, L., Tai, Y.W., Tang, C.K., Danelljan, M., Yu, F.: Segment anything meets point tracking. arXiv preprint arXiv:2307.01197 (2023)"},{"key":"21_CR37","doi-asserted-by":"crossref","unstructured":"Su, J., Yin, R., Zhang, S., Luo, J.: Motion-state alignment for video semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3570\u20133579 (2023)","DOI":"10.1109\/CVPRW59228.2023.00365"},{"key":"21_CR38","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"21_CR39","doi-asserted-by":"publisher","first-page":"4117","DOI":"10.1109\/TASE.2023.3292373","volume":"21","author":"H Wu","year":"2023","unstructured":"Wu, H., Zhao, Z., Wang, Z.: META-Unet: multi-scale efficient transformer attention Unet for fast and high-accuracy polyp segmentation. IEEE Trans. Autom. Sci. Eng. 21, 4117\u20134128 (2023)","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"issue":"4","key":"21_CR40","doi-asserted-by":"publisher","first-page":"2610","DOI":"10.1109\/TCYB.2022.3162873","volume":"53","author":"H Wu","year":"2022","unstructured":"Wu, H., Zhao, Z., Zhong, J., Wang, W., Wen, Z., Qin, J.: PolypSeg+: a lightweight context-aware network for real-time polyp segmentation. IEEE Trans. Cybern. 53(4), 2610\u20132621 (2022)","journal-title":"IEEE Trans. Cybern."},{"key":"21_CR41","unstructured":"Wu, J., et al.: Medical SAM adapter: adapting segment anything model for medical image segmentation. arXiv preprint arXiv:2304.12620 (2023)"},{"key":"21_CR42","unstructured":"Yang, J., Gao, M., Li, Z., Gao, S., Wang, F., Zheng, F.: Track anything: segment anything meets videos. arXiv preprint arXiv:2304.11968 (2023)"},{"key":"21_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, K., Liu, D.: Customized segment anything model for medical image segmentation. arXiv preprint arXiv:2304.13785 (2023)","DOI":"10.2139\/ssrn.4495221"},{"key":"21_CR44","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Zhou, T., Wang, S., Liang, P., Zhang, Y., Chen, D.Z.: Input augmentation with SAM: boosting medical image segmentation with segmentation foundation model. In: Celebi, M.E., et al. (eds.) Medical Image Computing and Computer Assisted Intervention, MICCAI 2023 Workshops. LNCS, vol. 14393, pp. 129\u2013139. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-47401-9_13","DOI":"10.1007\/978-3-031-47401-9_13"},{"key":"21_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1007\/978-3-030-87193-2_2","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Liu, H., Hu, Q.: TransFuse: fusing transformers and CNNs for medical image segmentation. In: de Bruijne, M., et al. (eds.) MICCAI 2021, Part I 24. LNCS, vol. 12901, pp. 14\u201324. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87193-2_2"},{"key":"21_CR46","unstructured":"Zhou, T., Zhang, Y., Zhou, Y., Wu, Y., Gong, C.: Can SAM segment polyps? arXiv preprint arXiv:2304.07583 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73337-6_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T23:06:55Z","timestamp":1730329615000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73337-6_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031733369","9783031733376"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73337-6_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}