{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T12:15:11Z","timestamp":1767183311077,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":50,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819609000"},{"type":"electronic","value":"9789819609017"}],"license":[{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"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\/978-981-96-0901-7_11","type":"book-chapter","created":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T07:56:02Z","timestamp":1733558162000},"page":"174-190","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Polyp-SES: Automatic Polyp Segmentation with\u00a0Self-enriched Semantic Model"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3838-4428","authenticated-orcid":false,"given":"Quang Vinh","family":"Nguyen","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3278-727X","authenticated-orcid":false,"given":"Thanh Hoang Son","family":"Vo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0172-5508","authenticated-orcid":false,"given":"Sae-Ryung","family":"Kang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3575-5035","authenticated-orcid":false,"given":"Soo-Hyung","family":"Kim","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,8]]},"reference":[{"key":"11_CR1","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. CMIG 43, 99\u2013111 (2015)","DOI":"10.1016\/j.compmedimag.2015.02.007"},{"key":"11_CR2","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., Hu, H.: Gcnet: Non-local networks meet squeeze-excitation networks and beyond. In: ICCVW. pp.\u00a00\u20130 (2019)","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"11_CR3","unstructured":"Chen, J., Lu, Y., Yu, Q., Luo, X., Adeli, E., Wang, Y., Lu, L., Yuille, A.L., Zhou, Y.: Transunet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306 (2021)"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. pp. 248\u2013255. Ieee (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"11_CR5","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":"11_CR6","unstructured":"Dosovitskiy, A.: An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Fan, D.P., Ji, G.P., Zhou, T., Chen, G., Fu, H., Shen, J., Shao, L.: Pranet: Parallel reverse attention network for polyp segmentation. In: MICCAI. pp. 263\u2013273 (2020)","DOI":"10.1007\/978-3-030-59725-2_26"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Fang, Y., Chen, C., Yuan, Y., Tong, K.y.: Selective feature aggregation network with area-boundary constraints for polyp segmentation. In: MICCAI. pp. 302\u2013310 (2019)","DOI":"10.1007\/978-3-030-32239-7_34"},{"key":"11_CR9","first-page":"186","volume":"60","author":"Y Feng","year":"2017","unstructured":"Feng, Y., Zhao, H., Li, X., Zhang, X., Li, H.: A multi-scale 3d otsu thresholding algorithm for medical image segmentation. DSP 60, 186\u2013199 (2017)","journal-title":"DSP"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., Tang, Y., Nath, V., Yang, D., Myronenko, A., Landman, B., Roth, H.R., Xu, D.: Unetr: Transformers for 3d medical image segmentation. In: WACV. pp. 574\u2013584 (2022)","DOI":"10.1109\/WACV51458.2022.00181"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"11_CR12","unstructured":"Huang, C.H., Wu, H.Y., Lin, Y.L.: Hardnet-mseg: A simple encoder-decoder polyp segmentation neural network that achieves over 0.9 mean dice and 86 fps. arXiv preprint arXiv:2101.07172 (2021)"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Jha, D., Smedsrud, P.H., Riegler, M.A., Halvorsen, P., de\u00a0Lange, T., Johansen, D., Johansen, H.D.: Kvasir-seg: A segmented polyp dataset. In: MMM. pp. 451\u2013462 (2020)","DOI":"10.1007\/978-3-030-37734-2_37"},{"key":"11_CR14","unstructured":"Jha, D., Tomar, N.K., Sharma, V., Bagci, U.: Transnetr: Transformer-based residual network for polyp segmentation with multi-center out-of-distribution testing. arXiv preprint arXiv:2303.07428 (2023)"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Li, K., Wang, Y., Zhang, J., Gao, P., Song, G., Liu, Y., Li, H., Qiao, Y.: Uniformer: Unifying convolution and self-attention for visual recognition. IEEE TPAMI (2023)","DOI":"10.1109\/TPAMI.2023.3282631"},{"key":"11_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: Hierarchical vision transformer using shifted windows. In: ICCV. pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"11_CR17","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"issue":"1","key":"11_CR18","doi-asserted-by":"publisher","first-page":"014005","DOI":"10.1117\/1.JMI.10.1.014005","volume":"10","author":"A Lou","year":"2023","unstructured":"Lou, A., Guan, S., Loew, M.: Caranet: context axial reverse attention network for segmentation of small medical objects. Journal of Medical Imaging 10(1), 014005\u2013014005 (2023)","journal-title":"Journal of Medical Imaging"},{"issue":"7","key":"11_CR19","doi-asserted-by":"publisher","first-page":"1488","DOI":"10.1109\/TMI.2014.2314959","volume":"33","author":"AV Mamonov","year":"2014","unstructured":"Mamonov, A.V., Figueiredo, I.N., Figueiredo, P.N., Tsai, Y.H.R.: Automated polyp detection in colon capsule endoscopy. IEEE Trans. Med. Imaging 33(7), 1488\u20131502 (2014)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Milletari, F., Navab, N., Ahmadi, S.A.: V-net: Fully convolutional neural networks for volumetric medical image segmentation. In: IC3DV. pp. 565\u2013571. Ieee (2016)","DOI":"10.1109\/3DV.2016.79"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Mubarak, D.M.N., Sathik, M.M., Beevi, S.Z., Revathy, K.: A hybrid region growing algorithm for medical image segmentation. IJCSIT pp. 61\u201370 (2012)","DOI":"10.5121\/ijcsit.2012.4306"},{"key":"11_CR22","unstructured":"Nguyen, Q.V., Huynh, V.T., Kim, S.H.: Adaptation of distinct semantics for uncertain areas in polyp segmentation. In: BMVC (2023)"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Nguyen, Q.V., Tran, T.T., Pham, V.T.: Gca-net: Geometrical constraints-based advanced network for polyp segmentation. In: 2022 9th NAFOSTED Conference on Information and Computer Science (NICS). pp. 241\u2013246. IEEE (2022)","DOI":"10.1109\/NICS56915.2022.10013367"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Nguyen, Q.V., Tran, T.T., et\u00a0al.: Fcmd-net: A full-connection multi-decoder network for polyp segmentation. In: 2022 6th International Conference on Green Technology and Sustainable Development (GTSD). pp. 1070\u20131075. IEEE (2022)","DOI":"10.1109\/GTSD54989.2022.9989317"},{"key":"11_CR25","doi-asserted-by":"crossref","unstructured":"Patel, K., Bur, A.M., Wang, G.: Enhanced u-net: A feature enhancement network for polyp segmentation. In: 2021 18th conference on robots and vision (CRV). pp. 181\u2013188. IEEE (2021)","DOI":"10.1109\/CRV52889.2021.00032"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: Convolutional networks for biomedical image segmentation. In: MICCAI. pp. 234\u2013241 (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"3","key":"11_CR27","first-page":"774","volume":"30","author":"T Shen","year":"2010","unstructured":"Shen, T., Li, H., Huang, X.: Active volume models for medical image segmentation. IEEE TMI 30(3), 774\u2013791 (2010)","journal-title":"IEEE TMI"},{"key":"11_CR28","first-page":"283","volume":"9","author":"J Silva","year":"2014","unstructured":"Silva, J., Histace, A., Romain, O., Dray, X., Granado, B.: Toward embedded detection of polyps in wce images for early diagnosis of colorectal cancer. IJCARS 9, 283\u2013293 (2014)","journal-title":"IJCARS"},{"key":"11_CR29","first-page":"79","volume":"2015","author":"N Tajbakhsh","year":"2015","unstructured":"Tajbakhsh, N., Gurudu, S., Liang, J.: Automatic polyp detection in colonoscopy videos using an ensemble of convolutional neural networks. IEEE ISBI 2015, 79\u201383 (2015)","journal-title":"IEEE ISBI"},{"issue":"2","key":"11_CR30","first-page":"630","volume":"35","author":"N Tajbakhsh","year":"2015","unstructured":"Tajbakhsh, N., Gurudu, S.R., Liang, J.: Automated polyp detection in colonoscopy videos using shape and context information. IEEE TMI 35(2), 630\u2013644 (2015)","journal-title":"IEEE TMI"},{"key":"11_CR31","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. NeurIPS 30 (2017)"},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"V\u00e1zquez, D., Bernal, J., S\u00e1nchez, F.J., Fern\u00e1ndez-Esparrach, G., L\u00f3pez, A.M., Romero, A., Drozdzal, M., Courville, A., et\u00a0al.: A benchmark for endoluminal scene segmentation of colonoscopy images. JHE 2017 (2017)","DOI":"10.1155\/2017\/4037190"},{"key":"11_CR33","doi-asserted-by":"crossref","unstructured":"Wang, H., Cao, P., Wang, J., Zaiane, O.R.: Uctransnet: rethinking the skip connections in u-net from a channel-wise perspective with transformer. In: AAAI. vol.\u00a036, pp. 2441\u20132449 (2022)","DOI":"10.1609\/aaai.v36i3.20144"},{"key":"11_CR34","doi-asserted-by":"crossref","unstructured":"Wang, J., Huang, Q., Tang, F., Meng, J., Su, J., Song, S.: Stepwise feature fusion: Local guides global. In: MICCAI. pp. 110\u2013120 (2022)","DOI":"10.1007\/978-3-031-16437-8_11"},{"key":"11_CR35","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Fan, D.P., Song, K., Liang, D., Lu, T., Luo, P., Shao, L.: Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In: ICCV. pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"11_CR36","doi-asserted-by":"crossref","unstructured":"Wei, J., Hu, Y., Zhang, R., Li, Z., Zhou, S.K., Cui, S.: Shallow attention network for polyp segmentation. In: MICCAI. pp. 699\u2013708 (2021)","DOI":"10.1007\/978-3-030-87193-2_66"},{"key":"11_CR37","doi-asserted-by":"crossref","unstructured":"Wenxuan, W., Chen, C., Meng, D., Hong, Y., Sen, Z., Jiangyun, L.: Transbts: Multimodal brain tumor segmentation using transformer. In: MICCAI. pp. 109\u2013119 (2021)","DOI":"10.1007\/978-3-030-87193-2_11"},{"key":"11_CR38","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: Cbam: Convolutional block attention module. In: Proceedings of the European conference on computer vision (ECCV). pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"11_CR39","volume":"151","author":"C Wu","year":"2022","unstructured":"Wu, C., Long, C., Li, S., Yang, J., Jiang, F., Zhou, R.: Msraformer: Multiscale spatial reverse attention network for polyp segmentation. CBM 151, 106274 (2022)","journal-title":"CBM"},{"key":"11_CR40","doi-asserted-by":"crossref","unstructured":"Xie, S., Tu, Z.: Holistically-nested edge detection. In: ICCV. pp. 1395\u20131403 (2015)","DOI":"10.1109\/ICCV.2015.164"},{"key":"11_CR41","doi-asserted-by":"crossref","unstructured":"Xie, Y., Zhang, J., Shen, C., Xia, Y.: Cotr: Efficiently bridging cnn and transformer for 3d medical image segmentation. In: MICCAI. pp. 171\u2013180 (2021)","DOI":"10.1007\/978-3-030-87199-4_16"},{"key":"11_CR42","unstructured":"Xu, C., Pham, D.L., Prince, J.L.: Image segmentation using deformable models. Handbook of medical imaging 2(20), 0 (2000)"},{"issue":"11","key":"11_CR43","first-page":"1344","volume":"23","author":"J Yao","year":"2004","unstructured":"Yao, J., Miller, M., Franaszek, M., Summers, R.M.: Colonic polyp segmentation in ct colonography-based on fuzzy clustering and deformable models. IEEE TMI 23(11), 1344\u20131352 (2004)","journal-title":"IEEE TMI"},{"key":"11_CR44","doi-asserted-by":"crossref","unstructured":"Yin, Z., Liang, K., Ma, Z., Guo, J.: Duplex contextual relation network for polyp segmentation. In: IEEE ISBI. pp.\u00a01\u20135 (2022)","DOI":"10.1109\/ISBI52829.2022.9761402"},{"key":"11_CR45","unstructured":"Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122 (2015)"},{"issue":"2","key":"11_CR46","doi-asserted-by":"publisher","first-page":"896","DOI":"10.1109\/TPAMI.2023.3329173","volume":"46","author":"W Yu","year":"2024","unstructured":"Yu, W., Si, C., Zhou, P., Luo, M., Zhou, Y., Feng, J., Yan, S., Wang, X.: Metaformer baselines for vision. IEEE TPAMI 46(2), 896\u2013912 (2024)","journal-title":"Metaformer baselines for vision. IEEE TPAMI"},{"key":"11_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, R., Li, G., Li, Z., Cui, S., Qian, D., Yu, Y.: Adaptive context selection for polyp segmentation. In: MICCAI. pp. 253\u2013262 (2020)","DOI":"10.1007\/978-3-030-59725-2_25"},{"key":"11_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Liu, H., Hu, Q.: Transfuse: Fusing transformers and cnns for medical image segmentation. In: MICCAI. pp. 14\u201324 (2021)","DOI":"10.1007\/978-3-030-87193-2_2"},{"key":"11_CR49","doi-asserted-by":"crossref","unstructured":"Zhao, X., Zhang, L., Lu, H.: Automatic polyp segmentation via multi-scale subtraction network. In: MICCAI. pp. 120\u2013130 (2021)","DOI":"10.1007\/978-3-030-87193-2_12"},{"issue":"6","key":"11_CR50","first-page":"1856","volume":"39","author":"Z Zhou","year":"2019","unstructured":"Zhou, Z., Siddiquee, M.M.R., Tajbakhsh, N., Liang, J.: Unet++: Redesigning skip connections to exploit multiscale features in image segmentation. IEEE TMI 39(6), 1856\u20131867 (2019)","journal-title":"IEEE TMI"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0901-7_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T08:09:25Z","timestamp":1733558965000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0901-7_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,8]]},"ISBN":["9789819609000","9789819609017"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0901-7_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,8]]},"assertion":[{"value":"8 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}