{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T22:33:21Z","timestamp":1730327601146,"version":"3.28.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,12,7]]},"DOI":"10.1145\/3628797.3629014","type":"proceedings-article","created":{"date-parts":[[2023,12,6]],"date-time":"2023-12-06T20:25:34Z","timestamp":1701894334000},"page":"631-638","update-policy":"http:\/\/dx.doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ConvTransNet: Merging Convolution with Transformer to Enhance Polyp Segmentation"],"prefix":"10.1145","author":[{"ORCID":"http:\/\/orcid.org\/0000-0003-2823-3861","authenticated-orcid":false,"given":"Trong-Hieu","family":"Nguyen-Mau","sequence":"first","affiliation":[{"name":"University of Science, VNU-HCM, Viet Nam"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-7367-1401","authenticated-orcid":false,"given":"Trong-Vu","family":"Hoang","sequence":"additional","affiliation":[{"name":"University of Science, VNU-HCM, Viet Nam"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-0888-8908","authenticated-orcid":false,"given":"Hai-Dang","family":"Nguyen","sequence":"additional","affiliation":[{"name":"University of Science, VNU-HCM, Viet Nam"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-3046-3041","authenticated-orcid":false,"given":"Minh-Triet","family":"Tran","sequence":"additional","affiliation":[{"name":"University of Science, VNU-HCM, Viet Nam"}]}],"member":"320","published-online":{"date-parts":[[2023,12,7]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"2015. WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians. Computerized medical imaging and graphics 43","author":"Bernal Jorge","year":"2015","unstructured":"Jorge Bernal and et al.2015. WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians. Computerized medical imaging and graphics 43 (2015), 99\u2013111."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings, Part III. Springer, 205\u2013218","author":"Cao Hu","year":"2023","unstructured":"Hu Cao, Yueyue Wang, Joy Chen, Dongsheng Jiang, Xiaopeng Zhang, Qi Tian, and Manning Wang. 2023. Swin-unet: Unet-like pure transformer for medical image segmentation. In Computer Vision\u2013ECCV 2022 Workshops: Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part III. Springer, 205\u2013218."},{"key":"e_1_3_2_1_3_1","volume-title":"Transunet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306","author":"Chen Jieneng","year":"2021","unstructured":"Jieneng Chen, Yongyi Lu, Qihang Yu, Xiangde Luo, Ehsan Adeli, Yan Wang, Le Lu, Alan\u00a0L Yuille, and Yuyin Zhou. 2021. Transunet: Transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306 (2021)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.01.013"},{"key":"e_1_3_2_1_5_1","volume-title":"Davit: Dual attention vision transformers. In Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327","author":"Ding Mingyu","year":"2022","unstructured":"Mingyu Ding, Bin Xiao, Noel Codella, Ping Luo, Jingdong Wang, and Lu Yuan. 2022. Davit: Dual attention vision transformers. In Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXIV. Springer, 74\u201392."},{"key":"e_1_3_2_1_6_1","volume-title":"Polyp-pvt: Polyp segmentation with pyramid vision transformers. arXiv preprint arXiv:2108.06932","author":"Dong Bo","year":"2021","unstructured":"Bo Dong, Wenhai Wang, Deng-Ping Fan, Jinpeng Li, Huazhu Fu, and Ling Shao. 2021. Polyp-pvt: Polyp segmentation with pyramid vision transformers. arXiv preprint arXiv:2108.06932 (2021)."},{"key":"e_1_3_2_1_7_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejca.2021.07.039"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59725-2_26"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32239-7_34"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053405"},{"key":"e_1_3_2_1_15_1","volume-title":"How much position information do convolutional neural networks encode?arXiv preprint arXiv:2001.08248","author":"Islam Md\u00a0Amirul","year":"2020","unstructured":"Md\u00a0Amirul Islam, Sen Jia, and Neil\u00a0DB Bruce. 2020. How much position information do convolutional neural networks encode?arXiv preprint arXiv:2001.08248 (2020)."},{"volume-title":"MultiMedia Modeling: 26th International Conference, MMM 2020, Daejeon, South Korea, January 5\u20138, 2020, Proceedings, Part II 26","author":"Jha D.","key":"e_1_3_2_1_16_1","unstructured":"D. Jha and et al.2020. Kvasir-seg: A segmented polyp dataset. In MultiMedia Modeling: 26th International Conference, MMM 2020, Daejeon, South Korea, January 5\u20138, 2020, Proceedings, Part II 26. Springer, 451\u2013462."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISM46123.2019.00049"},{"key":"e_1_3_2_1_18_1","volume-title":"TransNetR: Transformer-based Residual Network for Polyp Segmentation with Multi-Center Out-of-Distribution Testing. arXiv preprint arXiv:2303.07428","author":"Jha Debesh","year":"2023","unstructured":"Debesh Jha, Nikhil\u00a0Kumar Tomar, Vanshali Sharma, and Ulas Bagci. 2023. TransNetR: Transformer-based Residual Network for Polyp Segmentation with Multi-Center Out-of-Distribution Testing. arXiv preprint arXiv:2303.07428 (2023)."},{"key":"e_1_3_2_1_19_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma P","year":"2014","unstructured":"Diederik\u00a0P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"volume-title":"Medical Imaging 2021: Image Processing, Vol.\u00a011596","author":"Lou Ange","key":"e_1_3_2_1_22_1","unstructured":"Ange Lou, Shuyue Guan, and Murray Loew. 2021. DC-UNet: rethinking the U-Net architecture with dual channel efficient CNN for medical image segmentation. In Medical Imaging 2021: Image Processing, Vol.\u00a011596. SPIE, 758\u2013768."},{"key":"e_1_3_2_1_23_1","volume-title":"Swish: a self-gated activation function. arXiv preprint arXiv:1710.05941 7, 1","author":"Ramachandran Prajit","year":"2017","unstructured":"Prajit Ramachandran, Barret Zoph, and Quoc\u00a0V Le. 2017. Swish: a self-gated activation function. arXiv preprint arXiv:1710.05941 7, 1 (2017), 5."},{"key":"e_1_3_2_1_24_1","volume-title":"U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference","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\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. Springer, 234\u2013241."},{"key":"e_1_3_2_1_25_1","volume-title":"Cancer statistics","author":"Siegel L","year":"2022","unstructured":"Rebecca\u00a0L Siegel, Kimberly\u00a0D Miller, Hannah\u00a0E Fuchs, and Ahmedin Jemal. 2022. Cancer statistics, 2022. CA: a cancer journal for clinicians 72, 1 (2022), 7\u201333."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-013-0926-3"},{"key":"e_1_3_2_1_27_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_28_1","volume-title":"Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research 15, 1","author":"Srivastava Nitish","year":"2014","unstructured":"Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever, and Ruslan Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research 15, 1 (2014), 1929\u20131958."},{"key":"e_1_3_2_1_29_1","volume-title":"2015. Automated polyp detection in colonoscopy videos using shape and context information","author":"Tajbakhsh Nima","year":"2015","unstructured":"Nima Tajbakhsh and et al.2015. Automated polyp detection in colonoscopy videos using shape and context information. IEEE transactions on medical imaging (2015)."},{"key":"e_1_3_2_1_30_1","volume-title":"Automated polyp detection in colonoscopy videos using shape and context information","author":"Tajbakhsh Nima","year":"2015","unstructured":"Nima Tajbakhsh, Suryakanth\u00a0R Gurudu, and Jianming Liang. 2015. Automated polyp detection in colonoscopy videos using shape and context information. IEEE transactions on medical imaging 35, 2 (2015), 630\u2013644."},{"key":"e_1_3_2_1_31_1","volume-title":"International conference on machine learning. PMLR, 10347\u201310357","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herv\u00e9 J\u00e9gou. 2021. Training data-efficient image transformers & distillation through attention. In International conference on machine learning. PMLR, 10347\u201310357."},{"key":"e_1_3_2_1_32_1","volume-title":"A benchmark for endoluminal scene segmentation of colonoscopy images. Journal of healthcare engineering 2017","author":"V\u00e1zquez David","year":"2017","unstructured":"David V\u00e1zquez, Jorge Bernal, F\u00a0Javier S\u00e1nchez, Gloria Fern\u00e1ndez-Esparrach, Antonio\u00a0M L\u00f3pez, Adriana Romero, Michal Drozdzal, and Aaron Courville. 2017. A benchmark for endoluminal scene segmentation of colonoscopy images. Journal of healthcare engineering 2017 (2017)."},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings, Part III. Springer, 110\u2013120","author":"Wang Jinfeng","year":"2022","unstructured":"Jinfeng Wang, Qiming Huang, Feilong Tang, Jia Meng, Jionglong Su, and Sifan Song. 2022. Stepwise feature fusion: Local guides global. In Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2022: 25th International Conference, Singapore, September 18\u201322, 2022, Proceedings, Part III. Springer, 110\u2013120."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"e_1_3_2_1_37_1","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie Enze","year":"2021","unstructured":"Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose\u00a0M Alvarez, and Ping Luo. 2021. SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in Neural Information Processing Systems 34 (2021), 12077\u201312090.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00299"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87193-2_12"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00889-5_1"}],"event":{"name":"SOICT 2023: The 12th International Symposium on Information and Communication Technology","acronym":"SOICT 2023","location":"Ho Chi Minh Vietnam"},"container-title":["Proceedings of the 12th International Symposium on Information and Communication Technology"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3628797.3629014","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,5]],"date-time":"2024-03-05T22:17:27Z","timestamp":1709677047000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3628797.3629014"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,7]]},"references-count":42,"alternative-id":["10.1145\/3628797.3629014","10.1145\/3628797"],"URL":"https:\/\/doi.org\/10.1145\/3628797.3629014","relation":{},"subject":[],"published":{"date-parts":[[2023,12,7]]},"assertion":[{"value":"2023-12-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}