{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T17:50:22Z","timestamp":1777053022759,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","funder":[{"name":"Romanian Hub for Artificial Intelligence - HRIA","award":["351416"],"award-info":[{"award-number":["351416"]}]},{"name":"ENFIELD: European Lighthouse to Manifest Trustworthy and Green AI","award":["oc1-2024-TES-01-19"],"award-info":[{"award-number":["oc1-2024-TES-01-19"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,8]]},"DOI":"10.1145\/3746271.3776602","type":"proceedings-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T17:31:21Z","timestamp":1777051881000},"page":"17-23","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["ViTXSEG: Vision Transformer for Medical Segmentation via Multi-Explainability Fusion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5814-992X","authenticated-orcid":false,"given":"Eduard","family":"Hogea","sequence":"first","affiliation":[{"name":"Department of Computer Science, West University of Timisoara, Timisoara, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4846-3752","authenticated-orcid":false,"given":"Darian M.","family":"Onchis","sequence":"additional","affiliation":[{"name":"Department of Computer Science, West University of Timisoara, Timisoara, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7319-8798","authenticated-orcid":false,"given":"Ana","family":"Coporan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, West University of Timisoara, Timisoara, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7249-1871","authenticated-orcid":false,"given":"Adina Magda","family":"Florea","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Politehnica University of Bucharest, Bucharest, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7391-6187","authenticated-orcid":false,"given":"Codruta","family":"Istin","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Technology, Politehnica University of Timisoara, Timisoara, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,24]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-13690-4"},{"key":"e_1_3_2_1_2_1","volume-title":"Quantifying attention flow in transformers. arXiv preprint arXiv:2005.00928","author":"Abnar Samira","year":"2020","unstructured":"Samira Abnar and Willem Zuidema. 2020. Quantifying attention flow in transformers. arXiv preprint arXiv:2005.00928 (2020)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"e_1_3_2_1_4_1","volume-title":"European conference on computer vision. Springer, 205-218","author":"Cao Hu","year":"2022","unstructured":"Hu Cao, Yueyue Wang, Joy Chen, Dongsheng Jiang, Xiaopeng Zhang, Qi Tian, and Manning Wang. 2022. Swin-unet: Unet-like pure transformer for medical image segmentation. In European conference on computer vision. Springer, 205-218."},{"key":"e_1_3_2_1_5_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 L 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_6_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. 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_7_1","volume-title":"International Conference on Learning Representations (ICLR).","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_8_1","volume-title":"Proc. 31st Netw. Distrib. Syst. Secur. Symp.","author":"Fung Clement","year":"2024","unstructured":"Clement Fung, Eric Zeng, and Lujo Bauer. 2024. Attributions for ML-based ICS anomaly detection: From theory to practice. In Proc. 31st Netw. Distrib. Syst. Secur. Symp."},{"key":"e_1_3_2_1_9_1","volume-title":"VGG Image Annotator (VIA). https:\/\/www.robots.ox.ac.uk\/ vgg\/software\/via\/via_demo.html. Version 2.0.12, accessed","author":"Visual Geometry Group","year":"2025","unstructured":"Visual Geometry Group. 2021. VGG Image Annotator (VIA). https:\/\/www.robots.ox.ac.uk\/ vgg\/software\/via\/via_demo.html. Version 2.0.12, accessed April 6, 2025."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-02111-x"},{"key":"e_1_3_2_1_11_1","volume-title":"International MICCAI brainlesion workshop","author":"Hatamizadeh Ali","unstructured":"Ali Hatamizadeh, Vishwesh Nath, Yucheng Tang, Dong Yang, Holger R Roth, and Daguang Xu. 2021. Swin unetr: Swin transformers for semantic segmentation of brain tumors in mri images. In International MICCAI brainlesion workshop. Springer, 272-284."},{"key":"e_1_3_2_1_12_1","volume-title":"Adina Magda Florea, and Codruta Istin","author":"Hogea Eduard","year":"2024","unstructured":"Eduard Hogea, Darian M Onchis, Ana Coporan, Adina Magda Florea, and Codruta Istin. 2024a. ViTmiX: Vision Transformer Explainability Augmented by Mixed Visualization Methods. arXiv preprint arXiv:2412.14231 (2024)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","first-page":"892","DOI":"10.1016\/j.jmsy.2024.10.003","article-title":"LogicLSTM: Logically-driven long short-term memory model for fault diagnosis in gearboxes","volume":"77","author":"Hogea Eduard","year":"2024","unstructured":"Eduard Hogea, Darian M Onchi\u015f, Ruqiang Yan, and Zheng Zhou. 2024b. LogicLSTM: Logically-driven long short-term memory model for fault diagnosis in gearboxes. Journal of Manufacturing Systems, Vol. 77 (2024), 892-902.","journal-title":"Journal of Manufacturing Systems"},{"key":"e_1_3_2_1_14_1","volume-title":"Exddv: A new dataset for explainable deepfake detection in video. arXiv preprint arXiv:2503.14421","author":"Hondru Vlad","year":"2025","unstructured":"Vlad Hondru, Eduard Hogea, Darian Onchis, and Radu Tudor Ionescu. 2025. Exddv: A new dataset for explainable deepfake detection in video. arXiv preprint arXiv:2503.14421 (2025)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s42452-025-06879-5"},{"key":"e_1_3_2_1_16_1","volume-title":"A Survey of Vision Transformers in Autonomous Driving: Current Trends and Future Directions. arXiv preprint arXiv:2403.07542","author":"Lai-Dang Quoc-Vinh","year":"2024","unstructured":"Quoc-Vinh Lai-Dang. 2024. A Survey of Vision Transformers in Autonomous Driving: Current Trends and Future Directions. arXiv preprint arXiv:2403.07542 (2024)."},{"key":"e_1_3_2_1_17_1","volume-title":"Lundberg and Su-In Lee","author":"Scott","year":"2017","unstructured":"Scott M. Lundberg and Su-In Lee. 2017. A Unified Approach to Interpreting Model Predictions. In Advances in Neural Information Processing Systems 30 (NeurIPS 2017). 4765-4774."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2013.6610779"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3625287"},{"key":"e_1_3_2_1_20_1","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). 1135-1144","author":"Ribeiro Marco Tulio","year":"2016","unstructured":"Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2016. ''Why Should I Trust You?: Explaining the Predictions of Any Classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD). 1135-1144."},{"key":"e_1_3_2_1_21_1","volume-title":"Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015 (Lecture Notes in Computer Science","volume":"241","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 - MICCAI 2015 (Lecture Notes in Computer Science, Vol. 9351). Springer, 234-241."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.01.012"},{"key":"e_1_3_2_1_23_1","volume-title":"IEEE International Conference on Computer Vision (ICCV). 618-626","author":"Selvaraju Ramprasaath R.","year":"2017","unstructured":"Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, and Dhruv Batra. 2017. Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. In IEEE International Conference on Computer Vision (ICCV). 618-626."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.fsisyn.2022.100217"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning (ICML). 3319-3328","author":"Sundararajan Mukund","year":"2017","unstructured":"Mukund Sundararajan, Ankur Taly, and Qiqi Yan. 2017. Axiomatic Attribution for Deep Networks. In Proceedings of the 34th International Conference on Machine Learning (ICML). 3319-3328."},{"key":"e_1_3_2_1_26_1","volume-title":"Patel","author":"Jose Valanarasu Jeya Maria","year":"2021","unstructured":"Jeya Maria Jose Valanarasu, Phuong Nguyen, and Vishal M. Patel. 2021. Medical Transformer: Gated Axial-Attention for Medical Image Segmentation. In Medical Image Computing and Computer-Assisted Intervention - MICCAI 2021, Part III (Lecture Notes in Computer Science, Vol. 12903). Springer, 121-132."},{"key":"e_1_3_2_1_27_1","volume-title":"Part I (Lecture Notes in Computer Science","volume":"119","author":"Wang Wenxuan","year":"2021","unstructured":"Wenxuan Wang, Chen Chen, Meng Ding, Hong Yu, Sen Zha, and Jiangyun Li. 2021. TransBTS: Multimodal Brain Tumor Segmentation Using Transformer. In Medical Image Computing and Computer-Assisted Intervention - MICCAI 2021, Part I (Lecture Notes in Computer Science, Vol. 12901). Springer, 109-119."},{"key":"e_1_3_2_1_28_1","volume-title":"Part III (Lecture Notes in Computer Science","volume":"180","author":"Xie Yutong","year":"2021","unstructured":"Yutong Xie, Jiancheng Yang, Yukun Zhou, Zhengxing Shen, and Yong Xia. 2021. CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation. In Medical Image Computing and Computer-Assisted Intervention - MICCAI 2021, Part III (Lecture Notes in Computer Science, Vol. 12903). Springer, 171-180."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the International Workshop on Automotive and Medical Multimedia: Bridging the Gap Between Mobility and Healthcare"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746271.3776602","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T17:31:35Z","timestamp":1777051895000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746271.3776602"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,8]]},"references-count":30,"alternative-id":["10.1145\/3746271.3776602","10.1145\/3746271"],"URL":"https:\/\/doi.org\/10.1145\/3746271.3776602","relation":{},"subject":[],"published":{"date-parts":[[2026,4,8]]},"assertion":[{"value":"2026-04-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}