{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T20:38:50Z","timestamp":1770410330088,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819569625","type":"print"},{"value":"9789819569632","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-6963-2_24","type":"book-chapter","created":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T10:08:52Z","timestamp":1770372532000},"page":"222-229","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["VERGE in\u00a0VBS 2026"],"prefix":"10.1007","author":[{"given":"Nick","family":"Pantelidis","sequence":"first","affiliation":[]},{"given":"Eleni","family":"Kosmidou","sequence":"additional","affiliation":[]},{"given":"Damianos","family":"Galanopoulos","sequence":"additional","affiliation":[]},{"given":"Dimitris","family":"Georgalis","sequence":"additional","affiliation":[]},{"given":"Stefanos","family":"Pasios","sequence":"additional","affiliation":[]},{"given":"Konstantinos","family":"Apostolidis","sequence":"additional","affiliation":[]},{"given":"Andreas","family":"Goulas","sequence":"additional","affiliation":[]},{"given":"Maria","family":"Pegia","sequence":"additional","affiliation":[]},{"given":"Georgios","family":"Tsionkis","sequence":"additional","affiliation":[]},{"given":"Konstantinos","family":"Gkountakos","sequence":"additional","affiliation":[]},{"given":"Grigorios","family":"Kouvrakis","sequence":"additional","affiliation":[]},{"given":"Anastasia","family":"Moumtzidou","sequence":"additional","affiliation":[]},{"given":"Ilias","family":"Gialampoukidis","sequence":"additional","affiliation":[]},{"given":"Stefanos","family":"Vrochidis","sequence":"additional","affiliation":[]},{"given":"Vasileios","family":"Mezaris","sequence":"additional","affiliation":[]},{"given":"Ioannis","family":"Kompatsiaris","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,2,7]]},"reference":[{"key":"24_CR1","doi-asserted-by":"publisher","unstructured":"Bai, S., et\u00a0al.: Qwen2.5-VL technical report. Tech. rep., arXiv (2025). https:\/\/doi.org\/10.48550\/arXiv.2502.13923. Technical Report, Qwen2.5-VL series","DOI":"10.48550\/arXiv.2502.13923"},{"key":"24_CR2","unstructured":"Bati\u0107, D., Holm, F., \u00d6zsoy, E., Czempiel, T., Navab, N.: Whether and when does endoscopy domain pretraining make sense? arXiv preprint: arXiv:2303.17636 (2023)"},{"key":"24_CR3","doi-asserted-by":"crossref","unstructured":"Burambekova, A., Shamoi, P.: Comparative analysis of color models for human perception and visual color difference. In: IEEE 5th International Conference on Smart Information Systems and Technologies (SIST), pp.\u00a01\u20136. IEEE (2025)","DOI":"10.1109\/SIST61657.2025.11139184"},{"key":"24_CR4","unstructured":"Che, C., Wang, C., Vercauteren, T., Tsoka, S., Garcia-Peraza-Herrera, L.C.: LEMON: a large endoscopic monocular dataset and foundation model for perception in surgical settings (2025). https:\/\/arxiv.org\/abs\/2503.19740"},{"key":"24_CR5","unstructured":"Cui, C., et al.: PaddleOCR 3.0 technical report (2025). https:\/\/arxiv.org\/abs\/2507.05595"},{"key":"24_CR6","doi-asserted-by":"publisher","unstructured":"Galanopoulos, D., Goulas, A., Leventakis, A., Patras, I., Mezaris, V.: An LLM framework for long-form video retrieval and audio-visual question answering using Qwen2\/2.5. In: 2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 3730\u20133739 (2025). https:\/\/doi.org\/10.1109\/CVPRW67362.2025.00358","DOI":"10.1109\/CVPRW67362.2025.00358"},{"key":"24_CR7","doi-asserted-by":"publisher","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 (CVPR), pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"24_CR8","unstructured":"Hong, W.Y., Kao, C.L., Kuo, Y.H., Wang, J.R., Chang, W.L., Shih, C.S.: CholecSeg8k: a semantic segmentation dataset for laparoscopic cholecystectomy based on cholec80 (2020). https:\/\/arxiv.org\/abs\/2012.12453"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Imawati, I., Sudarma, M., Putra, I., Bayupati, I.P.A.: A study of lab color space and its visualization. In: International Conference on Applied Mathematics, Statistics, and Computing, pp. 17\u201328. Atlantis Press (2024)","DOI":"10.2991\/978-94-6463-413-6_3"},{"issue":"1","key":"24_CR10","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1109\/TPAMI.2010.57","volume":"33","author":"H Jegou","year":"2010","unstructured":"Jegou, H., Douze, M., Schmid, C.: Product quantization for nearest neighbor search. IEEE Trans. Pattern Anal. Mach. Intell. 33(1), 117\u2013128 (2010)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"24_CR11","doi-asserted-by":"crossref","unstructured":"Jin, A., et al.: Tool detection and operative skill assessment in surgical videos using region-based convolutional neural networks. In: IEEE Winter Conference on Applications of Computer Vision (2018)","DOI":"10.1109\/WACV.2018.00081"},{"key":"24_CR12","doi-asserted-by":"publisher","unstructured":"Khan, F.F., Li, X., Temple, A.J., Elhoseiny, M.: FishNet: a large-scale dataset and benchmark for fish recognition, detection, and functional trait prediction. In: 2023 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 20439\u201320449 (2023). https:\/\/doi.org\/10.1109\/ICCV51070.2023.01874","DOI":"10.1109\/ICCV51070.2023.01874"},{"key":"24_CR13","doi-asserted-by":"publisher","unstructured":"Leibetseder, A., et al.: LapGyn4: a dataset for 4 automatic content analysis problems in the domain of laparoscopic gynecology. In: Proceedings of the 9th ACM Multimedia Systems Conference, MMSys 2018, Amsterdam, The Netherlands, 12\u201315 June 2018, pp. 357\u2013362. ACM (2018). https:\/\/doi.org\/10.1145\/3204949.3208127","DOI":"10.1145\/3204949.3208127"},{"key":"24_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Nasirihaghighi, S., et al.: GynSurg: a comprehensive gynecology laparoscopic surgery dataset (2025). https:\/\/arxiv.org\/abs\/2506.11356","DOI":"10.1145\/3746027.3758267"},{"issue":"3","key":"24_CR16","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1109\/JOE.2015.2469915","volume":"41","author":"K Panetta","year":"2016","unstructured":"Panetta, K., Gao, C., Agaian, S.: Human-visual-system-inspired underwater image quality measures. IEEE J. Oceanic Eng. 41(3), 541\u2013551 (2016). https:\/\/doi.org\/10.1109\/JOE.2015.2469915","journal-title":"IEEE J. Oceanic Eng."},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"Pantelidis, N., et al.: VERGE in VBS 2025. In: MultiMedia Modeling, pp. 355\u2013362. Springer Nature Singapore, Singapore (2025)","DOI":"10.1007\/978-981-96-2074-6_43"},{"key":"24_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1007\/978-3-319-51811-4_9","volume-title":"MultiMedia Modeling","author":"N Pittaras","year":"2017","unstructured":"Pittaras, N., Markatopoulou, F., Mezaris, V., Patras, I.: Comparison of fine-tuning and extension strategies for deep convolutional neural networks. In: Amsaleg, L., Gu\u00f0mundsson, G.\u00de, Gurrin, C., J\u00f3nsson, B.\u00de, Satoh, S. (eds.) MMM 2017. LNCS, vol. 10132, pp. 102\u2013114. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-51811-4_9"},{"issue":"1","key":"24_CR19","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1038\/s41597-023-02073-7","volume":"10","author":"MS R\u00edos","year":"2023","unstructured":"R\u00edos, M.S., et al.: Cholec80-CVS: an open dataset with an evaluation of Strasberg\u2019s critical view of safety for AI. Sci. Data 10(1), 194 (2023). https:\/\/doi.org\/10.1038\/s41597-023-02073-7","journal-title":"Sci. Data"},{"key":"24_CR20","unstructured":"Rossetto, L., Schoeffmann, K., Gurrin, C., Loko\u010d, J., Bailer, W.: Results of the 2025 video browser showdown. arXiv preprint: arXiv:2509.12000 (2025)"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Rossetto, L., Schuldt, H., Awad, G., Butt, A.A.: V3C \u2013 a research video collection. In: MultiMedia Modeling, pp. 349\u2013360. Springer International Publishing, Cham (2019)","DOI":"10.1007\/978-3-030-05710-7_29"},{"key":"24_CR22","unstructured":"Shao, S., et al.: CrowdHuman: a benchmark for detecting human in a crowd. arXiv preprint: arXiv:1805.00123 (2018)"},{"key":"24_CR23","unstructured":"Sou\u010dek, T., Loko\u010d, J.: TransNet V2: an effective deep network architecture for fast shot transition detection. arXiv preprint: arXiv:2008.04838 (2020)"},{"key":"24_CR24","unstructured":"Tian, Y., Ye, Q., Doermann, D.: YOLOv12: attention-centric real-time object detectors. arXiv preprint: arXiv:2502.12524 (2025)"},{"key":"24_CR25","doi-asserted-by":"crossref","unstructured":"Truong, Q.T., et al.: Marine video kit: a new marine video dataset for content-based analysis and retrieval. In: MultiMedia Modeling, pp. 539\u2013550. Springer International Publishing, Cham (2023)","DOI":"10.1007\/978-3-031-27077-2_42"},{"issue":"1","key":"24_CR26","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/TMI.2016.2593957","volume":"36","author":"AP Twinanda","year":"2016","unstructured":"Twinanda, A.P., Shehata, S., Mutter, D., Marescaux, J., De Mathelin, M., Padoy, N.: EndoNet: a deep architecture for recognition tasks on laparoscopic videos. IEEE Trans. Med. Imaging 36(1), 86\u201397 (2016)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"24_CR27","doi-asserted-by":"publisher","unstructured":"Varghese, R., M., S.: YOLOv8: a novel object detection algorithm with enhanced performance and robustness. In: 2024 International Conference on Advances in Data Engineering and Intelligent Computing Systems (ADICS), pp.\u00a01\u20136 (2024). https:\/\/doi.org\/10.1109\/ADICS58448.2024.10533619","DOI":"10.1109\/ADICS58448.2024.10533619"},{"key":"24_CR28","unstructured":"Yang, A., et\u00a0al.: Qwen3 technical report. arXiv preprint: arXiv:2505.09388 (2025)"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-6963-2_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T10:08:57Z","timestamp":1770372537000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-6963-2_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819569625","9789819569632"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-6963-2_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"7 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 January 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 January 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2026.cz\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}