{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:26:20Z","timestamp":1759883180593,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032060686","type":"print"},{"value":"9783032060693","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:00:00Z","timestamp":1759881600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:00:00Z","timestamp":1759881600000},"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\/978-3-032-06069-3_9","type":"book-chapter","created":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T15:54:02Z","timestamp":1759852442000},"page":"105-118","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dynamic Sub-region Search In Homogeneous Collections Using CLIP"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3341-1524","authenticated-orcid":false,"given":"Bastian","family":"J\u00e4ckl","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2733-7690","authenticated-orcid":false,"given":"Vojt\u011bch","family":"Kloda","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7966-9740","authenticated-orcid":false,"given":"Daniel","family":"A. Keim","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3558-4144","authenticated-orcid":false,"given":"Jakub","family":"Loko\u010d","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,8]]},"reference":[{"key":"9_CR1","unstructured":"Grounded-sam-2. https:\/\/github.com\/IDEA-Research\/Grounded-SAM-2, Accessed 06 May 2025"},{"key":"9_CR2","doi-asserted-by":"publisher","unstructured":"Bla\u017eek, A., Loko\u010d, J., Matzner, F., Skopal, T.: Enhanced signature-based video browser. In: He, X., Luo, S., Tao, D., Xu, C., Yang, J., Hasan, M.A. (eds.) MMM 2015. LNCS, vol. 8936, pp. 243\u2013248. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-14442-9_22","DOI":"10.1007\/978-3-319-14442-9_22"},{"key":"9_CR3","doi-asserted-by":"publisher","unstructured":"Garcia-D\u2019Urso, N.E., Galan-Cuenca, A., Climent-P\u00e9rez, P., Saval-Calvo, M., Azorin-Lopez, J., Fuster-Guillo, A.: Efficient instance segmentation using deep learning for species identification in fish markets. In: IJCNN, pp.\u00a01\u20138 (2022). https:\/\/doi.org\/10.1109\/IJCNN55064.2022.9892945","DOI":"10.1109\/IJCNN55064.2022.9892945"},{"key":"9_CR4","doi-asserted-by":"publisher","unstructured":"Hinami, R., Matsui, Y., Satoh, S.: Region-based image retrieval revisited. In: ACM MM, MM 2017, pp. 528\u2013536. ACM (2017). https:\/\/doi.org\/10.1145\/3123266.3123312","DOI":"10.1145\/3123266.3123312"},{"key":"9_CR5","doi-asserted-by":"publisher","unstructured":"Islam, M.J., et al.: Semantic segmentation of underwater imagery: dataset and benchmark. In: IROS, IEEE\/RSJ (2020). https:\/\/doi.org\/10.1109\/IROS45743.2020.9340821","DOI":"10.1109\/IROS45743.2020.9340821"},{"key":"9_CR6","doi-asserted-by":"publisher","unstructured":"J\u00e4ckl, B., Kloda, V., Keim, D.A., Loko\u010d, J.: Dynamic sub-region search in homogeneous collections using clip (2025). https:\/\/doi.org\/10.48550\/arXiv.2506.09506","DOI":"10.48550\/arXiv.2506.09506"},{"key":"9_CR7","unstructured":"J\u00e4ckl, B., Kloda, V., Keim, D.A., Loko\u010d, J.: Experimental evaluation of static image sub-region based search models using clip. In: ArXiv (2025)"},{"key":"9_CR8","doi-asserted-by":"publisher","unstructured":"Khanam, R., Hussain, M.: Yolov11: an overview of the key architectural enhancements (2024). https:\/\/doi.org\/10.48550\/arXiv.2410.17725","DOI":"10.48550\/arXiv.2410.17725"},{"key":"9_CR9","doi-asserted-by":"publisher","unstructured":"Kirillov, A., et al.: Segment anything. arXiv:2304.02643 (2023). https:\/\/doi.org\/10.48550\/arXiv.2304.02643","DOI":"10.48550\/arXiv.2304.02643"},{"key":"9_CR10","doi-asserted-by":"publisher","unstructured":"Korfhage, N., M\u00fchling, M., Freisleben, B.: Search anything: segmentation-based similarity search via region prompts. In: Multimedia Tools and Applications (2024). https:\/\/doi.org\/10.1007\/s11042-024-20509-z","DOI":"10.1007\/s11042-024-20509-z"},{"key":"9_CR11","doi-asserted-by":"publisher","unstructured":"Lian, S., Li, H., Cong, R., Li, S., Zhang, W., Kwong, S.: Watermask: instance segmentation for underwater imagery. In: ICCV, pp. 1305\u20131315, October 2023. https:\/\/doi.org\/10.1109\/ICCV51070.2023.00126","DOI":"10.1109\/ICCV51070.2023.00126"},{"key":"9_CR12","doi-asserted-by":"publisher","unstructured":"Liu, S., et\u00a0al.: Grounding dino: marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.05499","DOI":"10.48550\/arXiv.2303.05499"},{"key":"9_CR13","doi-asserted-by":"publisher","unstructured":"Loko\u010d, J., Mejzl\u00edk, F., Vesel\u00fd, P., Soucek, T.: Enhanced somhunter for known-item search in lifelog data. In: Gurrin, C., et al. (eds.) Proceedings of the 4th Annual on Lifelog Search Challenge, LSC, pp. 71\u201373. ACM (2021). https:\/\/doi.org\/10.1145\/3463948.3469074","DOI":"10.1145\/3463948.3469074"},{"key":"9_CR14","doi-asserted-by":"publisher","first-page":"3481","DOI":"10.1007\/s00530-023-01143-5","volume":"6","author":"J Loko\u010d","year":"2023","unstructured":"Loko\u010d, J., Andreadis, S., Bailer, W., Duane, A., Gurrin, C., Ma, Z., et al.: Interactive video retrieval in the age of effective joint embedding deep models: lessons from the 11th vbs. Multimedia Syst. 6, 3481\u20133504 (2023). https:\/\/doi.org\/10.1007\/s00530-023-01143-5","journal-title":"Multimedia Syst."},{"key":"9_CR15","doi-asserted-by":"publisher","unstructured":"Mai, L., Jin, H., Lin, Z., Fang, C., Brandt, J., Liu, F.: Spatial-semantic image search by visual feature synthesis. In: CVPR, pp. 1121\u20131130 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.125","DOI":"10.1109\/CVPR.2017.125"},{"key":"9_CR16","doi-asserted-by":"publisher","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision (2024). https:\/\/doi.org\/10.48550\/arXiv.2304.07193","DOI":"10.48550\/arXiv.2304.07193"},{"key":"9_CR17","doi-asserted-by":"publisher","unstructured":"Pourian, N., Manjunath, B.: Retrieval of images with objects of specific size, location, and spatial configuration. In: 2015 IEEE Winter Conference on Applications of Computer Vision, pp. 960\u2013967 (2015). https:\/\/doi.org\/10.1109\/WACV.2015.133","DOI":"10.1109\/WACV.2015.133"},{"key":"9_CR18","doi-asserted-by":"publisher","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision (2021). https:\/\/doi.org\/10.48550\/arXiv.2103.00020","DOI":"10.48550\/arXiv.2103.00020"},{"key":"9_CR19","doi-asserted-by":"publisher","unstructured":"Ranasinghe, K., Shukla, S.N., Poursaeed, O., Ryoo, M.S., Lin, T.Y.: Learning to localize objects improves spatial reasoning in visual-llms. In: CVPR, pp. 12977\u201312987 (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.01233","DOI":"10.1109\/CVPR52733.2024.01233"},{"key":"9_CR20","doi-asserted-by":"publisher","unstructured":"Ravi, N., et al.: Sam 2: segment anything in images and videos (2024). https:\/\/doi.org\/10.48550\/arXiv.2408.00714","DOI":"10.48550\/arXiv.2408.00714"},{"key":"9_CR21","doi-asserted-by":"publisher","unstructured":"Ren, T., et al.: Grounded sam: assembling open-world models for diverse visual tasks (2024). https:\/\/doi.org\/10.48550\/arXiv.2401.14159","DOI":"10.48550\/arXiv.2401.14159"},{"key":"9_CR22","doi-asserted-by":"publisher","unstructured":"Sauter, L., Gasser, R., Schuldt, H., Bernstein, A., Rossetto, L.: Performance evaluation in multimedia retrieval. TOMM (1) (2024). https:\/\/doi.org\/10.1145\/3678881","DOI":"10.1145\/3678881"},{"key":"9_CR23","doi-asserted-by":"publisher","unstructured":"Shlapentokh-Rothman, M., et al.: Region-based representations revisited. In: CVPR, pp. 17107\u201317116, June 2024. https:\/\/doi.org\/10.1109\/CVPR52733.2024.01619","DOI":"10.1109\/CVPR52733.2024.01619"},{"key":"9_CR24","doi-asserted-by":"publisher","unstructured":"Smith, J.R., Chang, S.F.: Visualseek: a fully automated content-based image query system. In: ACM MM, p. 87\u201398 (1997). https:\/\/doi.org\/10.1145\/244130.244151","DOI":"10.1145\/244130.244151"},{"key":"9_CR25","doi-asserted-by":"publisher","unstructured":"Stroh, M., et al.: Prak tool v3: enhancing video item search using localized text and texture queries. In: ACM MMM, pp. 326\u2013333. Springer (2025). https:\/\/doi.org\/10.1007\/978-981-96-2074-6_39","DOI":"10.1007\/978-981-96-2074-6_39"},{"key":"9_CR26","doi-asserted-by":"publisher","unstructured":"Truong, Q.T., et al.: Marine video kit: a new marine video dataset for content-based analysis and retrieval. In: ACM MMM, pp. 539\u2013550. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-27077-2_42","DOI":"10.1007\/978-3-031-27077-2_42"},{"key":"9_CR27","doi-asserted-by":"publisher","unstructured":"Vadicamo, L., Arnold, R., Bailer, W., Carrara, F., Gurrin, C., Hezel, N., et\u00a0al.: Evaluating performance and trends in interactive video retrieval: insights from the 12th vbs competition. IEEE, pp. 79342\u201379366 (2024). https:\/\/doi.org\/10.1109\/ACCESS.2024.3405638","DOI":"10.1109\/ACCESS.2024.3405638"},{"key":"9_CR28","doi-asserted-by":"publisher","unstructured":"Xu, H., Wang, J., Hua, X.S., Li, S.: Image search by concept map. In: SIGIR, SIGIR 2010, pp. 275\u2013282. ACM (2010). https:\/\/doi.org\/10.1145\/1835449.1835497","DOI":"10.1145\/1835449.1835497"},{"key":"9_CR29","doi-asserted-by":"publisher","unstructured":"Xu, S., Zhang, M., Song, W., Mei, H., He, Q., Liotta, A.: A systematic review and analysis of deep learning-based underwater object detection. Neurocomputing 204\u2013232 (2023). https:\/\/doi.org\/10.1016\/j.neucom.2023.01.056","DOI":"10.1016\/j.neucom.2023.01.056"},{"key":"9_CR30","doi-asserted-by":"publisher","unstructured":"Zhao, X., et al.: Fast segment anything (2023). https:\/\/doi.org\/10.48550\/arXiv.2306.12156","DOI":"10.48550\/arXiv.2306.12156"}],"container-title":["Lecture Notes in Computer Science","Similarity Search and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06069-3_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T15:54:06Z","timestamp":1759852446000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06069-3_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,8]]},"ISBN":["9783032060686","9783032060693"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06069-3_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,8]]},"assertion":[{"value":"8 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"SISAP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Similarity Search and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Reykjavik","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Iceland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 October 2025","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":"sisap2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.sisap.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}