{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T12:29:37Z","timestamp":1771244977958,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819569496","type":"print"},{"value":"9789819569502","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\/978-981-95-6950-2_9","type":"book-chapter","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T11:58:44Z","timestamp":1771243124000},"page":"117-132","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["FIGROTD: A Friendly-to-Handle Dataset for\u00a0Image Guided Retrieval with\u00a0Optional Text"],"prefix":"10.1007","author":[{"given":"Hoang-Bao","family":"Le","sequence":"first","affiliation":[]},{"given":"Allie","family":"Tran","sequence":"additional","affiliation":[]},{"given":"Binh T.","family":"Nguyen","sequence":"additional","affiliation":[]},{"given":"Liting","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Cathal","family":"Gurrin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,2,17]]},"reference":[{"key":"9_CR1","doi-asserted-by":"crossref","unstructured":"Agnolucci, L., Baldrati, A., Bertini, M., Del\u00a0Bimbo, A.: iSEARLE: improving textual inversion for zero-shot composed image retrieval. arXiv preprint arXiv:2405.02951 (2024)","DOI":"10.1109\/ICCV51070.2023.01407"},{"key":"9_CR2","unstructured":"Cuong, D.V., Le, H.B., Nguyen, A.P.N., Zhou, L., Gurrin, C.: Quizzard@INOVA challenge 2025 \u2013 track a: Plug-and-play technique in interleaved multi-image model (2025). https:\/\/arxiv.org\/abs\/2506.11737"},{"issue":"2","key":"9_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1348246.1348248","volume":"40","author":"R Datta","year":"2008","unstructured":"Datta, R., Joshi, D., Li, J., Wang, J.Z.: Image retrieval: ideas, influences, and trends of the new age. ACM Comput. Surv. (CSUR) 40(2), 1\u201360 (2008)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"9_CR4","doi-asserted-by":"crossref","unstructured":"Dey, S., Riba, P., Dutta, A., Llados, J., Song, Y.Z.: Doodle to search: practical zero-shot sketch-based image retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2179\u20132188 (2019)","DOI":"10.1109\/CVPR.2019.00228"},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Gatti, P., Parikh, K.G., Paul, D.P., Gupta, M., Mishra, A.: Composite sketch+text queries for retrieving objects with elusive names and complex interactions. In: AAAI (2024)","DOI":"10.1609\/aaai.v38i3.27956"},{"key":"9_CR6","doi-asserted-by":"publisher","unstructured":"Hummel, T., Karthik, S., Georgescu, M.I., Akata, Z.: EgoCVR: an egocentric benchmark for fine-grained composed video retrieval. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision, ECCV 2024. LNCS, vol. 15095, pp. 1\u201317. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-72913-3_1","DOI":"10.1007\/978-3-031-72913-3_1"},{"key":"9_CR7","doi-asserted-by":"crossref","unstructured":"Huynh, C., et al.: CoLLM: a large language model for composed image retrieval. arXiv preprint arXiv:2503.19910 (2025)","DOI":"10.1109\/CVPR52734.2025.00378"},{"key":"9_CR8","doi-asserted-by":"publisher","unstructured":"Levy, M., Ben-Ari, R., Darshan, N., Lischinski, D.: Data roaming and quality assessment for composed image retrieval. Proc. AAAI Conf. Artif. Intell. 38(4), 2991\u20132999 (2024). https:\/\/doi.org\/10.1609\/aaai.v38i4.28081, https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/28081","DOI":"10.1609\/aaai.v38i4.28081"},{"key":"9_CR9","unstructured":"Li, F., et al.: LLaVA-next-interleave: tackling multi-image, video, and 3d in large multimodal models. arXiv preprint arXiv:2407.07895 (2024)"},{"key":"9_CR10","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML (2022)"},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Li, Q., Wang, S., Zhang, W., Bai, S., Nie, W., Liu, A.: DCDL: dual causal disentangled learning for zero-shot sketch-based image retrieval. IEEE Trans. Multimedia (2025)","DOI":"10.1109\/TMM.2025.3543035"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Lin, F., Li, M., Li, D., Hospedales, T., Song, Y.Z., Qi, Y.: Zero-shot everything sketch-based image retrieval, and in explainable style. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23349\u201323358 (2023)","DOI":"10.1109\/CVPR52729.2023.02236"},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"Liu, L., Shen, F., Shen, Y., Liu, X., Shao, L.: Deep sketch hashing: Fast free-hand sketch-based image retrieval. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2862\u20132871 (2017)","DOI":"10.1109\/CVPR.2017.247"},{"key":"9_CR14","unstructured":"Liu, Y., Yao, J., Zhang, Y., Wang, Y., Xie, W.: Zero-shot composed text-image retrieval. arXiv preprint arXiv:2306.07272 (2023)"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Z., Rodriguez-Opazo, C., Teney, D., Gould, S.: Image retrieval on real-life images with pre-trained vision-and-language models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), October 2021, pp. 2125\u20132134 ()","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"9_CR16","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"Pang, L., Wang, Y., Song, Y.Z., Huang, T., Tian, Y.: Cross-domain adversarial feature learning for sketch re-identification. In: Proceedings of the 26th ACM international conference on Multimedia, pp. 609\u2013617 (2018)","DOI":"10.1145\/3240508.3240606"},{"key":"9_CR18","doi-asserted-by":"crossref","unstructured":"Psomas, B., et al.: Composed image retrieval for remote sensing. In: 2024 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2024 (2024)","DOI":"10.1109\/IGARSS53475.2024.10642874"},{"key":"9_CR19","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"9_CR20","unstructured":"Rossetto, L., et\u00a0al.: The CASTLE 2024 dataset: advancing the art of multimodal understanding. arXiv preprint arXiv:2503.17116 (2025)"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Sain, A., Bhunia, A.K., Chowdhury, P.N., Koley, S., Xiang, T., Song, Y.Z.: Clip for all things zero-shot sketch-based image retrieval, fine-grained or not. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2765\u20132775 (2023)","DOI":"10.1109\/CVPR52729.2023.00271"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Vo, N., et al.: Composing text and image for image retrieval - an empirical odyssey. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019 (2019)","DOI":"10.1109\/CVPR.2019.00660"},{"key":"9_CR23","unstructured":"Wang, P., Chen, Z., Zhao, Z., Su, F.: Prompting vision-language fusion for zero-shot composed image retrieval. In: The 16th Asian Conference on Machine Learning (Conference Track) (2025)"},{"key":"9_CR24","unstructured":"Wu, H., et al.: The fashion IQ dataset: retrieving images by combining side information and relative natural language feedback. In: CVPR (2021)"},{"key":"9_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1007\/978-3-030-01225-0_19","volume-title":"Computer Vision \u2013 ECCV 2018","author":"SK Yelamarthi","year":"2018","unstructured":"Yelamarthi, S.K., Reddy, S.K., Mishra, A., Mittal, A.: A zero-shot framework for sketch based image retrieval. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 316\u2013333. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_19"},{"key":"9_CR26","doi-asserted-by":"publisher","first-page":"102398","DOI":"10.1016\/j.aei.2024.102398","volume":"60","author":"H Zhang","year":"2024","unstructured":"Zhang, H., Cheng, D., Kou, Q., Asad, M., Jiang, H.: Indicative vision transformer for end-to-end zero-shot sketch-based image retrieval. Adv. Eng. Inform. 60, 102398 (2024)","journal-title":"Adv. Eng. Inform."},{"key":"9_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, H., Liu, S., Zhang, C., Ren, W., Wang, R., Cao, X.: SketchNet: sketch classification with web images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1105\u20131113 (2016)","DOI":"10.1109\/CVPR.2016.125"},{"key":"9_CR28","unstructured":"Zhang, K., et al.: MagicLens: self-supervised image retrieval with open-ended instructions. In: The Forty-First International Conference on Machine Learning (ICML), pp. 59403\u201359420 (2024)"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-6950-2_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T11:58:48Z","timestamp":1771243128000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-6950-2_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819569496","9789819569502"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-6950-2_9","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":"17 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"}}]}}