{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T08:09:42Z","timestamp":1789027782552,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370228","type":"print"},{"value":"9783032370235","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\/978-3-032-37023-5_29","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T07:58:44Z","timestamp":1789027124000},"page":"528-546","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["OCTOPUS: Multi-agentic Universal Compositional Visual Retrieval"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0097-3617","authenticated-orcid":false,"given":"Zhangtao","family":"Cheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8412-6303","authenticated-orcid":false,"given":"Bozhu","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8163-3146","authenticated-orcid":false,"given":"Ting","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8038-8150","authenticated-orcid":false,"given":"Fan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"key":"29_CR1","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"29_CR2","unstructured":"Bai, S., et al.: Qwen2.5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"29_CR3","unstructured":"Bai, Y., et al.: Sentence-level prompts benefit composed image retrieval. In: Proceedings of the International Conference on Learning Representations (ICLR) (2024)"},{"key":"29_CR4","doi-asserted-by":"crossref","unstructured":"Baldrati, A., Agnolucci, L., Bertini, M., Del Bimbo, A.: Zero-shot composed image retrieval with textual inversion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 15338\u201315347 (2023)","DOI":"10.1109\/ICCV51070.2023.01407"},{"key":"29_CR5","doi-asserted-by":"publisher","first-page":"40393","DOI":"10.52202\/079017-1278","volume":"37","author":"H Chen","year":"2024","unstructured":"Chen, H., Wang, X., Chen, H., Zhang, Z., Feng, W., Huang, B., Jia, J., Zhu, W.: Verified: a video corpus moment retrieval benchmark for fine-grained video understanding. Adv. Neural Inf. Process. Syst. (NeurIPS) 37, 40393\u201340406 (2024)","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"29_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Y., Bazzani, L.: Learning joint visual semantic matching embeddings for language-guided retrieval. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 136\u2013152. Springer (2020)","DOI":"10.1007\/978-3-030-58542-6_9"},{"key":"29_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Lang, J., Zhong, T., Zhou, F.: Seeing the unseen in micro-video popularity prediction: self-correlation retrieval for missing modality generation. In: Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 142\u2013152 (2025)","DOI":"10.1145\/3690624.3709308"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, Z., et al.: Generative thinking, corrective action: user-friendly composed image retrieval via automatic multi-agent collaboration. In: Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), pp. 334\u2013344 (2025)","DOI":"10.1145\/3711896.3736982"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Cheng, Z., Zhang, J., Xu, X., Trajcevski, G., Zhong, T., Zhou, F.: Retrieval-augmented hypergraph for multimodal social media popularity prediction. In: Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 445\u2013455 (2024)","DOI":"10.1145\/3637528.3672041"},{"key":"29_CR10","unstructured":"Cheng, Z., Zheng, B., Zhong, T., Zhou, F.: Evidential matching, uncertainty calibration: towards robust composed video retrieval with noisy triplets. In: Proceedings of the ACM Web Conference, pp. 2373\u20132383 (2026)"},{"key":"29_CR11","unstructured":"Delmas, G., de\u00a0Rezende, R.S., Csurka, G., Larlus, D.: ARTEMIS: attention-based retrieval with text-explicit matching and implicit similarity. In: Proceedings of the International Conference on Learning Representations (ICLR) (2022)"},{"key":"29_CR12","unstructured":"Gao, L., et al.: PAL: program-aided language models. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 10764\u201310799. PMLR (2023)"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Gu, G., Chun, S., Kim, W., Kang, Y., Yun, S.: Language-only efficient training of zero-shot composed image retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13225\u201313234 (2024)","DOI":"10.1109\/CVPR52733.2024.01256"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Han, X., et al.: Automatic spatially-aware fashion concept discovery. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1463\u20131471 (2017)","DOI":"10.1109\/ICCV.2017.163"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Hong, R., Lang, J., Zhong, T., Wang, Y., Zhou, F.: Tameing long contexts in personalization: towards training-free and state-aware MLLM personalized assistant. In: Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 452\u2013463 (2026)","DOI":"10.1145\/3770854.3780214"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Hummel, T., Karthik, S., Georgescu, M.I., Akata, Z.: EgoCVR: an egocentric benchmark for fine-grained composed video retrieval. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 1\u201317 (2024)","DOI":"10.1007\/978-3-031-72913-3_1"},{"key":"29_CR17","unstructured":"Hurst, A., et al.: GPT-4o system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"29_CR18","unstructured":"Ilharco, G., et al.: OpenCLIP. https:\/\/doi.org\/10.5281\/zenodo.5143773"},{"issue":"6","key":"29_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3636552","volume":"56","author":"SM Islam","year":"2024","unstructured":"Islam, S.M., Joardar, S., Sekh, A.A.: A survey on fashion image retrieval. ACM Comput. Surv. 56(6), 1\u201325 (2024)","journal-title":"ACM Comput. Surv."},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Ji, Z., Yu, T., Xu, Y., Lee, N., Ishii, E., Fung, P.: Towards mitigating LLM hallucination via self reflection. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.123"},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Karthik, S., Mancini, M., Akata, Z.: KG-SP: knowledge guided simple primitives for open world compositional zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9336\u20139345 (2022)","DOI":"10.1109\/CVPR52688.2022.00912"},{"key":"29_CR22","unstructured":"Karthik, S., Roth, K., Mancini, M., Akata, Z.: Vision-by-language for training-free compositional image retrieval. In: Proceedings of the International Conference on Learning Representations (ICLR) (2024)"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Komeili, M., Shuster, K., Weston, J.: Internet-augmented dialogue generation. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), pp. 8460\u20138478 (2022)","DOI":"10.18653\/v1\/2022.acl-long.579"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Li, Y., Ma, F., Yang, Y.: Imagine and seek: improving composed image retrieval with an imagined proxy. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3984\u20133993 (2025)","DOI":"10.1109\/CVPR52734.2025.00377"},{"key":"29_CR25","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), pp. 2125\u20132134 (2021)","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Lu, P., et al.: Chameleon: plug-and-play compositional reasoning with large language models. Adv. Neural Inf. Process. Syst. (NeurIPS) 36, 43447\u201343478 (2023)","DOI":"10.52202\/075280-1882"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Mancini, M., Naeem, M.F., Xian, Y., Akata, Z.: Open world compositional zero-shot learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5222\u20135230 (2021)","DOI":"10.1109\/CVPR46437.2021.00518"},{"key":"29_CR28","doi-asserted-by":"crossref","unstructured":"Pavlichenko, N., Ustalov, D.: Best prompts for text-to-image models and how to find them. In: Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), pp. 2067\u20132071 (2023)","DOI":"10.1145\/3539618.3592000"},{"issue":"4","key":"29_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3704435","volume":"57","author":"Y Qin","year":"2024","unstructured":"Qin, Y., et al.: Tool learning with foundation models. ACM Comput. Surv. 57(4), 1\u201340 (2024)","journal-title":"ACM Comput. Surv."},{"key":"29_CR30","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 8748\u20138763 (2021)"},{"key":"29_CR31","doi-asserted-by":"crossref","unstructured":"Roth, K., Vinyals, O., Akata, Z.: Integrating language guidance into vision-based deep metric learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16177\u201316189 (2022)","DOI":"10.1109\/CVPR52688.2022.01570"},{"key":"29_CR32","doi-asserted-by":"crossref","unstructured":"Saito, K., et al.: Pic2Word: mapping pictures to words for zero-shot composed image retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 19305\u201319314 (2023)","DOI":"10.1109\/CVPR52729.2023.01850"},{"key":"29_CR33","doi-asserted-by":"crossref","unstructured":"Schick, T., et al.: ToolFormer: language models can teach themselves to use tools. Adv. Neural Inf. Process. Syst. (NeurIPS) 36, 68539\u201368551 (2023)","DOI":"10.52202\/075280-2997"},{"key":"29_CR34","doi-asserted-by":"crossref","unstructured":"Song, X., Lin, H., Wen, H., Hou, B., Xu, M., Nie, L.: A comprehensive survey on composed image retrieval. ACM Trans. Inf. Syst. (TOIS) (2025)","DOI":"10.1145\/3767328"},{"key":"29_CR35","doi-asserted-by":"crossref","unstructured":"Tang, Y., et al.: Reason-before-retrieve: one-stage reflective chain-of-thoughts for training-free zero-shot composed image retrieval. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14400\u201314410 (2025)","DOI":"10.1109\/CVPR52734.2025.01343"},{"key":"29_CR36","doi-asserted-by":"crossref","unstructured":"Thawakar, O., et al.: Beyond simple edits: composed video retrieval with dense modifications. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2025)","DOI":"10.1109\/ICCV51701.2025.01900"},{"key":"29_CR37","doi-asserted-by":"crossref","unstructured":"Thawakar, O., et al.: Composed video retrieval via enriched context and discriminative embeddings. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 26896\u201326906 (2024)","DOI":"10.1109\/CVPR52733.2024.02540"},{"key":"29_CR38","doi-asserted-by":"crossref","unstructured":"Ventura, L., Yang, A., Schmid, C., Varol, G.: CoVR: learning composed video retrieval from web video captions. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), vol. 38, pp. 5270\u20135279 (2024)","DOI":"10.1609\/aaai.v38i6.28334"},{"key":"29_CR39","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), pp. 6439\u20136448 (2019)","DOI":"10.1109\/CVPR.2019.00660"},{"key":"29_CR40","unstructured":"Wu, C., et\u00a0al.: Qwen-image technical report. arXiv preprint arXiv:2508.02324 (2025)"},{"key":"29_CR41","doi-asserted-by":"crossref","unstructured":"Wu, H., et al.: Fashion IQ: a new dataset towards retrieving images by natural language feedback. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11307\u201311317 (2021)","DOI":"10.1109\/CVPR46437.2021.01115"},{"issue":"4","key":"29_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3626235","volume":"56","author":"L Yang","year":"2023","unstructured":"Yang, L., et al.: Diffusion models: a comprehensive survey of methods and applications. ACM Comput. Surv. 56(4), 1\u201339 (2023)","journal-title":"ACM Comput. Surv."},{"key":"29_CR43","doi-asserted-by":"crossref","unstructured":"Yang, Z., Xue, D., Qian, S., Dong, W., Xu, C.: LDRE: LLM-based divergent reasoning and ensemble for zero-shot composed image retrieval. In: Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), pp. 80\u201390 (2024)","DOI":"10.1145\/3626772.3657740"},{"key":"29_CR44","doi-asserted-by":"crossref","unstructured":"Yang, Z., Pang, W., Yuan, Y.: XR: cross-modal agents for composed image retrieval. In: Proceedings of the ACM Web Conference 2026, pp. 2071\u20132082 (2026)","DOI":"10.1145\/3774904.3792276"},{"key":"29_CR45","unstructured":"Yao, S., et al.: ReAct: synergizing reasoning and acting in language models. In: Proceedings of the International Conference on Learning Representations (ICLR) (2023)"},{"key":"29_CR46","unstructured":"Yue, W., Qi, Z., Wu, Y., Sun, J., Wang, Y., Wang, S.: Learning fine-grained representations through textual token disentanglement in composed video retrieval. In: Proceedings of the International Conference on Learning Representations (ICLR), vol.\u00a03, p.\u00a04 (2025)"},{"key":"29_CR47","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. In: Proceedings of the International Conference on Learning Representations (ICLR) (2024)"},{"key":"29_CR48","unstructured":"Zhuang, Y., et al.: Toolchain*: efficient action space navigation in large language models with A* search. In: Proceedings of the International Conference on Learning Representations (ICLR) (2024)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37023-5_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T07:59:02Z","timestamp":1789027142000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37023-5_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370228","9783032370235"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37023-5_29","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":"11 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","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":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}