{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T13:09:43Z","timestamp":1765544983188,"version":"3.40.3"},"publisher-location":"Cham","reference-count":59,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031728471"},{"type":"electronic","value":"9783031728488"}],"license":[{"start":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T00:00:00Z","timestamp":1732838400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T00:00:00Z","timestamp":1732838400000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72848-8_23","type":"book-chapter","created":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T13:36:58Z","timestamp":1732801018000},"page":"391-408","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multimodal Label Relevance Ranking via\u00a0Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0787-511X","authenticated-orcid":false,"given":"Taian","family":"Guo","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2441-2861","authenticated-orcid":false,"given":"Taolin","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1035-1499","authenticated-orcid":false,"given":"Haoqian","family":"Wu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4211-7479","authenticated-orcid":false,"given":"Hanjun","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3663-0149","authenticated-orcid":false,"given":"Ruizhi","family":"Qiao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8132-9083","authenticated-orcid":false,"given":"Xing","family":"Sun","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,29]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Ai, Q., Bi, K., Guo, J., Croft, W.B.: Learning a deep listwise context model for ranking refinement. In: The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 135\u2013144 (2018)","DOI":"10.1145\/3209978.3209985"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Ai, Q., Wang, X., Bruch, S., Golbandi, N., Bendersky, M., Najork, M.: Learning groupwise multivariate scoring functions using deep neural networks. In: Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval, pp. 85\u201392 (2019)","DOI":"10.1145\/3341981.3344218"},{"key":"23_CR3","unstructured":"Bao, H., et al.: VLMo: unified vision-language pre-training with mixture-of-modality-experts. In: Advances in Neural Information Processing Systems, vol. 35, pp. 32897\u201332912 (2022)"},{"key":"23_CR4","unstructured":"Barto, A., Duff, M.: Monte Carlo matrix inversion and reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 6 (1993)"},{"key":"23_CR5","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1007\/11871842_53","volume-title":"Machine Learning: ECML 2006","author":"K Brinker","year":"2006","unstructured":"Brinker, K., H\u00fcllermeier, E.: Case-based label ranking. In: F\u00fcrnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS (LNAI), vol. 4212, pp. 566\u2013573. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11871842_53"},{"key":"23_CR6","unstructured":"Brinker, K., H\u00fcllermeier, E.: Case-based multilabel ranking. In: Proceedings of the 20th International Joint Conference on Artificial Intelligence, pp. 702\u2013707 (2007)"},{"issue":"23\u2013581","key":"23_CR7","first-page":"81","volume":"11","author":"CJ Burges","year":"2010","unstructured":"Burges, C.J.: From ranknet to lambdarank to lambdamart: an overview. Learning 11(23\u2013581), 81 (2010)","journal-title":"Learning"},{"key":"23_CR8","doi-asserted-by":"publisher","unstructured":"Buyl, M., Missault, P., Sondag, P.A.: Rankformer: listwise learning-to-rank using listwide labels. In: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2023, pp. 3762\u20133773. Association for Computing Machinery (2023). https:\/\/doi.org\/10.1145\/3580305.3599892","DOI":"10.1145\/3580305.3599892"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Cao, Z., Qin, T., Liu, T.Y., Tsai, M.F., Li, H.: Learning to rank: from pairwise approach to listwise approach. In: Proceedings of the 24th International Conference on Machine Learning, pp. 129\u2013136 (2007)","DOI":"10.1145\/1273496.1273513"},{"key":"23_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-030-58577-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y-C Chen","year":"2020","unstructured":"Chen, Y.-C., et al.: UNITER: UNiversal image-TExt representation learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12375, pp. 104\u2013120. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58577-8_7"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Cheng, W., H\u00fchn, J., H\u00fcllermeier, E.: Decision tree and instance-based learning for label ranking. In: Proceedings of the 26th Annual International Conference on Machine Learning, pp. 161\u2013168 (2009)","DOI":"10.1145\/1553374.1553395"},{"key":"23_CR12","unstructured":"Cheng, W., H\u00fcllermeier, E.: Instance-based label ranking using the mallows model. In: ECCBR Workshops, pp. 143\u2013157 (2008)"},{"key":"23_CR13","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1007\/11776420_44","volume-title":"Learning Theory","author":"D Cossock","year":"2006","unstructured":"Cossock, D., Zhang, T.: Subset ranking using regression. In: Lugosi, G., Simon, H.U. (eds.) COLT 2006. LNCS (LNAI), vol. 4005, pp. 605\u2013619. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11776420_44"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Crammer, K., Singer, Y.: Pranking with ranking. In: Advances in Neural Information Processing Systems, vol. 14 (2001)","DOI":"10.7551\/mitpress\/1120.003.0087"},{"key":"23_CR15","unstructured":"Dekel, O., Singer, Y., Manning, C.D.: Log-linear models for label ranking. In: Advances in Neural Information Processing Systems, vol. 16 (2003)"},{"key":"23_CR16","unstructured":"Dery, L., Shmueli, E.: Improving label ranking ensembles using boosting techniques. arXiv preprint arXiv:2001.07744 (2020)"},{"key":"23_CR17","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16 \\times 16$$ words: transformers for image recognition at scale. In: ICLR 2021: The Ninth International Conference on Learning Representations (2021)"},{"key":"23_CR18","unstructured":"Fotakis, D., Kalavasis, A., Kontonis, V., Tzamos, C.: Linear label ranking with bounded noise. In: Advances in Neural Information Processing Systems, vol. 35, pp. 15642\u201315656 (2022)"},{"key":"23_CR19","unstructured":"Fotakis, D., Kalavasis, A., Psaroudaki, E.: Label ranking through nonparametric regression. In: International Conference on Machine Learning, pp. 6622\u20136659. PMLR (2022)"},{"key":"23_CR20","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/s10994-008-5064-8","volume":"73","author":"J F\u00fcrnkranz","year":"2008","unstructured":"F\u00fcrnkranz, J., H\u00fcllermeier, E., Loza Menc\u00eda, E., Brinker, K.: Multilabel classification via calibrated label ranking. Mach. Learn. 73, 133\u2013153 (2008)","journal-title":"Mach. Learn."},{"key":"23_CR21","unstructured":"Garg, S., Wu, Y., Balakrishnan, S., Lipton, Z.: A unified view of label shift estimation. In: Advances in Neural Information Processing Systems, vol. 33, pp. 3290\u20133300 (2020)"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Har-Peled, S., Roth, D., Zimak, D.: Constraint classification for multiclass classification and ranking. In: Advances in Neural Information Processing Systems, vol. 15 (2002)","DOI":"10.1007\/3-540-36169-3_29"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"He, S., et al.: Open-vocabulary multi-label classification via multi-modal knowledge transfer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 808\u2013816 (2023)","DOI":"10.1609\/aaai.v37i1.25159"},{"key":"23_CR24","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1007\/978-3-030-58548-8_41","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Q Huang","year":"2020","unstructured":"Huang, Q., Xiong, Yu., Rao, A., Wang, J., Lin, D.: MovieNet: a holistic dataset for movie understanding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12349, pp. 709\u2013727. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58548-8_41"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Huang, Z., Zeng, Z., Huang, Y., Liu, B., Fu, D., Fu, J.: Seeing out of the box: end-to-end pre-training for vision-language representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12976\u201312985 (2021)","DOI":"10.1109\/CVPR46437.2021.01278"},{"issue":"16\u201317","key":"23_CR26","doi-asserted-by":"publisher","first-page":"1897","DOI":"10.1016\/j.artint.2008.08.002","volume":"172","author":"E H\u00fcllermeier","year":"2008","unstructured":"H\u00fcllermeier, E., F\u00fcrnkranz, J., Cheng, W., Brinker, K.: Label ranking by learning pairwise preferences. Artif. Intell. 172(16\u201317), 1897\u20131916 (2008)","journal-title":"Artif. Intell."},{"key":"23_CR27","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Kanehira, A., Harada, T.: Multi-label ranking from positive and unlabeled data. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5138\u20135146 (2016)","DOI":"10.1109\/CVPR.2016.555"},{"key":"23_CR29","unstructured":"Korba, A., Garcia, A., d\u2019Alch\u00e9 Buc, F.: A structured prediction approach for label ranking. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"23_CR30","unstructured":"Kumar, A., Liang, P.S., Ma, T.: Verified uncertainty calibration. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"23_CR31","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1007\/978-3-030-46133-1_14","volume-title":"ECML PKDD 2019","author":"C Li","year":"2020","unstructured":"Li, C., Pavlu, V., Aslam, J., Wang, B., Qin, K.: Learning to calibrate and rerank multi-label predictions. In: Brefeld, U., Fromont, E., Hotho, A., Knobbe, A., Maathuis, M., Robardet, C. (eds.) ECML PKDD 2019. LNCS, vol. 11908, pp. 220\u2013236. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-46133-1_14"},{"key":"23_CR32","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"23_CR33","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"23_CR34","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. In: Advances in Neural Information Processing Systems, vol. 34, pp. 9694\u20139705 (2021)"},{"key":"23_CR35","unstructured":"Li, P., Wu, Q., Burges, C.: MCRank: learning to rank using multiple classification and gradient boosting. In: Advances in Neural Information Processing Systems, vol. 20 (2007)"},{"key":"23_CR36","doi-asserted-by":"crossref","unstructured":"Li, W., et al.: Unimo: towards unified-modal understanding and generation via cross-modal contrastive learning. arXiv preprint arXiv:2012.15409 (2020)","DOI":"10.18653\/v1\/2021.acl-long.202"},{"key":"23_CR37","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"23_CR38","doi-asserted-by":"crossref","unstructured":"Liu, T.Y., et\u00a0al.: Learning to rank for information retrieval. Found. Trends\u00ae Inf. Retrieval 3(3), 225\u2013331 (2009)","DOI":"10.1561\/1500000016"},{"key":"23_CR39","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"23_CR40","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/978-3-031-20053-3_23","volume-title":"ECCV 2022","author":"Z Liu","year":"2022","unstructured":"Liu, Z., Shen, Z., Long, Y., Xing, E., Cheng, K.T., Leichner, C.: Data-free neural architecture search via recursive label calibration. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13684, pp. 391\u2013406. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20053-3_23"},{"key":"23_CR41","unstructured":"Lu, J., Batra, D., Parikh, D., Lee, S.: VilBERT: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"23_CR42","unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"23_CR43","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. In: Advances in Neural Information Processing Systems, vol. 35, pp. 27730\u201327744 (2022)"},{"key":"23_CR44","doi-asserted-by":"crossref","unstructured":"Pang, L., Xu, J., Ai, Q., Lan, Y., Cheng, X., Wen, J.: SetRank: learning a permutation-invariant ranking model for information retrieval. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 499\u2013508 (2020)","DOI":"10.1145\/3397271.3401104"},{"key":"23_CR45","doi-asserted-by":"crossref","unstructured":"Pei, C., et\u00a0al.: Personalized re-ranking for recommendation. In: Proceedings of the 13th ACM Conference on Recommender Systems, pp. 3\u201311 (2019)","DOI":"10.1145\/3298689.3347000"},{"key":"23_CR46","unstructured":"Qin, T., Liu, T.: Introducing LETOR 4.0 datasets. CoRR abs\/1306.2597 (2013). http:\/\/arxiv.org\/abs\/1306.2597"},{"key":"23_CR47","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML 2021: 38th International Conference on Machine Learning, pp. 8748\u20138763 (2021)"},{"key":"23_CR48","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: International Conference on Machine Learning, pp. 1889\u20131897. PMLR (2015)"},{"key":"23_CR49","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"23_CR50","unstructured":"Shalev-Shwartz, S., Singer, Y.: Efficient learning of label ranking by soft projections onto polyhedra (2006)"},{"key":"23_CR51","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. In: International Conference on Machine Learning, pp. 387\u2013395. PMLR (2014)"},{"key":"23_CR52","unstructured":"Touvron, H., et\u00a0al.: Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"23_CR53","unstructured":"Watkins, C.J.C.H.: Learning from delayed rewards (1989)"},{"key":"23_CR54","doi-asserted-by":"crossref","unstructured":"Xia, F., Liu, T.Y., Wang, J., Zhang, W., Li, H.: Listwise approach to learning to rank: theory and algorithm. In: Proceedings of the 25th International Conference on Machine Learning, pp. 1192\u20131199 (2008)","DOI":"10.1145\/1390156.1390306"},{"key":"23_CR55","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Vision-language pre-training with triple contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15671\u201315680 (2022)","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"23_CR56","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: Coca: contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917 (2022)"},{"key":"23_CR57","unstructured":"Zeng, Y., Zhang, X., Li, H.: Multi-grained vision language pre-training: aligning texts with visual concepts. arXiv preprint arXiv:2111.08276 (2021)"},{"key":"23_CR58","unstructured":"Zhang, Y., et\u00a0al.: Recognize anything: a strong image tagging model. arXiv preprint arXiv:2306.03514 (2023)"},{"key":"23_CR59","doi-asserted-by":"crossref","unstructured":"Zhuang, T., Ou, W., Wang, Z.: Globally optimized mutual influence aware ranking in e-commerce search. arXiv preprint arXiv:1805.08524 (2018)","DOI":"10.24963\/ijcai.2018\/518"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72848-8_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T14:11:37Z","timestamp":1732803097000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72848-8_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,29]]},"ISBN":["9783031728471","9783031728488"],"references-count":59,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72848-8_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,29]]},"assertion":[{"value":"29 November 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","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":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}