{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T16:51:59Z","timestamp":1782492719681,"version":"3.54.5"},"reference-count":48,"publisher":"Elsevier BV","issue":"1","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206252"],"award-info":[{"award-number":["62206252"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006407","name":"Henan Province Natural Science Foundation","doi-asserted-by":"publisher","award":["252300423339"],"award-info":[{"award-number":["252300423339"]}],"id":[{"id":"10.13039\/501100006407","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Processing & Management"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.ipm.2026.104985","type":"journal-article","created":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T13:30:13Z","timestamp":1781962213000},"page":"104985","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["Self-balanced information bottleneck for few-shot multimodal information extraction"],"prefix":"10.1016","volume":"64","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5033-5576","authenticated-orcid":false,"given":"Youwei","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6338-419X","authenticated-orcid":false,"given":"Kai","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3930-6081","authenticated-orcid":false,"given":"Qiwei","family":"Miao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinghao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.ipm.2026.104985_b1","unstructured":"Alemi, A. A., Fischer, I., Dillon, J. V., & Murphy, K. (2017). Deep variational information bottleneck. In Proceedings of the 5th international conference on learning representations."},{"key":"10.1016\/j.ipm.2026.104985_b2","doi-asserted-by":"crossref","first-page":"2875","DOI":"10.1109\/TMM.2025.3557634","article-title":"VideoDreamer: Customized multi-subject text-to-video generation with disen-mix finetuning on language-video foundation models","volume":"27","author":"Chen","year":"2025","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.ipm.2026.104985_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2026.113243","article-title":"GaitADIB: Adversarial disentangled information bottleneck network for unseen-view gait recognition","volume":"177","author":"Du","year":"2026","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.ipm.2026.104985_b4","doi-asserted-by":"crossref","unstructured":"Eberts, M., & Ulges, A. (2020). Span-based joint entity and relation extraction with transformer pre-training. vol. 325, In Proceedings of the 24th European conference on artificial intelligence (pp. 2006\u20132013).","DOI":"10.3233\/FAIA200321"},{"issue":"1","key":"10.1016\/j.ipm.2026.104985_b5","doi-asserted-by":"crossref","first-page":"561","DOI":"10.1109\/TCSVT.2023.3284474","article-title":"Towards bridged vision and language: Learning cross-modal knowledge representation for relation extraction","volume":"34","author":"Feng","year":"2024","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"4","key":"10.1016\/j.ipm.2026.104985_b6","doi-asserted-by":"crossref","first-page":"4579","DOI":"10.1109\/TCSVT.2025.3637231","article-title":"InfoBFR: Real-world blind face restoration via information bottleneck","volume":"36","author":"Gao","year":"2026","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.1016\/j.ipm.2026.104985_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112775","article-title":"EmoEEG: A transferable generalist framework for EEG emotion recognition via information bottleneck theory","volume":"172","author":"Gao","year":"2026","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.ipm.2026.104985_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107172","article-title":"SQGE: Support-query prototype guidance and enhancement for few-shot relational triple extraction","volume":"185","author":"Gao","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.ipm.2026.104985_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110779","article-title":"Few-shot relational triple extraction with hierarchical prototype optimization","volume":"156","author":"Gao","year":"2024","journal-title":"Pattern Recognition"},{"key":"10.1016\/j.ipm.2026.104985_b10","doi-asserted-by":"crossref","unstructured":"Gong, J., & Eldardiry, H. (2024). Few-shot relation extraction with hybrid visual evidence. In Proceedings of the 2024 joint international conference on computational linguistics (pp. 7232\u20137247).","DOI":"10.63317\/2kxdyhpu8jhf"},{"key":"10.1016\/j.ipm.2026.104985_b11","doi-asserted-by":"crossref","unstructured":"Guo, Q., Zhang, J., Wang, S., Tian, L., Kang, Z., Yan, B., & Xiao, W. (2025). Bridging Generative and Discriminative Learning: Few-shot relation extraction via two-stage knowledge-guided pre-training. In Proceedings of the 34th international joint conference on artificial intelligence (pp. 8068\u20138076).","DOI":"10.24963\/ijcai.2025\/897"},{"key":"10.1016\/j.ipm.2026.104985_b12","doi-asserted-by":"crossref","unstructured":"He, Y., Cai, D., Qian, S., Fang, Q., Wei, Y., & Xu, C. (2026). Multi-modal bipartite graph structure learning with information bottleneck for micro-video recommendation. In Proceedings of the ACM web conference 2026 (pp. 6876\u20136886).","DOI":"10.1145\/3774904.3792708"},{"issue":"12","key":"10.1016\/j.ipm.2026.104985_b13","doi-asserted-by":"crossref","first-page":"18357","DOI":"10.1109\/TNNLS.2023.3314807","article-title":"Template-free prompting for few-shot named entity recognition via semantic-enhanced contrastive learning","volume":"35","author":"He","year":"2024","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.ipm.2026.104985_b14","doi-asserted-by":"crossref","unstructured":"Hu, X., Chen, J., Liu, A., Meng, S., Wen, L., & Yu, P. S. (2023). Prompt Me Up: Unleashing the power of alignments for multimodal entity and relation extraction. In Proceedings of the 31st ACM international conference on multimedia (pp. 5185\u20135194).","DOI":"10.1145\/3581783.3611899"},{"issue":"8","key":"10.1016\/j.ipm.2026.104985_b15","doi-asserted-by":"crossref","first-page":"5325","DOI":"10.1109\/TPAMI.2024.3366349","article-title":"A survey on information bottleneck","volume":"46","author":"Hu","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"3","key":"10.1016\/j.ipm.2026.104985_b16","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2024.104033","article-title":"A knowledge-enhanced network for joint multimodal entity-relation extraction","volume":"62","author":"Huang","year":"2025","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104985_b17","doi-asserted-by":"crossref","unstructured":"Huang, S., Zhong, W., Cai, D., Wan, F., Wang, C., Wang, M., Qiao, M., & Xu, R. (2025). Empowering Self-Learning of LLMs: Inner knowledge explicitation as a catalyst. In Proceedings of the 39th association for the advancement of artificial intelligence (pp. 24150\u201324158).","DOI":"10.1609\/aaai.v39i23.34590"},{"key":"10.1016\/j.ipm.2026.104985_b18","unstructured":"Lei, S., Cheng, Z., Jia, K., & Tao, D. (2026). Revisiting LLM reasoning via information bottleneck. In Proceedings of the 14th international conference on learning representations."},{"issue":"3","key":"10.1016\/j.ipm.2026.104985_b19","doi-asserted-by":"crossref","first-page":"3708","DOI":"10.1109\/TVT.2024.3499947","article-title":"SiamTADT: A task-aware drone tracker for aerial autonomous vehicles","volume":"74","author":"Li","year":"2025","journal-title":"IEEE Transactions on Vehicular Technology"},{"key":"10.1016\/j.ipm.2026.104985_b20","doi-asserted-by":"crossref","unstructured":"Li, Q., Ji, C., Guo, S., Zhao, Y., Mao, Q., Wang, S., Wei, Y., & Li, J. (2024). Variational multi-modal hypergraph attention network for multi-modal relation extraction. In Proceedings of the 32nd ACM international conference on multimedia (pp. 5185\u20135194).","DOI":"10.24963\/ijcai.2024\/907"},{"key":"10.1016\/j.ipm.2026.104985_b21","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1109\/TMM.2025.3623509","article-title":"Learning compact representations with an information bottleneck for camouflaged object detection","volume":"28","author":"Li","year":"2026","journal-title":"IEEE Transactions on Multimedia"},{"issue":"2","key":"10.1016\/j.ipm.2026.104985_b22","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2025.104388","article-title":"CITR: Context-driven implicit triple reasoning for joint multimodal entity-relation extraction","volume":"63","author":"Liu","year":"2026","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104985_b23","unstructured":"Loshchilov, I., & Hutter, F. (2019). Decoupled weight decay regularization. In Proceedings of the 7th international conference on learning representations."},{"issue":"6","key":"10.1016\/j.ipm.2026.104985_b24","doi-asserted-by":"crossref","first-page":"5195","DOI":"10.1109\/TCSVT.2025.3527032","article-title":"Efficient multimodal selection for retrieval in knowledge-based visual question answering","volume":"35","author":"Luo","year":"2025","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"7","key":"10.1016\/j.ipm.2026.104985_b25","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2026.104799","article-title":"From perception to comprehension: A cognitive hierarchy for multimodal relation extraction","volume":"63","author":"Meng","year":"2026","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104985_b26","first-page":"140:1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"10.1016\/j.ipm.2026.104985_b27","doi-asserted-by":"crossref","unstructured":"Ren, F., Zhang, L., Zhao, X., Yin, S., Liu, S., & Li, B. (2022). A simple but effective bidirectional framework for relational triple extraction. In Proceedings of the 15th ACM international conference on web search and data mining (pp. 824\u2013832).","DOI":"10.1145\/3488560.3498409"},{"key":"10.1016\/j.ipm.2026.104985_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.122918","article-title":"Multi-modal semantics fusion model for domain relation extraction via information bottleneck","volume":"244","author":"Tian","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.ipm.2026.104985_b29","unstructured":"Tishby, N., Pereira, F. C., & Bialek, W. (1999). The information bottleneck method. In Proceedings of the 37th annual allerton conference on communication control computing (pp. 368\u2013377)."},{"key":"10.1016\/j.ipm.2026.104985_b30","doi-asserted-by":"crossref","unstructured":"Tishby, N., & Zaslavsky, N. (2015). Deep learning and the information bottleneck principle. In Proceedings of the 2015 IEEE information theory workshop (pp. 1\u20135).","DOI":"10.1109\/ITW.2015.7133169"},{"issue":"3","key":"10.1016\/j.ipm.2026.104985_b31","doi-asserted-by":"crossref","first-page":"1894","DOI":"10.1109\/TPAMI.2024.3511593","article-title":"JARVIS-1: Open-world multi-task agents with memory-augmented multimodal language models","volume":"47","author":"Wang","year":"2025","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.ipm.2026.104985_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107250","article-title":"Span-aware pre-trained network with deep information bottleneck for scientific entity relation extraction","volume":"186","author":"Wang","year":"2025","journal-title":"Neural Networks"},{"issue":"12","key":"10.1016\/j.ipm.2026.104985_b33","doi-asserted-by":"crossref","first-page":"9677","DOI":"10.1109\/TPAMI.2024.3420937","article-title":"Disentangled representation learning","volume":"46","author":"Wang","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.ipm.2026.104985_b34","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112504","article-title":"Joint multimodal entity-relation extraction based on temporal enhancement and similarity-gated attention","volume":"304","author":"Wang","year":"2024","journal-title":"Knowledge-Based Systems"},{"issue":"6","key":"10.1016\/j.ipm.2026.104985_b35","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2023.103511","article-title":"Deep purified feature mining model for joint named entity recognition and relation extraction","volume":"60","author":"Wang","year":"2023","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104985_b36","unstructured":"Wang, P., Yang, A., Men, R., Lin, J., Bai, S., Li, Z., Ma, J., Zhou, C., Zhou, J., & Yang, H. (2022). OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework. vol. 162, In Proceedings of the 39th international conference on machine learning (pp. 23318\u201323340)."},{"key":"10.1016\/j.ipm.2026.104985_b37","doi-asserted-by":"crossref","unstructured":"Wang, Y., Yu, B., Zhang, Y., Liu, T., Zhu, H., & Sun, L. (2020). TPLinker: Single-stage joint extraction of entities and relations through token pair linking. In Proceedings of the 28th international conference on computational linguistics (pp. 1572\u20131582).","DOI":"10.18653\/v1\/2020.coling-main.138"},{"key":"10.1016\/j.ipm.2026.104985_b38","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, J., Qi, L., & Shi, Y. (2025). Balanced Direction from Multifarious Choices: Arithmetic meta-learning for domain generalization. In Proceedings of the 42nd computer vision and pattern recognition (pp. 30577\u201330587).","DOI":"10.1109\/CVPR52734.2025.02847"},{"key":"10.1016\/j.ipm.2026.104985_b39","unstructured":"Wu, T., & Fischer, I. S. (2020). Phase transitions for the information bottleneck in representation learning. In Proceedings of the 8th international conference on learning representations."},{"key":"10.1016\/j.ipm.2026.104985_b40","doi-asserted-by":"crossref","unstructured":"Xu, X., Zhang, Y., Zhou, F., & Song, J. (2025). Improving multimodal social media popularity prediction via selective retrieval knowledge augmentation. In Proceedings of the 39th association for the advancement of artificial intelligence (pp. 932\u2013940).","DOI":"10.1609\/aaai.v39i1.32078"},{"key":"10.1016\/j.ipm.2026.104985_b41","doi-asserted-by":"crossref","unstructured":"Yuan, L., Cai, Y., & Huang, J. (2024). Few-shot joint multimodal entity-relation extraction via knowledge-enhanced cross-modal prompt model. In Proceedings of the 32nd ACM international conference on multimedia (pp. 8701\u20138710).","DOI":"10.1145\/3664647.3680717"},{"key":"10.1016\/j.ipm.2026.104985_b42","doi-asserted-by":"crossref","unstructured":"Yuan, L., Cai, Y., Wang, J., & Li, Q. (2023). Joint multimodal entity-relation extraction based on edge-enhanced graph alignment network and word-pair relation tagging. In Proceedings of the 37th AAAI conference on artificial intelligence (pp. 11051\u201311059).","DOI":"10.1609\/aaai.v37i9.26309"},{"issue":"1","key":"10.1016\/j.ipm.2026.104985_b43","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TKDE.2024.3485107","article-title":"A fine-grained network for joint multimodal entity-relation extraction","volume":"37","author":"Yuan","year":"2025","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.1016\/j.ipm.2026.104985_b44","doi-asserted-by":"crossref","unstructured":"Zhang, D., Wei, S., Li, S., Wu, H., Zhu, Q., & Zhou, G. (2021). Multi-modal graph fusion for named entity recognition with targeted Visual Guidance. In Proceedings of the 35th AAAI conference on artificial intelligence (pp. 14347\u201314355).","DOI":"10.1609\/aaai.v35i16.17687"},{"issue":"4","key":"10.1016\/j.ipm.2026.104985_b45","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2025.104129","article-title":"A multi-granularity in-context learning method for few-shot named entity recognition via knowledgeable parameters fine-tuning","volume":"62","author":"Zhao","year":"2025","journal-title":"Information Processing & Management"},{"issue":"3","key":"10.1016\/j.ipm.2026.104985_b46","doi-asserted-by":"crossref","first-page":"4971","DOI":"10.1109\/TNNLS.2024.3365858","article-title":"Few-shot relation extraction with automatically generated prompts","volume":"36","author":"Zhao","year":"2025","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.ipm.2026.104985_b47","doi-asserted-by":"crossref","unstructured":"Zheng, C., Feng, J., Fu, Z., Cai, Y., Li, Q., & Wang, T. (2021). Multimodal relation extraction with efficient graph alignment. In Proceedings of the 29th ACM international conference on multimedia (pp. 5298\u20135306).","DOI":"10.1145\/3474085.3476968"},{"key":"10.1016\/j.ipm.2026.104985_b48","doi-asserted-by":"crossref","first-page":"2520","DOI":"10.1109\/TMM.2020.3013398","article-title":"Object-aware multimodal named entity recognition in social media posts with adversarial learning","volume":"23","author":"Zheng","year":"2021","journal-title":"IEEE Transactions on Multimedia"}],"container-title":["Information Processing & Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457326003766?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457326003766?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,26]],"date-time":"2026-06-26T16:34:58Z","timestamp":1782491698000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0306457326003766"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":48,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2027,1]]}},"alternative-id":["S0306457326003766"],"URL":"https:\/\/doi.org\/10.1016\/j.ipm.2026.104985","relation":{},"ISSN":["0306-4573"],"issn-type":[{"value":"0306-4573","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Self-balanced information bottleneck for few-shot multimodal information extraction","name":"articletitle","label":"Article Title"},{"value":"Information Processing & Management","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ipm.2026.104985","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104985"}}