{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T07:16:13Z","timestamp":1783149373360,"version":"3.54.6"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"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":["U23A20318"],"award-info":[{"award-number":["U23A20318"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276195"],"award-info":[{"award-number":["62276195"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Fusion"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.inffus.2026.104514","type":"journal-article","created":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T16:25:07Z","timestamp":1780676707000},"page":"104514","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["BiCPF: Bi-conditional parallel-fusion network for composed image retrieval"],"prefix":"10.1016","volume":"136","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2296-6370","authenticated-orcid":false,"given":"Yong","family":"Luo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinrong","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingyu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daqing","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minjing","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengya","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiwei","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongjing","family":"Shan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.inffus.2026.104514_sbref0001","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6439","article-title":"Composing text and image for image retrieval-an empirical odyssey","author":"Vo","year":"2019"},{"key":"10.1016\/j.inffus.2026.104514_sbref0002","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.inffus.2017.01.003","article-title":"Information fusion in content based image retrieval: a comprehensive overview","volume":"37","author":"Piras","year":"2017","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104514_sbref0003","series-title":"International Conference on Machine Learning","first-page":"12888","article-title":"Blip: bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022"},{"key":"10.1016\/j.inffus.2026.104514_sbref0004","series-title":"International Conference on Machine Learning","first-page":"19730","article-title":"Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.inffus.2026.104514_sbref0005","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4959","article-title":"Conditioned and composed image retrieval combining and partially fine-tuning clip-based features","author":"Baldrati","year":"2022"},{"key":"10.1016\/j.inffus.2026.104514_sbref0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102544","article-title":"Cross-modal semantic aligning and neighbor-aware completing for robust text\u2013image person retrieval","volume":"112","author":"Gong","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104514_sbref0007","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102428","article-title":"Educross: dual adversarial bipartite hypergraph learning for cross-modal retrieval in multimodal educational slides","volume":"109","author":"Li","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104514_sbref0008","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2025.102943","article-title":"TVT-Transformer: A tactile-visual-textual fusion network for object recognition","volume":"118","author":"Li","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104514_sbref0009","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"6576","article-title":"Decomposing semantic shifts for composed image retrieval","volume":"38","author":"Yang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104514_sbref0010","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2024.3401006","article-title":"Set of diverse queries with uncertainty regularization for composed image retrieval","author":"Xu","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.inffus.2026.104514_sbref0011","series-title":"Proceedings of the Asian Conference on Computer Vision","first-page":"1741","article-title":"Dual-path multimodal optimal transport for composed image retrieval","author":"Yan","year":"2024"},{"key":"10.1016\/j.inffus.2026.104514_sbref0012","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"2991","article-title":"Data roaming and quality assessment for composed image retrieval","volume":"38","author":"Levy","year":"2024"},{"issue":"2","key":"10.1016\/j.inffus.2026.104514_sbref0013","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3699715","article-title":"LLM-enhanced composed image retrieval: an intent uncertainty-Aware linguistic-Visual dual channel matching model","volume":"43","author":"Ge","year":"2025","journal-title":"ACM Trans. Inf. Syst."},{"key":"10.1016\/j.inffus.2026.104514_sbref0014","doi-asserted-by":"crossref","first-page":"17612","DOI":"10.52202\/068431-1280","article-title":"Mind the gap: understanding the modality gap in multi-modal contrastive representation learning","volume":"35","author":"Liang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104514_sbref0015","article-title":"Enhancing generalization with multi-modal relations","author":"Wang","year":"2025","journal-title":"Inf. Fusion"},{"issue":"11","key":"10.1016\/j.inffus.2026.104514_bib0016","doi-asserted-by":"crossref","first-page":"6621","DOI":"10.1109\/TSMC.2024.3429345","article-title":"Heterogeneous window transformer for image denoising","volume":"54","author":"Tian","year":"2024","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"10.1016\/j.inffus.2026.104514_bib0017","doi-asserted-by":"crossref","DOI":"10.1109\/TCE.2025.3565318","article-title":"A dynamic transformer network for vehicle detection","author":"Tian","year":"2025","journal-title":"IEEE Trans. Consum. Electron."},{"key":"10.1016\/j.inffus.2026.104514_sbref0018","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1016\/j.inffus.2022.10.013","article-title":"TFUN: Trilinear fusion network for ternary image-text retrieval","volume":"91","author":"Xu","year":"2023","journal-title":"Inf. Fusion"},{"issue":"3","key":"10.1016\/j.inffus.2026.104514_sbref0019","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3617597","article-title":"Composed image retrieval using contrastive learning and task-oriented clip-based features","volume":"20","author":"Baldrati","year":"2023","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"10.1016\/j.inffus.2026.104514_sbref0020","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"5753","article-title":"Bi-directional training for composed image retrieval via text prompt learning","author":"Liu","year":"2024"},{"key":"10.1016\/j.inffus.2026.104514_bib0021","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"8384","article-title":"Cross-modal feature alignment and fusion for composed image retrieval","author":"Wan","year":"2024"},{"key":"10.1016\/j.inffus.2026.104514_sbref0022","series-title":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","first-page":"229","article-title":"Simple but effective raw-data level multimodal fusion for composed image retrieval","author":"Wen","year":"2024"},{"key":"10.1016\/j.inffus.2026.104514_bib0023","unstructured":"E. Dodds, J. Culpepper, S. Herdade, Y. Zhang, K. Boakye, Modality-agnostic attention fusion for visual search with text feedback, (2020). https:\/\/doi.org\/10.48550\/arXiv.2007.00145."},{"key":"10.1016\/j.inffus.2026.104514_sbref0024","series-title":"The Twelfth International Conference on Learning Representations","article-title":"Sentence-level prompts benefit composed image retrieval","author":"Xu","year":"2024"},{"key":"10.1016\/j.inffus.2026.104514_sbref0025","series-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"3260","article-title":"Self-distilled dynamic fusion network for language-based fashion retrieval","author":"Wu","year":"2024"},{"key":"10.1016\/j.inffus.2026.104514_sbref0026","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14105","article-title":"Fashionvlp: vision language transformer for fashion retrieval with feedback","author":"Goenka","year":"2022"},{"key":"10.1016\/j.inffus.2026.104514_sbref0027","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3001","article-title":"Image search with text feedback by visiolinguistic attention learning","author":"Chen","year":"2020"},{"key":"10.1016\/j.inffus.2026.104514_sbref0028","series-title":"2023 IEEE International Conference on Multimedia and Expo (ICME)","first-page":"108","article-title":"Visual-linguistic alignment and composition for image retrieval with text feedback","author":"Li","year":"2023"},{"key":"10.1016\/j.inffus.2026.104514_sbref0029","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.inffus.2026.104514_sbref0030","article-title":"Vilbert: pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104514_sbref0031","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104514_bib0032","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1109\/TIP.2025.3645630","article-title":"A cosine network for image super-Resolution","volume":"35","author":"Tian","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.inffus.2026.104514_sbref0033","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102319","article-title":"Diverse semantic information fusion for unsupervised person re-identification","volume":"107","author":"Hu","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104514_sbref0034","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"1228","article-title":"FashionERN: enhance-and-refine network for composed fashion image retrieval","volume":"38","author":"Chen","year":"2024"},{"key":"10.1016\/j.inffus.2026.104514_sbref0035","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia","first-page":"1632","article-title":"Improving composed image retrieval via contrastive learning with scaling positives and negatives","author":"Feng","year":"2024"},{"key":"10.1016\/j.inffus.2026.104514_sbref0036","series-title":"Proceedings of the 31st ACM International Conference on Multimedia","first-page":"915","article-title":"Target-guided composed image retrieval","author":"Wen","year":"2023"},{"key":"10.1016\/j.inffus.2026.104514_sbref0037","series-title":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","first-page":"2177","article-title":"Cala: complementary association learning for augmenting comoposed image retrieval","author":"Jiang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104514_sbref0038","series-title":"ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"PAIR: Complementarity-guided disentanglement for composed image retrieval","author":"Fu","year":"2025"},{"key":"10.1016\/j.inffus.2026.104514_sbref0039","series-title":"ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"1","article-title":"MEDIAN: Adaptive intermediate-grained aggregation network for composed image retrieval","author":"Huang","year":"2025"},{"key":"10.1016\/j.inffus.2026.104514_sbref0040","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"5101","article-title":"Encoder: entity mining and modification relation binding for composed image retrieval","volume":"39","author":"Li","year":"2025"},{"key":"10.1016\/j.inffus.2026.104514_sbref0041","series-title":"Proceedings of the 2025 International Conference on Multimedia Retrieval","first-page":"972","article-title":"Text-Guided attribute enhancement framework for composed image retrieval","author":"Ma","year":"2025"},{"key":"10.1016\/j.inffus.2026.104514_sbref0042","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"19628","article-title":"Learning with noisy triplet correspondence for composed image retrieval","author":"Li","year":"2025"},{"key":"10.1016\/j.inffus.2026.104514_sbref0043","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"3974","article-title":"CCIN: Compositional conflict identification and neutralization for composed image retrieval","author":"Tian","year":"2025"},{"key":"10.1016\/j.inffus.2026.104514_sbref0044","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"2125","article-title":"Image retrieval on real-life images with pre-trained vision-and-language models","author":"Liu","year":"2021"},{"key":"10.1016\/j.inffus.2026.104514_sbref0045","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11307","article-title":"Fashion iq: a new dataset towards retrieving images by natural language feedback","author":"Wu","year":"2021"},{"key":"10.1016\/j.inffus.2026.104514_sbref0046","series-title":"European Conference on Computer Vision","first-page":"663","article-title":"Automatic attribute discovery and characterization from noisy web data","author":"Berg","year":"2010"},{"key":"10.1016\/j.inffus.2026.104514_sbref0047","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19305","article-title":"Pic2word: mapping pictures to words for zero-shot composed image retrieval","author":"Saito","year":"2023"},{"key":"10.1016\/j.inffus.2026.104514_sbref0048","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"15338","article-title":"Zero-shot composed image retrieval with textual inversion","author":"Baldrati","year":"2023"},{"key":"10.1016\/j.inffus.2026.104514_sbref0049","series-title":"The Twelfth International Conference on Learning Representations","article-title":"Vision-by-language for training-free compositional image retrieval","author":"Karthik","year":"2024"},{"key":"10.1016\/j.inffus.2026.104514_sbref0050","series-title":"Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","first-page":"80","article-title":"Ldre: llm-based divergent reasoning and ensemble for zero-shot composed image retrieval","author":"Yang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104514_sbref0051","series-title":"Proceedings of the 32nd ACM International Conference on Multimedia","first-page":"1245","article-title":"Semantic editing increment benefits zero-shot composed image retrieval","author":"Yang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104514_sbref0052","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"14400","article-title":"Reason-before-retrieve: one-stage reflective chain-of-thoughts for training-free zero-shot composed image retrieval","author":"Tang","year":"2025"},{"key":"10.1016\/j.inffus.2026.104514_bib0053","unstructured":"Y. Liu, J. Yao, Y. Zhang, Y. Wang, W. Xie, Zero-shot composed text-image retrieval, (2023). https:\/\/doi.org\/10.48550\/arXiv.2306.07272."},{"issue":"5","key":"10.1016\/j.inffus.2026.104514_sbref0054","doi-asserted-by":"crossref","first-page":"3665","DOI":"10.1109\/TPAMI.2023.3346434","article-title":"Self-training boosted multi-factor matching network for composed image retrieval","volume":"46","author":"Wen","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"10.1016\/j.inffus.2026.104514_sbref0055","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3767328","article-title":"A comprehensive survey on composed image retrieval","volume":"44","author":"Song","year":"2025","journal-title":"ACM Transactions on Information Systems"}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526003933?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526003933?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T06:30:14Z","timestamp":1783146614000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1566253526003933"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":55,"alternative-id":["S1566253526003933"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104514","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"BiCPF: Bi-conditional parallel-fusion network for composed image retrieval","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104514","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104514"}}