{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T22:07:40Z","timestamp":1780956460617,"version":"3.54.1"},"reference-count":51,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100005234","name":"Central China Normal University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005234","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2025M781597"],"award-info":[{"award-number":["2025M781597"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113724","type":"journal-article","created":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T06:29:51Z","timestamp":1776493791000},"page":"113724","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PC","title":["BenchCIR: Benchmarking robustness in composed image retrieval across modalities"],"prefix":"10.1016","volume":"179","author":[{"given":"Shitong","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qilei","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaogang","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weitong","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philip","family":"Torr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jindong","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113724_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109519","article-title":"MEP-3M: A large-scale multi-modal E-commerce product dataset","volume":"140","author":"Liu","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113724_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111781","article-title":"Prototype-guided text-based person search on rich Chinese descriptions","volume":"169","author":"Wu","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113724_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.109058","article-title":"Mitigating the effect of dataset shift in clustering","volume":"134","author":"Maldonado","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113724_b4","unstructured":"H. Wu, Y. Gao, X. Guo, Z. Al-Halah, S. Rennie, K. Grauman, R. Feris, The Fashion IQ Dataset: Retrieving Images by Combining Side Information and Relative Natural Language Feedback, in: CVPR, 2021."},{"key":"10.1016\/j.patcog.2026.113724_b5","doi-asserted-by":"crossref","unstructured":"Z. Liu, C. Rodriguez-Opazo, D. Teney, S. Gould, Image retrieval on real-life images with pre-trained vision-and-language models, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 2125\u20132134.","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"10.1016\/j.patcog.2026.113724_b6","doi-asserted-by":"crossref","unstructured":"N. Vo, L. Jiang, C. Sun, K. Murphy, L.-J. Li, L. Fei-Fei, J. Hays, Composing text and image for image retrieval-an empirical odyssey, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 6439\u20136448.","DOI":"10.1109\/CVPR.2019.00660"},{"key":"10.1016\/j.patcog.2026.113724_b7","series-title":"Artemis: Attention-based retrieval with text-explicit matching and implicit similarity","author":"Delmas","year":"2022"},{"key":"10.1016\/j.patcog.2026.113724_b8","doi-asserted-by":"crossref","unstructured":"A. Baldrati, M. Bertini, T. Uricchio, A. Del Bimbo, Effective conditioned and composed image retrieval combining CLIP-based features, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 21466\u201321474.","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"10.1016\/j.patcog.2026.113724_b9","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.patcog.2026.113724_b10","unstructured":"Y. bai, X. Xu, Y. Liu, S. Khan, F. Khan, W. Zuo, R.S.M. Goh, C.-M. Feng, Sentence-level Prompts Benefit Composed Image Retrieval, in: The Twelfth International Conference on Learning Representations, 2024."},{"key":"10.1016\/j.patcog.2026.113724_b11","series-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.patcog.2026.113724_b12","doi-asserted-by":"crossref","first-page":"8346","DOI":"10.1109\/TMM.2023.3235495","article-title":"Multi-modal transformer with global-local alignment for composed query image retrieval","volume":"25","author":"Xu","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.113724_b13","doi-asserted-by":"crossref","first-page":"9936","DOI":"10.1109\/TMM.2024.3417694","article-title":"Align and retrieve: Composition and decomposition learning in image retrieval with text feedback","volume":"26","author":"Xu","year":"2024","journal-title":"IEEE Trans. Multimed."},{"issue":"3","key":"10.1016\/j.patcog.2026.113724_b14","doi-asserted-by":"crossref","first-page":"5509","DOI":"10.1109\/TNNLS.2024.3381347","article-title":"Geometric matching for cross-modal retrieval","volume":"36","author":"Wang","year":"2024","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"issue":"10","key":"10.1016\/j.patcog.2026.113724_b15","doi-asserted-by":"crossref","first-page":"10494","DOI":"10.1109\/TCSVT.2024.3401006","article-title":"Set of diverse queries with uncertainty regularization for composed image retrieval","volume":"34","author":"Xu","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.113724_b16","series-title":"ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1685","article-title":"Multi-order adversarial representation learning for composed query image retrieval","author":"Fu","year":"2021"},{"key":"10.1016\/j.patcog.2026.113724_b17","doi-asserted-by":"crossref","unstructured":"S. Li, C. He, X. Liu, et al., Learning with Noisy Triplet Correspondence for Composed Image Retrieval, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2025, pp. 19628\u201319637.","DOI":"10.1109\/CVPR52734.2025.01828"},{"key":"10.1016\/j.patcog.2026.113724_b18","series-title":"CompoDiff: Versatile composed image retrieval with latent diffusion","author":"Gu","year":"2023"},{"key":"10.1016\/j.patcog.2026.113724_b19","doi-asserted-by":"crossref","unstructured":"L. Wang, W. Ao, V.N. Boddeti, et al., Generative zero-shot composed image retrieval, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2025, pp. 29690\u201329700.","DOI":"10.1109\/CVPR52734.2025.02764"},{"key":"10.1016\/j.patcog.2026.113724_b20","first-page":"2991","article-title":"Data roaming and quality assessment for composed image retrieval","volume":"vol. 38","author":"Levy","year":"2024"},{"key":"10.1016\/j.patcog.2026.113724_b21","first-page":"5270","article-title":"Covr: Learning composed video retrieval from web video captions","volume":"vol. 38","author":"Ventura","year":"2024"},{"key":"10.1016\/j.patcog.2026.113724_b22","unstructured":"D. Hendrycks, T. Dietterich, Benchmarking Neural Network Robustness to Common Corruptions and Perturbations, in: Proceedings of the International Conference on Learning Representations, 2019."},{"key":"10.1016\/j.patcog.2026.113724_b23","series-title":"Robustbench: a standardized adversarial robustness benchmark","author":"Croce","year":"2020"},{"key":"10.1016\/j.patcog.2026.113724_b24","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111299","article-title":"Real face foundation representation learning for generalized deepfake detection","volume":"161","author":"Shi","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113724_b25","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111497","article-title":"Guiding prototype networks with label semantics for few-shot text classification","volume":"164","author":"Liu","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113724_b26","series-title":"A closer look at the robustness of vision-and-language pre-trained models","author":"Li","year":"2020"},{"key":"10.1016\/j.patcog.2026.113724_b27","first-page":"34405","article-title":"Robustness analysis of video-language models against visual and language perturbations","volume":"35","author":"Chantry","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113724_b28","series-title":"Foil it! find one mismatch between image and language caption","author":"Shekhar","year":"2017"},{"key":"10.1016\/j.patcog.2026.113724_b29","doi-asserted-by":"crossref","unstructured":"J. Johnson, B. Hariharan, L. Van Der Maaten, L. Fei-Fei, C. Lawrence Zitnick, R. Girshick, Clevr: A diagnostic dataset for compositional language and elementary visual reasoning, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 2901\u20132910.","DOI":"10.1109\/CVPR.2017.215"},{"key":"10.1016\/j.patcog.2026.113724_b30","doi-asserted-by":"crossref","unstructured":"T. Thrush, R. Jiang, M. Bartolo, A. Singh, A. Williams, D. Kiela, C. Ross, Winoground: Probing vision and language models for visio-linguistic compositionality, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 5238\u20135248.","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"10.1016\/j.patcog.2026.113724_b31","doi-asserted-by":"crossref","unstructured":"X. Han, Z. Wu, P.X. Huang, X. Zhang, M. Zhu, Y. Li, Y. Zhao, L.S. Davis, Automatic spatially-aware fashion concept discovery, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 1463\u20131471.","DOI":"10.1109\/ICCV.2017.163"},{"key":"10.1016\/j.patcog.2026.113724_b32","series-title":"Pic2word: Mapping pictures to words for zero-shot composed image retrieval","author":"Saito","year":"2023"},{"issue":"8","key":"10.1016\/j.patcog.2026.113724_b33","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"10.1016\/j.patcog.2026.113724_b34","series-title":"Zero-shot composed image retrieval with textual inversion","author":"Baldrati","year":"2023"},{"key":"10.1016\/j.patcog.2026.113724_b35","series-title":"Modality-agnostic attention fusion for visual search with text feedback","author":"Dodds","year":"2020"},{"key":"10.1016\/j.patcog.2026.113724_b36","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XXX 16","first-page":"121","article-title":"Oscar: Object-semantics aligned pre-training for vision-language tasks","author":"Li","year":"2020"},{"key":"10.1016\/j.patcog.2026.113724_b37","series-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"10.1016\/j.patcog.2026.113724_b38","series-title":"Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXV","first-page":"634","article-title":"FashionViL: Fashion-focused vision-and-language representation learning","author":"Han","year":"2022"},{"key":"10.1016\/j.patcog.2026.113724_b39","doi-asserted-by":"crossref","unstructured":"Z. Liu, W. Sun, Y. Hong, D. Teney, S. Gould, Bi-Directional Training for Composed Image Retrieval via Text Prompt Learning, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, WACV, 2024, pp. 5753\u20135762.","DOI":"10.1109\/WACV57701.2024.00565"},{"key":"10.1016\/j.patcog.2026.113724_b40","unstructured":"J. Li, D. Li, C. Xiong, S. Hoi, BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation, in: ICML, 2022."},{"key":"10.1016\/j.patcog.2026.113724_b41","series-title":"Vlm2vec: Training vision-language models for massive multimodal embedding tasks","author":"Jiang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113724_b42","series-title":"Qwen technical report","author":"Bai","year":"2023"},{"key":"10.1016\/j.patcog.2026.113724_b43","series-title":"Neural Information Processing: 26th International Conference, ICONIP 2019, Sydney, NSW, Australia, December 12\u201315, 2019, Proceedings, Part III 26","first-page":"235","article-title":"Models in the wild: On corruption robustness of neural nlp systems","author":"Rychalska","year":"2019"},{"key":"10.1016\/j.patcog.2026.113724_b44","series-title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection","author":"Liu","year":"2023"},{"key":"10.1016\/j.patcog.2026.113724_b45","series-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"10.1016\/j.patcog.2026.113724_b46","series-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2021"},{"key":"10.1016\/j.patcog.2026.113724_b47","doi-asserted-by":"crossref","unstructured":"Y. Chen, S. Gong, L. Bazzani, Image search with text feedback by visiolinguistic attention learning, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 3001\u20133011.","DOI":"10.1109\/CVPR42600.2020.00307"},{"key":"10.1016\/j.patcog.2026.113724_b48","doi-asserted-by":"crossref","unstructured":"S. Lee, D. Kim, B. Han, Cosmo: Content-style modulation for image retrieval with text feedback, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 802\u2013812.","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"10.1016\/j.patcog.2026.113724_b49","first-page":"2071","article-title":"Vision transformers are robust learners","volume":"vol. 36","author":"Paul","year":"2022"},{"key":"10.1016\/j.patcog.2026.113724_b50","series-title":"Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.patcog.2026.113724_b51","doi-asserted-by":"crossref","unstructured":"A. Neculai, Y. Chen, Z. Akata, Probabilistic compositional embeddings for multimodal image retrieval, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 4547\u20134557.","DOI":"10.1109\/CVPRW56347.2022.00501"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326006898?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326006898?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T21:53:41Z","timestamp":1780955621000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326006898"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":51,"alternative-id":["S0031320326006898"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113724","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"BenchCIR: Benchmarking robustness in composed image retrieval across modalities","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113724","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":"113724"}}