{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,16]],"date-time":"2026-08-16T19:25:53Z","timestamp":1786908353173,"version":"build-2736575974"},"reference-count":45,"publisher":"Elsevier BV","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":["62476069"],"award-info":[{"award-number":["62476069"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Displays"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.displa.2026.103647","type":"journal-article","created":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T15:41:04Z","timestamp":1785944464000},"page":"103647","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P1","title":["MAIC: Multimodal Alignment at Instance and Cluster levels for vision\u2013language data pruning"],"prefix":"10.1016","volume":"96","author":[{"given":"Zhaopan","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziheng","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wangbo","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengfei","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojiang","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongxun","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.displa.2026.103647_b1","doi-asserted-by":"crossref","unstructured":"Y. Goyal, T. Khot, D. Summers-Stay, D. Batra, D. Parikh, Making the v in vqa matter: Elevating the role of image understanding in visual question answering, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 6904\u20136913.","DOI":"10.1109\/CVPR.2017.670"},{"key":"10.1016\/j.displa.2026.103647_b2","doi-asserted-by":"crossref","DOI":"10.1016\/j.displa.2024.102712","article-title":"Enhanced ADHD detection: Frequency information embedded in a visual-language framework","volume":"83","author":"Hu","year":"2024","journal-title":"Displays"},{"key":"10.1016\/j.displa.2026.103647_b3","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.displa.2026.103647_b4","doi-asserted-by":"crossref","unstructured":"B.A. Plummer, L. Wang, C.M. Cervantes, J.C. Caicedo, J. Hockenmaier, S. Lazebnik, Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models, in: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 2641\u20132649.","DOI":"10.1109\/ICCV.2015.303"},{"key":"10.1016\/j.displa.2026.103647_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.displa.2024.102773","article-title":"Fusing differentiable rendering and language\u2013image contrastive learning for superior zero-shot point cloud classification","volume":"84","author":"Xie","year":"2024","journal-title":"Displays"},{"key":"10.1016\/j.displa.2026.103647_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.displa.2024.102710","article-title":"BVA-Transformer: Image-text multimodal classification and dialogue model architecture based on blip and visual attention mechanism","volume":"83","author":"Zhang","year":"2024","journal-title":"Displays"},{"key":"10.1016\/j.displa.2026.103647_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.displa.2025.103042","article-title":"CLIPFusion: Infrared and visible image fusion network based on image\u2013text large model and adaptive learning","volume":"89","author":"Sun","year":"2025","journal-title":"Displays"},{"key":"10.1016\/j.displa.2026.103647_b8","doi-asserted-by":"crossref","unstructured":"L.H. Li, H. You, Z. Wang, A. Zareian, S.-F. Chang, K.-W. Chang, Unsupervised vision-and-language pre-training without parallel images and captions, in: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2021, pp. 5339\u20135350.","DOI":"10.18653\/v1\/2021.naacl-main.420"},{"key":"10.1016\/j.displa.2026.103647_b9","doi-asserted-by":"crossref","unstructured":"P. Sharma, N. Ding, S. Goodman, R. Soricut, Conceptual captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning, in: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2018, pp. 2556\u20132565.","DOI":"10.18653\/v1\/P18-1238"},{"key":"10.1016\/j.displa.2026.103647_b10","doi-asserted-by":"crossref","unstructured":"S. Changpinyo, P. Sharma, N. Ding, R. Soricut, Conceptual 12m: Pushing web-scale image-text pre-training to recognize long-tail visual concepts, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 3558\u20133568.","DOI":"10.1109\/CVPR46437.2021.00356"},{"issue":"2","key":"10.1016\/j.displa.2026.103647_b11","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1145\/2812802","article-title":"YFCC100M: The new data in multimedia research","volume":"59","author":"Thomee","year":"2016","journal-title":"Commun. ACM"},{"key":"10.1016\/j.displa.2026.103647_b12","series-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021"},{"key":"10.1016\/j.displa.2026.103647_b13","series-title":"SemDeDup: Data-efficient learning at web-scale through semantic deduplication","author":"Abbas","year":"2023"},{"key":"10.1016\/j.displa.2026.103647_b14","doi-asserted-by":"crossref","unstructured":"A.J. Wang, K.Q. Lin, D.J. Zhang, S.W. Lei, M.Z. Shou, Too Large; Data Reduction for Vision-Language Pre-Training, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023.","DOI":"10.1109\/ICCV51070.2023.00292"},{"key":"10.1016\/j.displa.2026.103647_b15","article-title":"Noise-robust vision-language pre-training with positive-negative learning","author":"Huang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.displa.2026.103647_b16","doi-asserted-by":"crossref","unstructured":"J. Hessel, A. Holtzman, M. Forbes, R. Le Bras, Y. Choi, Clipscore: A reference-free evaluation metric for image captioning, in: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021, pp. 7514\u20137528.","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"10.1016\/j.displa.2026.103647_b17","doi-asserted-by":"crossref","unstructured":"Q. Yu, Q. Sun, X. Zhang, Y. Cui, F. Zhang, Y. Cao, X. Wang, J. Liu, Capsfusion: Rethinking image-text data at scale, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 14022\u201314032.","DOI":"10.1109\/CVPR52733.2024.01330"},{"key":"10.1016\/j.displa.2026.103647_b18","unstructured":"D. Zhu, X. Shen, X. Li, M. Elhoseiny, et al., Minigpt-4: Enhancing vision-language understanding with advanced large language models, in: International Conference on Learning Representations, Vol. 2024, 2024, pp. 18378\u201318394."},{"key":"10.1016\/j.displa.2026.103647_b19","doi-asserted-by":"crossref","unstructured":"Y. Zeng, Q. Jin, T. Bao, W. Li, Multi-modal knowledge hypergraph for diverse image retrieval, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37, 2023, pp. 3376\u20133383.","DOI":"10.1609\/aaai.v37i3.25445"},{"key":"10.1016\/j.displa.2026.103647_b20","unstructured":"J. Robinson, C.-Y. Chuang, S. Sra, S. Jegelka, Contrastive Learning with Hard Negative Samples, in: International Conference on Learning Representations, ICLR, 2021."},{"key":"10.1016\/j.displa.2026.103647_b21","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.displa.2026.103647_b22","article-title":"Improving multimodal datasets with image captioning","volume":"36","author":"Nguyen","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.displa.2026.103647_b23","doi-asserted-by":"crossref","unstructured":"A. Mahmoud, M. Elhoushi, A. Abbas, Y. Yang, N. Ardalani, H. Leather, A.S. Morcos, Sieve: Multimodal dataset pruning using image captioning models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 22423\u201322432.","DOI":"10.1109\/CVPR52733.2024.02116"},{"key":"10.1016\/j.displa.2026.103647_b24","unstructured":"P. Maini, S. Goyal, Z. Lipton, Z. Kolter, A. Raghunathan, T-mars: Improving visual representations by circumventing text feature learning, in: International Conference on Learning Representations, Vol. 2024, 2024, pp. 34003\u201334031."},{"key":"10.1016\/j.displa.2026.103647_b25","doi-asserted-by":"crossref","first-page":"15028","DOI":"10.52202\/079017-0480","article-title":"Cliploss and norm-based data selection methods for multimodal contrastive learning","volume":"37","author":"Wang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.displa.2026.103647_b26","series-title":"ICASSP 2026-2026 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"12687","article-title":"RGSC: Retrieve and then generate image-text pairs from semantic concepts for unsupervised vision-language Pre-Training","author":"Xu","year":"2026"},{"key":"10.1016\/j.displa.2026.103647_b27","doi-asserted-by":"crossref","unstructured":"J. Xu, Y. Song, D. Wang, W. Zhao, M. Chen, K. Chen, Q. Li, Quality over quantity: Boosting data efficiency through ensembled multimodal data curation, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 39, 2025, pp. 21761\u201321769.","DOI":"10.1609\/aaai.v39i20.35481"},{"key":"10.1016\/j.displa.2026.103647_b28","first-page":"97537","article-title":"Filter like you test: Data-driven data filtering for clip pretraining","volume":"38","author":"Shechter","year":"2026","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.displa.2026.103647_b29","series-title":"Multimodal data curation through ranked retrieval","author":"Muthukumar","year":"2026"},{"key":"10.1016\/j.displa.2026.103647_b30","article-title":"Vision-language dataset distillation","author":"Wu","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"10.1016\/j.displa.2026.103647_b31","unstructured":"Y. Xu, Z. Lin, Y. Qiu, et al., Low-rank similarity mining for multimodal dataset distillation, in: Proceedings of the International Conference on Machine Learning, 2024."},{"key":"10.1016\/j.displa.2026.103647_b32","series-title":"Advances in Neural Information Processing Systems","article-title":"Beyond modality collapse: Representations blending for multimodal dataset distillation","author":"Zhang","year":"2025"},{"key":"10.1016\/j.displa.2026.103647_b33","first-page":"111","article-title":"From scarcity to efficiency: Improving clip training via visual-enriched captions","author":"Lai","year":"2024","journal-title":"Eur. Conf. Comput. Vis."},{"key":"10.1016\/j.displa.2026.103647_b34","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.displa.2026.103647_b35","doi-asserted-by":"crossref","unstructured":"W. Yan, Y. Zhang, C. Lv, C. Tang, G. Yue, L. Liao, W. Lin, GCFAgg: Global and Cross-view Feature Aggregation for Multi-view Clustering, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 19863\u201319872.","DOI":"10.1109\/CVPR52729.2023.01902"},{"key":"10.1016\/j.displa.2026.103647_b36","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume":"33","author":"Caron","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.displa.2026.103647_b37","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume":"26","author":"Cuturi","year":"2013","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.displa.2026.103647_b38","doi-asserted-by":"crossref","unstructured":"E.D. Cubuk, B. Zoph, J. Shlens, Q.V. Le, Randaugment: Practical automated data augmentation with a reduced search space, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020, pp. 702\u2013703.","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"10.1016\/j.displa.2026.103647_b39","series-title":"ICML","article-title":"BLIP: Bootstrapping language-image Pre-training for unified vision-language understanding and generation","author":"Li","year":"2022"},{"key":"10.1016\/j.displa.2026.103647_b40","series-title":"International Conference on Machine Learning","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","author":"Kim","year":"2021"},{"key":"10.1016\/j.displa.2026.103647_b41","doi-asserted-by":"crossref","unstructured":"A. Suhr, S. Zhou, A. Zhang, I. Zhang, H. Bai, Y. Artzi, A corpus for reasoning about natural language grounded in photographs, in: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019, pp. 6418\u20136428.","DOI":"10.18653\/v1\/P19-1644"},{"key":"10.1016\/j.displa.2026.103647_b42","doi-asserted-by":"crossref","unstructured":"H. Agrawal, K. Desai, Y. Wang, X. Chen, R. Jain, M. Johnson, D. Batra, D. Parikh, S. Lee, P. Anderson, Nocaps: Novel object captioning at scale, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 8948\u20138957.","DOI":"10.1109\/ICCV.2019.00904"},{"key":"10.1016\/j.displa.2026.103647_b43","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.displa.2026.103647_b44","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"248","article-title":"Imagenet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.displa.2026.103647_b45","article-title":"Bilinear attention networks","volume":"31","author":"Kim","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Displays"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0141938226003100?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0141938226003100?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,16]],"date-time":"2026-08-16T19:22:22Z","timestamp":1786908142000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0141938226003100"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":45,"alternative-id":["S0141938226003100"],"URL":"https:\/\/doi.org\/10.1016\/j.displa.2026.103647","relation":{},"ISSN":["0141-9382"],"issn-type":[{"value":"0141-9382","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MAIC: Multimodal Alignment at Instance and Cluster levels for vision\u2013language data pruning","name":"articletitle","label":"Article Title"},{"value":"Displays","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.displa.2026.103647","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":"103647"}}