{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:07:15Z","timestamp":1788937635495,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":58,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372512","type":"print"},{"value":"9783032372529","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37252-9_8","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:45:50Z","timestamp":1788936350000},"page":"130-148","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fragmented Text is Insufficient for\u00a0Image Representation: Fine-Grained Correspondence in\u00a0Multimodal Dataset Distillation"],"prefix":"10.1007","author":[{"given":"Jingwei","family":"Fang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaxin","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junhui","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuheng","family":"Jia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"8_CR1","unstructured":"Andrew, G., Arora, R., Bilmes, J.A., Livescu, K.: Deep canonical correlation analysis. In: International Conference on Machine Learning, ICML, pp. 1247\u20131255 (2013)"},{"key":"8_CR2","unstructured":"Brock, A., De, S., Smith, S.L., Simonyan, K.: High-performance large-scale image recognition without normalization. In: International Conference on Machine Learning, ICML, pp. 1059\u20131071 (2021)"},{"key":"8_CR3","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems, NeurIPS (2020)"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Cazenavette, G., Wang, T., Torralba, A., Efros, A.A., Zhu, J.: Dataset distillation by matching training trajectories. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, pp. 10708\u201310717 (2022)","DOI":"10.1109\/CVPR52688.2022.01045"},{"key":"8_CR5","unstructured":"Cui, J., Wang, R., Si, S., Hsieh, C.: Scaling up dataset distillation to ImageNet-1k with constant memory. In: International Conference on Machine Learning, ICML, pp. 6565\u20136590 (2023)"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT, pp. 4171\u20134186 (2019)","DOI":"10.18653\/v1\/N19-1423"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Ding, G., Chen, R., Yao, A.: Condensing action segmentation datasets via generative network inversion. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, pp. 17733\u201317742 (2025)","DOI":"10.1109\/CVPR52734.2025.01652"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Du, J., Jiang, Y., Tan, V.Y.F., Zhou, J.T., Li, H.: Minimizing the accumulated trajectory error to improve dataset distillation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, pp. 3749\u20133758 (2023)","DOI":"10.1109\/CVPR52729.2023.00365"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Du, J., Shi, Q., Zhou, J.T.: Sequential subset matching for dataset distillation. In: Advances in Neural Information Processing Systems, NeurIPS (2023)","DOI":"10.52202\/075280-2950"},{"key":"8_CR10","unstructured":"Frome, A., et al.: Devise: a deep visual-semantic embedding model. In: Advances in Neural Information Processing Systems, NeurIPS (2013)"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Gemmeke, J.F., et al.: Audio set: An ontology and human-labeled dataset for audio events. In: International Conference on Acoustics, Speech and Signal Processing, ICASSP, pp. 776\u2013780 (2017)","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Gu, Jet al.: Efficient dataset distillation via minimax diffusion. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, pp. 15793\u201315803 (2024)","DOI":"10.1109\/CVPR52733.2024.01495"},{"key":"8_CR13","unstructured":"Guo, Z., Wang, K., Cazenavette, G., Li, H., Zhang, K., You, Y.: Towards lossless dataset distillation via difficulty-aligned trajectory matching. In: International Conference on Learning Representations, ICLR (2024)"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"8_CR15","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"8_CR16","unstructured":"Belghazi, I., et al.: Mine: mutual information neural estimation. arXiv preprint arXiv:1801.04062 (2018)"},{"key":"8_CR17","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, ICML, pp. 4904\u20134916 (2021)"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Kang, W., Huang, H., Shang, Y., Shah, M., Yan, Y.: Robin3D: improving 3D large language model via robust instruction tuning. In: IEEE\/CVF International Conference on Computer Vision, ICCV, pp. 3905\u20133915 (2025)","DOI":"10.1109\/ICCV51701.2025.00372"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Kim, C.D., Kim, B., Lee, H., Kim, G.: AudioCaps: generating captions for audios in the wild. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT, pp. 119\u2013132 (2019)","DOI":"10.18653\/v1\/N19-1011"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Lee, Y., Chung, H.W.: CovMatch: Cross-covariance guided multimodal dataset distillation with trainable text encoder. In: Advances in Neural Information Processing Systems, NeurIPS (2025)","DOI":"10.52202\/085713-3398"},{"key":"8_CR21","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.C.H.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, ICML, pp. 12888\u201312900 (2022)"},{"key":"8_CR22","unstructured":"Li, J., Selvaraju, R.R., Gotmare, A., Joty, S.R., Xiong, C., Hoi, S.C.: Align before fuse: vision and language representation learning with momentum distillation. In: Advances in Neural Information Processing Systems, NeurIPS (2021)"},{"key":"8_CR23","unstructured":"Li, N., Liu, A.A., Zhang, J., Cui, J.: Latent video dataset distillation. arXiv preprint arXiv:2504.17132 (2025)"},{"key":"8_CR24","unstructured":"Li, Y., Li, W.: Data distillation for text classification. arXiv preprint arXiv:2104.08448 (2021)"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Lin, T., et al.: Microsoft COCO: common objects in context. In: European Conference on Computer Vision, ECCV, pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, pp. 26286\u201326296 (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems, NeurIPS (2023)","DOI":"10.52202\/075280-1516"},{"key":"8_CR28","unstructured":"Lu, H., Isonuma, M., Mori, J., Sakata, I.: UniDetox: universal detoxification of large language models via dataset distillation. In: International Conference on Learning Representations, ICLR (2025)"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Maekawa, A., Kosugi, S., Funakoshi, K., Okumura, M.: DILM: distilling dataset into language model for text-level dataset distillation. In: Findings of the Association for Computational Linguistics: NAACL, pp. 3138\u20133153 (2024)","DOI":"10.18653\/v1\/2024.findings-naacl.199"},{"key":"8_CR30","unstructured":"Nguyen, D., Li, Z., Bateni, M., Mirrokni, V., Razaviyayn, M., Mirzasoleiman, B.: Synthetic text generation for training large language models via gradient matching. arXiv preprint arXiv:2502.17607 (2025)"},{"key":"8_CR31","unstructured":"Nguyen, T., Chen, Z., Lee, J.: Dataset meta-learning from kernel ridge-regression. In: International Conference on Learning Representations, ICLR (2021)"},{"key":"8_CR32","unstructured":"Nguyen, T., Novak, R., Xiao, L., Lee, J.: Dataset distillation with infinitely wide convolutional networks. In: Advances in Neural Information Processing Systems, NeurIPS (2021)"},{"key":"8_CR33","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"8_CR34","doi-asserted-by":"crossref","unstructured":"Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J., Lazebnik, S.: Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models. Int. J. Comput. Vision IJCV 74\u201393 (2017)","DOI":"10.1007\/s11263-016-0965-7"},{"key":"8_CR35","unstructured":"Radford, A., Kim, J.W., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, ICML, pp. 8748\u20138763 (2021)"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R.B., He, K., Doll\u00e1r, P.: Designing network design spaces. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, pp. 10425\u201310433 (2020)","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Rohrbach, A., Hendricks, L.A., Burns, K., Darrell, T., Saenko, K.: Object hallucination in image captioning. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, pp. 4035\u20134045 (2018)","DOI":"10.18653\/v1\/D18-1437"},{"key":"8_CR38","doi-asserted-by":"crossref","unstructured":"Schmid, F., Koutini, K., Widmer, G.: Efficient large-scale audio tagging via transformer-to-CNN knowledge distillation. In: International Conference on Acoustics, Speech and Signal Processing ICASSP, pp. 1\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10096110"},{"key":"8_CR39","doi-asserted-by":"crossref","unstructured":"Shang, Y., Cai, M., Xu, B., Lee, Y.J., Yan, Y.: LLaVA-prumerge: adaptive token reduction for efficient large multimodal models. In: IEEE\/CVF International Conference on Computer Vision, ICCV, pp. 22857\u201322867 (2025)","DOI":"10.1109\/ICCV51701.2025.02122"},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"Su, D., Hou, J., Gao, W., Tian, Y., Tang, B.: $$\\text{D}^{4}$$m: dataset distillation via disentangled diffusion model. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, pp. 5809\u20135818 (2024)","DOI":"10.1109\/CVPR52733.2024.00555"},{"key":"8_CR41","doi-asserted-by":"crossref","unstructured":"Sun, P., Shi, B., Yu, D., Lin, T.: On the diversity and realism of distilled dataset: an efficient dataset distillation paradigm. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, pp. 9390\u20139399 (2024)","DOI":"10.1109\/CVPR52733.2024.00897"},{"key":"8_CR42","unstructured":"Toneva, M., Sordoni, A., des Combes, R.T., Trischler, A., Bengio, Y., Gordon, G.J.: An empirical study of example forgetting during deep neural network learning. In: International Conference on Learning Representations, ICLR (2019)"},{"key":"8_CR43","doi-asserted-by":"crossref","unstructured":"Wang, K., et al.: CAFE: learning to condense dataset by aligning features. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, pp. 12186\u201312195 (2022)","DOI":"10.1109\/CVPR52688.2022.01188"},{"key":"8_CR44","doi-asserted-by":"crossref","unstructured":"Wang, S., et al.: Dataset distillation with neural characteristic function: A minmax perspective. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, pp. 25570\u201325580 (2025)","DOI":"10.1109\/CVPR52734.2025.02381"},{"key":"8_CR45","unstructured":"Wang, T., Zhu, J.Y., Torralba, A., Efros, A.A.: Dataset distillation. arXiv preprint arXiv:1811.10959 (2018)"},{"key":"8_CR46","doi-asserted-by":"crossref","unstructured":"Wang, Z., Xu, Y., Lu, C., Li, Y.: Dancing with still images: video distillation via static-dynamic disentanglement. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, pp. 6296\u20136304 (2024)","DOI":"10.1109\/CVPR52733.2024.00602"},{"key":"8_CR47","doi-asserted-by":"crossref","unstructured":"Welling, M.: Herding dynamical weights to learn. In: International Conference on Machine Learning, ICML, pp. 1121\u20131128 (2009)","DOI":"10.1145\/1553374.1553517"},{"key":"8_CR48","doi-asserted-by":"crossref","unstructured":"Wolf, G.W.: Facility location: concepts, models, algorithms and case studies. series: contributions to management science. Int. J. Geogr. Inf. Sci. IJGIS 25, 331\u2013333 (2011)","DOI":"10.1080\/13658816.2010.528422"},{"key":"8_CR49","unstructured":"Wu, X., Zhang, B., Deng, Z., Russakovsky, O.: Vision-language dataset distillation. Trans. Mach. Learn. Res. TMLR (2024)"},{"key":"8_CR50","unstructured":"Xu, Y., Lin, Z., Qiu, Y., Lu, C., Li, Y.: Low-rank similarity mining for multimodal dataset distillation. In: International Conference on Machine Learning, ICML (2024)"},{"key":"8_CR51","doi-asserted-by":"crossref","unstructured":"Yin, Z., Xing, E.P., Shen, Z.: Squeeze, recover and relabel: dataset condensation at ImageNet scale from a new perspective. In: Advances in Neural Information Processing Systems, NeurIPS (2023)","DOI":"10.52202\/075280-3219"},{"key":"8_CR52","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: CoCa: contrastive captioners are image-text foundation models. Trans. Mach. Learn. Res. TMLR (2022)"},{"key":"8_CR53","unstructured":"Zhang, H., Li, S., Lin, F., Wang, W., Qian, Z., Ge, S.: DANCE: dual-view distribution alignment for dataset condensation. In: International Joint Conference on Artificial Intelligence, IJCAI, pp. 1679\u20131687 (2024)"},{"key":"8_CR54","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhang, Z., Du, J., Liu, Z., Zhou, J.T.: Beyond modality collapse: representations blending for multimodal dataset distillation. In: Advances in Neural Information Processing Systems, NeurIPS (2025)","DOI":"10.52202\/085713-3827"},{"key":"8_CR55","doi-asserted-by":"crossref","unstructured":"Zhao, B., Bilen, H.: Dataset condensation with distribution matching. In: IEEE\/CVF Winter Conference on Applications of Computer Vision, WACV, pp. 6503\u20136512 (2023)","DOI":"10.1109\/WACV56688.2023.00645"},{"key":"8_CR56","unstructured":"Zhao, B., Mopuri, K.R., Bilen, H.: Dataset condensation with gradient matching. In: International Conference on Learning Representations, ICLR (2021)"},{"key":"8_CR57","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Wang, H., Wu, J., Shang, Y., Liu, G., Yan, Y.: Efficient multimodal dataset distillation via generative models. In: Advances in Neural Information Processing Systems, NeurIPS (2025)","DOI":"10.52202\/085713-2280"},{"key":"8_CR58","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Nezhadarya, E., Ba, J.: Dataset distillation using neural feature regression. In: Advances in Neural Information Processing Systems, NeurIPS (2022)","DOI":"10.52202\/068431-0713"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37252-9_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:46:01Z","timestamp":1788936361000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37252-9_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372512","9783032372529"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37252-9_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"10 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}