{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:44:29Z","timestamp":1777657469286,"version":"3.51.4"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730153","type":"print"},{"value":"9783031730160","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-73016-0_19","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T19:02:40Z","timestamp":1729882960000},"page":"322-337","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["LookupViT: Compressing Visual Information to\u00a0a\u00a0Limited Number of\u00a0Tokens"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3441-8192","authenticated-orcid":false,"given":"Rajat","family":"Koner","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8394-9543","authenticated-orcid":false,"given":"Gagan","family":"Jain","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prateek","family":"Jain","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Volker","family":"Tresp","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sujoy","family":"Paul","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: Vivit: a video vision transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"19_CR2","first-page":"26831","volume":"34","author":"Y Bai","year":"2021","unstructured":"Bai, Y., Mei, J., Yuille, A.L., Xie, C.: Are transformers more robust than cnns? Adv. Neural. Inf. Process. Syst. 34, 26831\u201326843 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Beyer, L., et al.: Flexivit: one model for all patch sizes. CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01393"},{"key":"19_CR4","unstructured":"Beyer, L., Zhai, X., Kolesnikov, A.: Big vision (2022). https:\/\/github.com\/google-research\/big_vision"},{"key":"19_CR5","unstructured":"Bolya, D., Fu, C.Y., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token merging: your vit but faster. ICLR (2023)"},{"key":"19_CR6","unstructured":"Bradbury, J., et al.: JAX: composable transformations of Python+NumPy programs (2018). http:\/\/github.com\/google\/jax"},{"key":"19_CR7","unstructured":"Chen, X., et al.: Microsoft COCO captions: Data collection and evaluation server. CoRR (2015)"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Drop an octave: reducing spatial redundancy in convolutional neural networks with octave convolution. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3435\u20133444 (2019)","DOI":"10.1109\/ICCV.2019.00353"},{"key":"19_CR9","unstructured":"Dehghani, M., et\u00a0al.: Patch n\u2019pack: Navit, a vision transformer for any aspect ratio and resolution. Advances in Neural Information Processing Systems 36 (2024)"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. Ieee (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Dong, X., et al.: Cswin transformer: a general vision transformer backbone with cross-shaped windows. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12124\u201312134 (2022)","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"19_CR12","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. ICLR (2020)"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Fan, H., Xiong, B., Mangalam, K., Li, Y., Yan, Z., Malik, J., Feichtenhofer, C.: Multiscale vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6824\u20136835 (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Fayyaz, M., et al.: Adaptive token sampling for efficient vision transformers. In: European Conference on Computer Vision, pp. 396\u2013414. Springer (2022)","DOI":"10.1007\/978-3-031-20083-0_24"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Goyal, R., et\u00a0al.: The \u201csomething something\u201d video database for learning and evaluating visual common sense. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5842\u20135850 (2017)","DOI":"10.1109\/ICCV.2017.622"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., et al.: The many faces of robustness: a critical analysis of out-of-distribution generalization. ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"19_CR17","unstructured":"Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. In: ICLR (2019)"},{"key":"19_CR18","doi-asserted-by":"crossref","unstructured":"Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J., Song, D.: Natural adversarial examples. CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"19_CR19","unstructured":"Jaegle, A., Gimeno, F., Brock, A., Zisserman, A., Vinyals, O., Carreira, J.: Perceiver: general perception with iterative attention. PMLR (2021)"},{"key":"19_CR20","unstructured":"Kay, W., et\u00a0al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., Wu, C.Y., Fan, H., Mangalam, K., Xiong, B., Malik, J., Feichtenhofer, C.: Mvitv2: Improved multiscale vision transformers for classification and detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4804\u20134814 (2022)","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"19_CR23","unstructured":"Renggli, C., Pinto, A.S., Houlsby, N., Mustafa, B., Puigcerver, J., Riquelme, C.: Learning to merge tokens in vision transformers. arXiv preprint arXiv:2202.12015 (2022)"},{"key":"19_CR24","unstructured":"Ryali, C., et\u00a0al.: Hiera: a hierarchical vision transformer without the bells-and-whistles. arXiv preprint arXiv:2306.00989 (2023)"},{"key":"19_CR25","unstructured":"Ryoo, M.S., Piergiovanni, A., Arnab, A., Dehghani, M., Angelova, A.: Tokenlearner: what can 8 learned tokens do for images and videos? NeurIPS (2021)"},{"key":"19_CR26","unstructured":"Song, Z., Xu, Y., He, Z., Jiang, L., Jing, N., Liang, X.: Cp-vit: cascade vision transformer pruning via progressive sparsity prediction. arXiv preprint arXiv:2203.04570 (2022)"},{"key":"19_CR27","unstructured":"Steiner, A., Kolesnikov, A., Zhai, X., Wightman, R., Uszkoreit, J., Beyer, L.: How to train your vit? data, augmentation, and regularization in vision transformers. arXiv preprint arXiv:2106.10270 (2021)"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Sun, C., Shrivastava, A., Singh, S., Gupta, A.: Revisiting unreasonable effectiveness of data in deep learning era. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 843\u2013852 (2017)","DOI":"10.1109\/ICCV.2017.97"},{"key":"19_CR29","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., J\u00e9gou, H.: Training data-efficient image transformers & distillation through attention. In: International Conference on Machine Learning, pp. 10347\u201310357. PMLR (2021)"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Fan, D.P., Song, K., Liang, D., Lu, T., Luo, P., Shao, L.: Pyramid vision transformer: a versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"issue":"7","key":"19_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-022-3646-6","volume":"66","author":"H Yu","year":"2023","unstructured":"Yu, H., Wu, J.: A unified pruning framework for vision transformers. SCIENCE CHINA Inf. Sci. 66(7), 1\u20132 (2023)","journal-title":"SCIENCE CHINA Inf. Sci."},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Zhai, X., et al.: Lit: Zero-shot transfer with locked-image text tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18123\u201318133 (2022)","DOI":"10.1109\/CVPR52688.2022.01759"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73016-0_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T19:07:04Z","timestamp":1729883224000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73016-0_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031730153","9783031730160"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73016-0_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,26]]},"assertion":[{"value":"26 October 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}