{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:06:26Z","timestamp":1778079986707,"version":"3.51.4"},"publisher-location":"Cham","reference-count":68,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031729973","type":"print"},{"value":"9783031729980","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-72998-0_12","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T18:01:58Z","timestamp":1727632918000},"page":"200-218","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Agglomerative Token Clustering"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0544-0422","authenticated-orcid":false,"given":"Joakim Bruslund","family":"Haurum","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0617-8873","authenticated-orcid":false,"given":"Sergio","family":"Escalera","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5867-3652","authenticated-orcid":false,"given":"Graham W.","family":"Taylor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7584-5209","authenticated-orcid":false,"given":"Thomas B.","family":"Moeslund","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Beyer, L., et al.: FlexiViT: one model for all patch sizes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01393"},{"key":"12_CR2","unstructured":"Bolya, D., Fu, C.Y., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token merging: your ViT but faster. In: International Conference on Learning Representations (ICLR) (2023). https:\/\/openreview.net\/forum?id=JroZRaRw7Eu"},{"key":"12_CR3","doi-asserted-by":"crossref","unstructured":"Bolya, D., Hoffman, J.: Token merging for fast stable diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (2023)","DOI":"10.1109\/CVPRW59228.2023.00484"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Chang, S., et al.: Making vision transformers efficient from a token sparsification view. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00600"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Chavan, A., Shen, Z., Liu, Z., Liu, Z., Cheng, K.T., Xing, E.: Vision transformer slimming: multi-dimension searching in continuous optimization space. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00488"},{"key":"12_CR6","unstructured":"Chen, K., et al.: MMDetection: open MMLab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)"},{"key":"12_CR7","doi-asserted-by":"publisher","unstructured":"Chen, M., et al.: CF-ViT: a general coarse-to-fine method for vision transformer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, no. 6 (2023). https:\/\/doi.org\/10.1609\/aaai.v37i6.25860. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/25860","DOI":"10.1609\/aaai.v37i6.25860"},{"key":"12_CR8","unstructured":"Chen, T., Cheng, Y., Gan, Z., Yuan, L., Zhang, L., Wang, Z.: Chasing sparsity in vision transformers: an end-to-end exploration. In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems, vol.\u00a034 (2021). https:\/\/proceedings.neurips.cc\/paper\/2021\/file\/a61f27ab2165df0e18cc9433bd7f27c5-Paper.pdf"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Chen, X., Liu, Z., Tang, H., Yi, L., Zhao, H., Han, S.: SparseViT: revisiting activation sparsity for efficient high-resolution vision transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00205"},{"key":"12_CR10","unstructured":"Chen, Z., et al.: Vision transformer adapter for dense predictions. In: International Conference on Learning Representations (ICLR) (2023). https:\/\/openreview.net\/forum?id=plKu2GByCNW"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Chua, T.S., Tang, J., Hong, R., Li, H., Luo, Z., Zheng, Y.T.: NUS-WIDE: a real-world web image database from National University of Singapore. In: Proceedings of ACM Conference on Image and Video Retrieval (CIVR 2009), Santorini, Greece (2009)","DOI":"10.1145\/1646396.1646452"},{"key":"12_CR12","unstructured":"Dehghani, M., et al.: Patch n\u2019Pack: NaViT, a vision transformer for any aspect ratio and resolution. arXiv preprint arXiv:2307.06304 (2023)"},{"key":"12_CR13","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"12_CR14","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16\\times 16$$ words: transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR) (2021). https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"12_CR15","doi-asserted-by":"publisher","unstructured":"Everitt, B.S., Landau, S., Leese, M., Stahl, D.: Cluster Analysis. Wiley (2011). https:\/\/doi.org\/10.1002\/9780470977811","DOI":"10.1002\/9780470977811"},{"key":"12_CR16","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1007\/978-3-031-20083-0_24","volume-title":"European Conference on Computer Vision 2022 (ECCV 2022)","author":"M Fayyaz","year":"2022","unstructured":"Fayyaz, M., et al.: Adaptive token sampling for efficient vision transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13671, pp. 396\u2013414. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20083-0_24"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Graham, B., et al.: LeViT: a vision transformer in convnet\u2019s clothing for faster inference. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Haurum, J.B., Escalera, S., Taylor, G.W., Moeslund, T.B.: Which tokens to use? Investigating token reduction in vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) Workshops (2023)","DOI":"10.1109\/ICCVW60793.2023.00085"},{"key":"12_CR19","doi-asserted-by":"publisher","unstructured":"Haurum, J.B., Madadi, M., Escalera, S., Moeslund, T.B.: Multi-scale hybrid vision transformer and Sinkhorn tokenizer for sewer defect classification. Autom. Constr. 144 (2022). https:\/\/doi.org\/10.1016\/j.autcon.2022.104614. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0926580522004848","DOI":"10.1016\/j.autcon.2022.104614"},{"key":"12_CR20","doi-asserted-by":"publisher","unstructured":"He, J., et al.: TransFG: a transformer architecture for fine-grained recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 1 (2022). https:\/\/doi.org\/10.1609\/aaai.v36i1.19967. https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/19967","DOI":"10.1609\/aaai.v36i1.19967"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Dollar, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Heo, B., Yun, S., Han, D., Chun, S., Choe, J., Oh, S.J.: Rethinking spatial dimensions of vision transformers. In: Proceedings of the International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"12_CR24","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol.\u00a030 (2017). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/8a1d694707eb0fefe65871369074926d-Paper.pdf"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Hu, C., Zhu, L., Qiu, W., Wu, W.: Data augmentation vision transformer for fine-grained image classification. arXiv preprint arXiv:2211.12879 (2022)","DOI":"10.2139\/ssrn.4063510"},{"key":"12_CR26","doi-asserted-by":"publisher","unstructured":"Hu, Y., et al.: RAMS-Trans: recurrent attention multi-scale transformer for fine-grained image recognition. In: Proceedings of the 29th ACM International Conference on Multimedia, MM 2021. Association for Computing Machinery, New York (2021). https:\/\/doi.org\/10.1145\/3474085.3475561","DOI":"10.1145\/3474085.3475561"},{"key":"12_CR27","unstructured":"Jang, E., Gu, S., Poole, B.: Categorical reparameterization with gumbel-softmax. In: International Conference on Learning Representations (ICLR) (2017). https:\/\/openreview.net\/forum?id=rkE3y85ee"},{"key":"12_CR28","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1007\/978-3-031-20083-0_37","volume-title":"European Conference on Computer Vision (ECCV)","author":"Z Kong","year":"2022","unstructured":"Kong, Z., et al.: SPViT: enabling faster vision transformers via latency-aware soft token pruning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13671, pp. 620\u2013640. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20083-0_37"},{"key":"12_CR29","unstructured":"Li, L., Thorsley, D., Hassoun, J.: SaiT: sparse vision transformers through adaptive token pruning. arXiv preprint arXiv:2210.05832 (2022)"},{"key":"12_CR30","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1007\/978-3-031-20077-9_17","volume-title":"European Conference on Computer Vision (ECCV)","author":"Y Li","year":"2022","unstructured":"Li, Y., Mao, H., Girshick, R., He, K.: Exploring plain vision transformer backbones for object detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 280\u2013296. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_17"},{"key":"12_CR31","unstructured":"Li, Z., Yang, T., Wang, P., Cheng, J.: Q-ViT: fully differentiable quantization for vision transformer. arXiv preprint arXiv:2201.07703 (2022)"},{"key":"12_CR32","unstructured":"Liang, Y., Ge, C., Tong, Z., Song, Y., Wang, J., Xie, P.: EViT: expediting vision transformers via token reorganizations. In: International Conference on Learning Representations (ICLR) (2022). https:\/\/openreview.net\/forum?id=BjyvwnXXVn_"},{"issue":"12","key":"12_CR33","doi-asserted-by":"publisher","first-page":"3136","DOI":"10.1007\/s11263-023-01861-3","volume":"131","author":"M Lin","year":"2023","unstructured":"Lin, M., Chen, M., Zhang, Y., Shen, C., Ji, R., Cao, L.: Super vision transformer. Int. J. Comput. Vis. 131(12), 3136\u20133151 (2023). https:\/\/doi.org\/10.1007\/s11263-023-01861-3","journal-title":"Int. J. Comput. Vis."},{"key":"12_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"12_CR35","doi-asserted-by":"crossref","unstructured":"Lin, Y., Zhang, T., Sun, P., Li, Z., Zhou, S.: FQ-ViT: post-training quantization for fully quantized vision transformer. In: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-2022 (2022)","DOI":"10.24963\/ijcai.2022\/164"},{"key":"12_CR36","doi-asserted-by":"crossref","unstructured":"Liu, Y., Gehrig, M., Messikommer, N., Cannici, M., Scaramuzza, D.: Revisiting token pruning for object detection and instance segmentation. arXiv preprint arXiv:2306.07050 (2023)","DOI":"10.1109\/WACV57701.2024.00264"},{"key":"12_CR37","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 (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"12_CR38","doi-asserted-by":"crossref","unstructured":"Long, S., Zhao, Z., Pi, J., Wang, S., Wang, J.: Beyond attentive tokens: incorporating token importance and diversity for efficient vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00996"},{"key":"12_CR39","doi-asserted-by":"crossref","unstructured":"Marin, D., Chang, J.H.R., Ranjan, A., Prabhu, A., Rastegari, M., Tuzel, O.: Token pooling in vision transformers for image classification. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2023)","DOI":"10.1109\/WACV56688.2023.00010"},{"key":"12_CR40","doi-asserted-by":"crossref","unstructured":"Meng, L., et al.: AdaViT: adaptive vision transformers for efficient image recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01199"},{"key":"12_CR41","unstructured":"M\u00fcllner, D.: Modern hierarchical, agglomerative clustering algorithms. arXiv preprint arXiv:1109.2378 (2011)"},{"key":"12_CR42","unstructured":"Pan, B., Panda, R., Jiang, Y., Wang, Z., Feris, R., Oliva, A.: IA-$$\\text{RED}^2$$: interpretability-aware redundancy reduction for vision transformers. In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems, vol.\u00a034 (2021). https:\/\/proceedings.neurips.cc\/paper\/2021\/file\/d072677d210ac4c03ba046120f0802ec-Paper.pdf"},{"key":"12_CR43","doi-asserted-by":"publisher","unstructured":"Pan, Z., Zhuang, B., He, H., Liu, J., Cai, J.: Less is more: pay less attention in vision transformers. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, no. 2 (2022). https:\/\/doi.org\/10.1609\/aaai.v36i2.20099","DOI":"10.1609\/aaai.v36i2.20099"},{"key":"12_CR44","unstructured":"von Platen, P., et al.: Diffusers: state-of-the-art diffusion models (2022). https:\/\/github.com\/huggingface\/diffusers"},{"key":"12_CR45","unstructured":"Raghu, M., Unterthiner, T., Kornblith, S., Zhang, C., Dosovitskiy, A.: Do vision transformers see like convolutional neural networks? In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems, vol.\u00a034, pp. 12116\u201312128. Curran Associates, Inc. (2021). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/652cf38361a209088302ba2b8b7f51e0-Paper.pdf"},{"key":"12_CR46","unstructured":"Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., Hsieh, C.J.: DynamicViT: efficient vision transformers with dynamic token sparsification. In: Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems (2021). https:\/\/openreview.net\/forum?id=jB0Nlbwlybm"},{"key":"12_CR47","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":"12_CR48","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"12_CR49","doi-asserted-by":"crossref","unstructured":"Singh, M., et al.: Revisiting weakly supervised pre-training of visual perception models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00088"},{"key":"12_CR50","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":"12_CR51","unstructured":"Steiner, A.P., Kolesnikov, A., Zhai, X., Wightman, R., Uszkoreit, J., Beyer, L.: How to train your ViT? Data, augmentation, and regularization in vision transformers. Trans. Mach. Learn. Res. (2022). https:\/\/openreview.net\/forum?id=4nPswr1KcP"},{"key":"12_CR52","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., Jegou, H.: Training data-efficient image transformers & distillation through attention. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0139. PMLR (2021). https:\/\/proceedings.mlr.press\/v139\/touvron21a.html"},{"key":"12_CR53","doi-asserted-by":"crossref","unstructured":"Van\u00a0Horn, G., et al.: Building a bird recognition app and large scale dataset with citizen scientists: the fine print in fine-grained dataset collection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7298658"},{"key":"12_CR54","unstructured":"Wang, J., Yu, X., Gao, Y.: Feature fusion vision transformer for fine-grained visual categorization. In: British Machine Vision Conference (2021)"},{"key":"12_CR55","unstructured":"Wang, Y., Ye, S., Yu, S., You, X.: R2-Trans: fine-grained visual categorization with redundancy reduction. arXiv preprint arXiv:2204.10095 (2022)"},{"key":"12_CR56","unstructured":"Wang, Y., Huang, R., Song, S., Huang, Z., Huang, G.: Not all images are worth $$16\\times 16$$ words: dynamic transformers for efficient image recognition. In: Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems (2021). https:\/\/openreview.net\/forum?id=M0J1c3PqwKZ"},{"key":"12_CR57","unstructured":"Wang, Y., Du, B., Xu, C.: Multi-tailed vision transformer for efficient inference. arXiv preprint arXiv:2203.01587 (2022)"},{"key":"12_CR58","doi-asserted-by":"crossref","unstructured":"Wei, C., Duke, B., Jiang, R., Aarabi, P., Taylor, G.W., Shkurti, F.: Sparsifiner: learning sparse instance-dependent attention for efficient vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.02172"},{"key":"12_CR59","doi-asserted-by":"crossref","unstructured":"Wei, S., Ye, T., Zhang, S., Tang, Y., Liang, J.: Joint token pruning and squeezing towards more aggressive compression of vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00208"},{"key":"12_CR60","unstructured":"Wu, X., Zeng, F., Wang, X., Wang, Y., Chen, X.: PPT: token pruning and pooling for efficient vision transformers. arXiv preprint arXiv:2310.01812 (2023)"},{"key":"12_CR61","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: GroupViT: semantic segmentation emerges from text supervision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"12_CR62","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: Evo-ViT: slow-fast token evolution for dynamic vision transformer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036 (2022)","DOI":"10.1609\/aaai.v36i3.20202"},{"key":"12_CR63","doi-asserted-by":"crossref","unstructured":"Yin, H., Vahdat, A., Alvarez, J., Mallya, A., Kautz, J., Molchanov, P.: A-ViT: adaptive tokens for efficient vision transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01054"},{"issue":"7","key":"12_CR64","doi-asserted-by":"publisher","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. Sci. China Inf. Sci. 66(7), 179101 (2023). https:\/\/doi.org\/10.1007\/s11432-022-3646-6","journal-title":"Sci. China Inf. Sci."},{"key":"12_CR65","doi-asserted-by":"crossref","unstructured":"Yue, X., et al.: Vision transformer with progressive sampling. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00044"},{"key":"12_CR66","doi-asserted-by":"crossref","unstructured":"Zeng, W., et al.: Not all tokens are equal: human-centric visual analysis via token clustering transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01082"},{"key":"12_CR67","unstructured":"Zhu, Y., et al.: Make a long image short: adaptive token length for vision transformers. arXiv preprint arXiv:2112.01686 (2021)"},{"key":"12_CR68","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1007\/978-3-031-20083-0_26","volume-title":"European Conference on Computer Vision (ECCV)","author":"Z Zong","year":"2022","unstructured":"Zong, Z., et al.: Self-slimmed vision transformer. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13671, pp. 432\u2013448. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20083-0_26"}],"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\/978-3-031-72998-0_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T18:05:12Z","timestamp":1727633112000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72998-0_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031729973","9783031729980"],"references-count":68,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72998-0_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 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"}}]}}