{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T16:01:08Z","timestamp":1782835268646,"version":"3.54.5"},"publisher-location":"Cham","reference-count":71,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200823","type":"print"},{"value":"9783031200830","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20083-0_24","type":"book-chapter","created":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T19:46:34Z","timestamp":1667418394000},"page":"396-414","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":165,"title":["Adaptive Token Sampling for\u00a0Efficient Vision Transformers"],"prefix":"10.1007","author":[{"given":"Mohsen","family":"Fayyaz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soroush Abbasi","family":"Koohpayegani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Farnoush Rezaei","family":"Jafari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sunando","family":"Sengupta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamid Reza Vaezi","family":"Joze","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric","family":"Sommerlade","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamed","family":"Pirsiavash","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J\u00fcrgen","family":"Gall","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,3]]},"reference":[{"key":"24_CR1","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding. In: International Conference on Machine Learning (ICML) (2021)"},{"key":"24_CR2","unstructured":"Bulat, A., Perez Rua, J.M., Sudhakaran, S., Martinez, B., Tzimiropoulos, G.: Space-time mixing attention for video transformer. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"24_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-End object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"24_CR4","unstructured":"Carreira, J., Noland, E., Banki-Horvath, A., Hillier, C., Zisserman, A.: A short note about kinetics-600. In: arXiv preprint. arXiv:1808.01340v1 (2018)"},{"key":"24_CR5","doi-asserted-by":"crossref","unstructured":"Chen, C.F., Fan, Q., Panda, R.: Crossvit: cross-attention multi-scale vision transformer for image classification. In: IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"24_CR6","unstructured":"Cheng, B., Schwing, A.G., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"24_CR7","unstructured":"Child, R., Gray, S., Radford, A., Sutskever, I.: Generating long sequences with sparse transformers. In: arXiv preprint. arXiv:1904.10509 (2019)"},{"key":"24_CR8","unstructured":"Chu, X., Tian, Z., Zhang, B., Wang, X., Wei, X., Xia, H., Shen, C.: Conditional positional encodings for vision transformers. In: arXiv preprint. arXiv:2102.10882 (2021)"},{"key":"24_CR9","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: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"24_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/978-3-030-01225-0_18","volume-title":"Computer Vision \u2013 ECCV 2018","author":"A Diba","year":"2018","unstructured":"Diba, A., et al.: Spatio-temporal channel correlation networks for action classification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 299\u2013315. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_18"},{"key":"24_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1007\/978-3-030-58558-7_35","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Diba","year":"2020","unstructured":"Diba, A., et al.: Large scale holistic video understanding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 593\u2013610. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_35"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Diba, A., Sharma, V., Gool, L.V., Stiefelhagen, R.: Dynamonet: dynamic action and motion network. In: IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00629"},{"key":"24_CR13","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (ICLR) (2021)"},{"key":"24_CR14","doi-asserted-by":"crossref","unstructured":"Fan, H., Xiong, B., Mangalam, K., Li, Y., Yan, Z., Malik, J., Feichtenhofer, C.: Multiscale vision transformers. In: IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"24_CR15","unstructured":"Fan, Q., Chen, C.F.R., Kuehne, H., Pistoia, M., Cox, D.: More Is Less: learning Efficient Video Representations by Temporal Aggregation Modules. In: Advances in Neural Information Processing Systems (NeurIPS) (2019)"},{"key":"24_CR16","doi-asserted-by":"crossref","unstructured":"Fayyaz, M., Bahrami, E., Diba, A., Noroozi, M., Adeli, E., Van Gool, L., Gall, J.: 3d cnns with adaptive temporal feature resolutions. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00470"},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C.: X3d: Expanding architectures for efficient video recognition. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"24_CR18","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: IEEE\/CVF international conference on computer vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"24_CR19","unstructured":"Gong, Y., Liu, L., Yang, M., Bourdev, L.: Compressing deep convolutional networks using vector quantization. In: arXiv preprint. arXiv:1412.6115 (2014)"},{"key":"24_CR20","unstructured":"Goyal, S., Choudhury, A.R., Raje, S.M., Chakaravarthy, V.T., Sabharwal, Y., Verma, A.: Power-bert: accelerating bert inference via progressive word-vector elimination. In: International Conference on Machine Learning (ICML) (2020)"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Guo, Q., Qiu, X., Liu, P., Shao, Y., Xue, X., Zhang, Z.: Star-transformer. In: arXiv preprint. arXiv:1902.09113 (2019)","DOI":"10.18653\/v1\/N19-1133"},{"key":"24_CR22","unstructured":"Han, K., Xiao, A., Wu, E., Guo, J., Xu, C., Wang, Y.: Transformer in transformer. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"24_CR23","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) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"24_CR24","doi-asserted-by":"crossref","unstructured":"He, Y., Zhang, X., Sun, J.: Channel pruning for accelerating very deep neural networks. In: IEEE\/CVF International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.155"},{"key":"24_CR25","unstructured":"Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: NIPS Deep Learning and Representation Learning Workshop (2015)"},{"key":"24_CR26","unstructured":"Howard, A.G., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. In: arXiv preprint. arXiv:1704.04861 (2017)"},{"key":"24_CR27","doi-asserted-by":"crossref","unstructured":"Jaderberg, M., Vedaldi, A., Zisserman, A.: Speeding up convolutional neural networks with low rank expansions. In: arXiv preprint. arXiv:1405.3866 (2014)","DOI":"10.5244\/C.28.88"},{"key":"24_CR28","unstructured":"Jaszczur, S., et al.: Sparse is enough in scaling transformers. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"24_CR29","doi-asserted-by":"crossref","unstructured":"Jiang, B., Wang, M., Gan, W., Wu, W., Yan, J.: Stm: spatiotemporal and motion encoding for action recognition. In: IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00209"},{"key":"24_CR30","unstructured":"Jiang, Z., et al.: Token labeling: training a 85.5% top-1 accuracy vision transformer with 56m parameters on imagenet. In: arXiv preprint. arXiv:2104.10858v2 (2021)"},{"key":"24_CR31","unstructured":"Jiang, Z., et al.: All tokens matter: token labeling for training better vision transformers. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"24_CR32","doi-asserted-by":"crossref","unstructured":"Jiao, X., et al.: Tinybert: distilling bert for natural language understanding. In: arXiv preprint. arXiv:1909.10351 (2020)","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"24_CR33","unstructured":"Kay, W., et al.: The kinetics human action video dataset. In: arXiv preprint. arXiv:1705.06950 (2017)"},{"key":"24_CR34","unstructured":"Krizhevsky, A.: One weird trick for parallelizing convolutional neural networks. In: ArXiv preprint. arXiv:1404.5997 (2014)"},{"key":"24_CR35","doi-asserted-by":"crossref","unstructured":"Li, Y., Ji, B., Shi, X., Zhang, J., Kang, B., Wang, L.: Tea: temporal excitation and aggregation for action recognition. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"24_CR36","unstructured":"Liang, Y., Ge, C., Tong, Z., Song, Y., Wang, J., Xie, P.: Not all patches are what you need: Expediting vision transformers via token reorganizations. In: International Conference on Learning Representations (ICLR) (2022)"},{"key":"24_CR37","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., Han, S.: Tsm: Temporal shift module for efficient video understanding. In: IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"24_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-030-58568-6_41","volume-title":"Computer Vision \u2013 ECCV 2020","author":"B Liu","year":"2020","unstructured":"Liu, B., Rao, Y., Lu, J., Zhou, J., Hsieh, C.-J.: MetaDistiller: network self-boosting via meta-learned top-down distillation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 694\u2013709. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_41"},{"key":"24_CR39","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":"24_CR40","unstructured":"Marin, D., Chang, J.H.R., Ranjan, A., Prabhu, A.K., Rastegari, M., Tuzel, O.: Token pooling in vision transformers. arXiv preprint. arXiv:2110.03860 (2021)"},{"key":"24_CR41","unstructured":"Pan, B., Panda, R., Jiang, Y., Wang, Z., Feris, R., Oliva, A.: IA-RED$$^2$$: interpretability-aware redundancy reduction for vision transformers. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"24_CR42","doi-asserted-by":"crossref","unstructured":"Pan, Z., Zhuang, B., Liu, J., He, H., Cai, J.: Scalable vision transformers with hierarchical pooling. In: IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00043"},{"key":"24_CR43","doi-asserted-by":"crossref","unstructured":"Qiu, Z., Yao, T., Ngo, C.W., Tian, X., Mei, T.: Learning spatio-temporal representation with local and global diffusion. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01233"},{"key":"24_CR44","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K., Doll\u00e1r, P.: Designing network design spaces. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"24_CR45","doi-asserted-by":"crossref","unstructured":"Rao, Y., Lu, J., Lin, J., Zhou, J.: Runtime network routing for efficient image classification. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, pp. 2291-2304 (2019)","DOI":"10.1109\/TPAMI.2018.2878258"},{"key":"24_CR46","unstructured":"Rao, Y., Zhao, W., Liu, B., Lu, J., Zhou, J., Hsieh, C.J.: Dynamicvit: efficient vision transformers with dynamic token sparsification. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"24_CR47","unstructured":"Rao, Y., Zhao, W., Zhu, Z., Lu, J., Zhou, J.: Global filter networks for image classification. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"24_CR48","doi-asserted-by":"crossref","unstructured":"Roy, A., Saffar, M., Vaswani, A., Grangier, D.: Efficient content-based sparse attention with routing transformers. In: Transactions of the Association for Computational Linguistics, vol. 9, pp. 53\u201368 (2021)","DOI":"10.1162\/tacl_a_00353"},{"key":"24_CR49","unstructured":"Ryoo, M.S., Piergiovanni, A., Arnab, A., Dehghani, M., Angelova, A.: Tokenlearner: What can 8 learned tokens do for images and videos? arXiv preprint. arXiv:2106.11297 (2021)"},{"key":"24_CR50","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint. arXiv:1409.1556 (2015)"},{"key":"24_CR51","doi-asserted-by":"crossref","unstructured":"Sukhbaatar, S., Grave, E., Bojanowski, P., Joulin, A.: Adaptive attention span in transformers. In: ACL (2019)","DOI":"10.18653\/v1\/P19-1032"},{"key":"24_CR52","unstructured":"Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning (ICML) (2019)"},{"key":"24_CR53","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., Jegou, H.: Training data-efficient image transformers and distillation through attention. In: International Conference on Machine Learning (ICML) (2021)"},{"key":"24_CR54","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3d convolutional networks. In: IEEE International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"24_CR55","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Feiszli, M.: Video classification with channel-separated convolutional networks. In: IEEE\/CVF International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00565"},{"key":"24_CR56","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., Paluri, M.: A closer look at spatiotemporal convolutions for action recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00675"},{"key":"24_CR57","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (NeuRIPS) (2017)"},{"key":"24_CR58","doi-asserted-by":"crossref","unstructured":"Wang, H., Tran, D., Torresani, L., Feiszli, M.: Video modeling with correlation networks. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00043"},{"key":"24_CR59","doi-asserted-by":"crossref","unstructured":"Wang, K., Liu, Z., Lin, Y., Lin, J., Han, S.: Haq: Hardware-aware automated quantization with mixed precision. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00881"},{"key":"24_CR60","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: IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"24_CR61","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1007\/978-3-030-58598-3_27","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Wang","year":"2020","unstructured":"Wang, X., et al.: AttentionNAS: spatiotemporal attention cell search for video classification. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12353, pp. 449\u2013465. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58598-3_27"},{"key":"24_CR62","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"24_CR63","doi-asserted-by":"crossref","unstructured":"Wu, H., Xiao, B., Codella, N., Liu, M., Dai, X., Yuan, L., Zhang, L.: Cvt: introducing convolutions to vision transformers. In: IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"24_CR64","doi-asserted-by":"crossref","unstructured":"Xu, W., Xu, Y., Chang, T., Tu, Z.: Co-scale conv-attentional image transformers. In: arXiv preprint. arXiv:2104.06399 (2021)","DOI":"10.1109\/ICCV48922.2021.00983"},{"key":"24_CR65","doi-asserted-by":"crossref","unstructured":"Yu, X., Liu, T., Wang, X., Tao, D.: On compressing deep models by low rank and sparse decomposition. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.15"},{"key":"24_CR66","doi-asserted-by":"crossref","unstructured":"Yu, X., Rao, Y., Wang, Z., Liu, Z., Lu, J., Zhou, J.: Pointr: diverse point cloud completion with geometry-aware transformers. In: IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01227"},{"key":"24_CR67","doi-asserted-by":"crossref","unstructured":"Yuan, L., et al.: Tokens-to-token vit: training vision transformers from scratch on imagenet. In: arXiv preprint. arXiv:2101.11986 (2021)","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"24_CR68","doi-asserted-by":"crossref","unstructured":"Yue, X., Sun, S., Kuang, Z., Wei, M., Torr, P., Zhang, W., Lin, D.: Vision transformer with progressive sampling. In: IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00044"},{"key":"24_CR69","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jiang, L., Jia, J., Torr, P., Koltun, V.: Point transformer. In: IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"24_CR70","doi-asserted-by":"crossref","unstructured":"Zheng, S., et al.: Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"24_CR71","unstructured":"Zhou, D., et al.: Deepvit: towards deeper vision transformer. arXiv preprint. arXiv:2103.11886 (2021)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20083-0_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T12:03:08Z","timestamp":1710331388000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20083-0_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200823","9783031200830"],"references-count":71,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20083-0_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"3 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}