{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:23:19Z","timestamp":1772907799090,"version":"3.50.1"},"publisher-location":"Cham","reference-count":64,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730092","type":"print"},{"value":"9783031730108","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,10]],"date-time":"2024-11-10T00:00:00Z","timestamp":1731196800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,10]],"date-time":"2024-11-10T00:00:00Z","timestamp":1731196800000},"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\/978-3-031-73010-8_18","type":"book-chapter","created":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T13:11:57Z","timestamp":1731157917000},"page":"298-317","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Efficient Vision Transformers with\u00a0Partial Attention"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7411-0697","authenticated-orcid":false,"given":"Xuan-Thuy","family":"Vo","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6184-4133","authenticated-orcid":false,"given":"Duy-Linh","family":"Nguyen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1553-7631","authenticated-orcid":false,"given":"Adri","family":"Priadana","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4937-7082","authenticated-orcid":false,"given":"Kang-Hyun","family":"Jo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,10]]},"reference":[{"key":"18_CR1","unstructured":"Bolya, D., Fu, C.Y., Dai, X., Zhang, P., Feichtenhofer, C., Hoffman, J.: Token merging: your ViT but faster. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=JroZRaRw7Eu"},{"key":"18_CR2","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":"18_CR3","unstructured":"Chen, K., et\u00a0al.: MMDetection: open MMLab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Q., et al.: MixFormer: mixing features across windows and dimensions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5249\u20135259 (2022)","DOI":"10.1109\/CVPR52688.2022.00518"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Mobile-former: bridging mobilenet and transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5270\u20135279 (2022)","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"18_CR6","unstructured":"Chu, X., et al.: Twins: revisiting the design of spatial attention in vision transformers. In: Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems (2021). https:\/\/openreview.net\/forum?id=5kTlVBkzSRx"},{"key":"18_CR7","unstructured":"Chu, X., Tian, Z., Zhang, B., Wang, X., Shen, C.: Conditional positional encodings for vision transformers. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=3KWnuT-R1bh"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: RandAugment: practical automated data augmentation with a reduced search space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 702\u2013703 (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"18_CR9","unstructured":"Dai, Z., Liu, H., Le, Q.V., Tan, M.: CoAtNet: marrying convolution and attention for all data sizes. In: Advances in Neural Information Processing Systems, vol. 34, pp. 3965\u20133977 (2021)"},{"key":"18_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":"18_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":"18_CR12","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 (2021). https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"18_CR13","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1007\/978-3-031-20050-2_43","volume-title":"European Conference on Computer Vision 2022","author":"L Gao","year":"2022","unstructured":"Gao, L., Nie, D., Li, B., Ren, X.: Doubly-Fused ViT: fuse information from vision transformer doubly with local representation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13683, pp. 744\u2013761. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20050-2_43"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Grainger, R., Paniagua, T., Song, X., Cuntoor, N., Lee, M.W., Wu, T.: PaCa-ViT: learning patch-to-cluster attention in vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18568\u201318578 (2023)","DOI":"10.1109\/CVPR52729.2023.01781"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Guo, J., et al.: CMT: convolutional neural networks meet vision transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12175\u201312185 (2022)","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dar, G., Goodman, S., Ciprut, D., Berant, J.: Memory-efficient transformers via top-k attention. In: Proceedings of SustaiNLP: Workshop on Simple and Efficient Natural Language Processing. Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.sustainlp-1.5"},{"key":"18_CR17","unstructured":"Hatamizadeh, A., Yin, H., Heinrich, G., Kautz, J., Molchanov, P.: Global context vision transformers. In: International Conference on Machine Learning, pp. 12633\u201312646. PMLR (2023)"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Howard, A., et\u00a0al.: Searching for MobileNetV3. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1314\u20131324 (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"key":"18_CR21","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"18_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1007\/978-3-319-46493-0_39","volume-title":"Computer Vision \u2013 ECCV 2016","author":"G Huang","year":"2016","unstructured":"Huang, G., Sun, Y., Liu, Z., Sedra, D., Weinberger, K.Q.: Deep networks with stochastic depth. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part IV. LNCS, vol. 9908, pp. 646\u2013661. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_39"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Girshick, R., He, K., Doll\u00e1r, P.: Panoptic feature pyramid networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6399\u20136408 (2019)","DOI":"10.1109\/CVPR.2019.00656"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"18_CR25","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, Part V. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Lin, W., Wu, Z., Chen, J., Huang, J., Jin, L.: Scale-aware modulation meet transformer. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00553"},{"key":"18_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","volume-title":"Computer Vision \u2013 ECCV 2016","author":"W Liu","year":"2016","unstructured":"Liu, W., et al.: SSD: single shot multibox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016, Part I. LNCS, vol. 9905, pp. 21\u201337. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Liu, X., Peng, H., Zheng, N., Yang, Y., Hu, H., Yuan, Y.: EfficientViT: memory efficient vision transformer with cascaded group attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14420\u201314430 (2023)","DOI":"10.1109\/CVPR52729.2023.01386"},{"key":"18_CR29","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":"18_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A ConvNet for the 2020s. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"18_CR31","unstructured":"Mehta, S., Rastegari, M.: MobileViT: light-weight, general-purpose, and mobile-friendly vision transformer. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=vh-0sUt8HlG"},{"key":"18_CR32","unstructured":"Mehta, S., Rastegari, M.: Separable self-attention for mobile vision transformers. Trans. Mach. Learn. Res. (2023). https:\/\/openreview.net\/forum?id=tBl4yBEjKi"},{"key":"18_CR33","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, pp. 12309\u201312318 (2022)","DOI":"10.1109\/CVPR52688.2022.01199"},{"key":"18_CR34","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1007\/978-3-031-20083-0_18","volume-title":"European Conference on Computer Vision 2022","author":"J Pan","year":"2022","unstructured":"Pan, J., et al.: EdgeViTs: competing light-weight CNNs on mobile devices with vision transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13671, pp. 294\u2013311. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20083-0_18"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Pan, X., Ye, T., Xia, Z., Song, S., Huang, G.: Slide-transformer: hierarchical vision transformer with local self-attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2082\u20132091 (2023)","DOI":"10.1109\/CVPR52729.2023.00207"},{"key":"18_CR36","unstructured":"Pan, Z., Cai, J., Zhuang, B.: Fast vision transformers with HiLo attention. In: Advances in Neural Information Processing Systems, vol. 35, pp. 14541\u201314554 (2022)"},{"key":"18_CR37","doi-asserted-by":"crossref","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.\u00a036, pp. 2035\u20132043 (2022)","DOI":"10.1609\/aaai.v36i2.20099"},{"key":"18_CR38","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":"18_CR39","doi-asserted-by":"crossref","unstructured":"Ren, S., Zhou, D., He, S., Feng, J., Wang, X.: Shunted self-attention via multi-scale token aggregation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10853\u201310862 (2022)","DOI":"10.1109\/CVPR52688.2022.01058"},{"key":"18_CR40","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C.: MobileNetV2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4510\u20134520 (2018)","DOI":"10.1109\/CVPR.2018.00474"},{"key":"18_CR41","doi-asserted-by":"crossref","unstructured":"Shaker, A., Maaz, M., Rasheed, H., Khan, S., Yang, M.H., Khan, F.S.: SwiftFormer: efficient additive attention for transformer-based real-time mobile vision applications. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 17425\u201317436 (2023)","DOI":"10.1109\/ICCV51070.2023.01598"},{"key":"18_CR42","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"},{"issue":"10","key":"18_CR43","doi-asserted-by":"publisher","first-page":"12635","DOI":"10.1109\/TPAMI.2023.3285569","volume":"45","author":"W Sun","year":"2023","unstructured":"Sun, W., et al.: Vicinity vision transformer. IEEE Trans. Pattern Anal. Mach. Intell. 45(10), 12635\u201312649 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR44","unstructured":"Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"key":"18_CR45","unstructured":"Tang, S., Zhang, J., Zhu, S., Tan, P.: Quadtree attention for vision transformers. In: International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=fR-EnKWL_Zb"},{"key":"18_CR46","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":"18_CR47","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1007\/978-3-031-20053-3_27","volume-title":"European Conference on Computer Vision 2022","author":"Z Tu","year":"2022","unstructured":"Tu, Z., et al.: MaxViT: multi-axis vision transformer. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13684, pp. 459\u2013479. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20053-3_27"},{"key":"18_CR48","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"18_CR49","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1007\/978-3-031-20053-3_17","volume-title":"European Conference on Computer Vision 2022","author":"P Wang","year":"2022","unstructured":"Wang, P., et al.: KVT: $$k$$-NN attention for boosting vision transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13684, pp. 285\u2013302. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20053-3_17"},{"key":"18_CR50","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: 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":"3","key":"18_CR51","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","volume":"8","author":"W Wang","year":"2022","unstructured":"Wang, W., et al.: PVT v2: improved baselines with pyramid vision transformer. Comput. Vis. Media 8(3), 415\u2013424 (2022)","journal-title":"Comput. Vis. Media"},{"key":"18_CR52","doi-asserted-by":"crossref","unstructured":"Woo, S., et al.: ConvNeXt V2: co-designing and scaling ConvNets with masked autoencoders. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16133\u201316142 (2023)","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"18_CR53","doi-asserted-by":"crossref","unstructured":"Xia, Z., Pan, X., Song, S., Li, L.E., Huang, G.: Vision transformer with deformable attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4794\u20134803 (2022)","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"18_CR54","doi-asserted-by":"crossref","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 418\u2013434 (2018)","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"18_CR55","unstructured":"Yang, C., et al.: MOAT: alternating mobile convolution and attention brings strong vision models. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=H0HGljkxQFN"},{"key":"18_CR56","doi-asserted-by":"crossref","unstructured":"Yang, C., et al.: Lite vision transformer with enhanced self-attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11998\u201312008 (2022)","DOI":"10.1109\/CVPR52688.2022.01169"},{"key":"18_CR57","unstructured":"Yang, J., et al.: Focal attention for long-range interactions in vision transformers. In: Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems (2021). https:\/\/openreview.net\/forum?id=2zCRcTafea"},{"key":"18_CR58","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., Yoo, Y.: CutMix: regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6023\u20136032 (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"18_CR59","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: beyond empirical risk minimization. arXiv preprint arXiv:1710.09412 (2017)"},{"key":"18_CR60","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Rethinking mobile block for efficient attention-based models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 1389\u20131400 (2023)","DOI":"10.1109\/ICCV51070.2023.00134"},{"key":"18_CR61","unstructured":"Zhang, Q., Yang, Y.B.: ResT: an efficient transformer for visual recognition. In: Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems (2021). https:\/\/openreview.net\/forum?id=6Ab68Ip4Mu"},{"key":"18_CR62","unstructured":"Zhang, Q., Yang, Y.B.: ResT V2: simpler, faster and stronger. In: Advances in Neural Information Processing Systems, vol. 35, pp. 36440\u201336452 (2022)"},{"key":"18_CR63","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2019","unstructured":"Zhou, B., et al.: Semantic understanding of scenes through the ADE20K dataset. Int. J. Comput. Vis. 127, 302\u2013321 (2019)","journal-title":"Int. J. Comput. Vis."},{"key":"18_CR64","doi-asserted-by":"crossref","unstructured":"Zhu, L., Wang, X., Ke, Z., Zhang, W., Lau, R.W.: BiFormer: vision transformer with bi-level routing attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10323\u201310333 (2023)","DOI":"10.1109\/CVPR52729.2023.00995"}],"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\/978-3-031-73010-8_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T14:05:56Z","timestamp":1731161156000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73010-8_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,10]]},"ISBN":["9783031730092","9783031730108"],"references-count":64,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73010-8_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,10]]},"assertion":[{"value":"10 November 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"}}]}}