{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T19:08:35Z","timestamp":1791486515222,"version":"4.3.4"},"reference-count":72,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T00:00:00Z","timestamp":1710288000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T00:00:00Z","timestamp":1710288000000},"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":["Int J Comput Vis"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1007\/s11263-024-02035-5","type":"journal-article","created":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T20:40:20Z","timestamp":1710362420000},"page":"3355-3374","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Softmax-Free Linear Transformers"],"prefix":"10.1007","volume":"132","author":[{"given":"Jiachen","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junge","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiatian","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianfeng","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1031-5420","authenticated-orcid":false,"given":"Li","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,13]]},"reference":[{"key":"2035_CR1","unstructured":"Ba, J.L., Kiros, J.R. & Hinton, G.E. (2016). Layer normalization. arXiv preprint arXiv:1607.06450"},{"key":"2035_CR2","unstructured":"Bello, I. (2021). Lambdanetworks: Modeling long-range interactions without attention. In International conference on learning representations."},{"issue":"3","key":"2035_CR3","doi-asserted-by":"publisher","first-page":"410","DOI":"10.1137\/0703035","volume":"3","author":"A Ben-Israel","year":"1966","unstructured":"Ben-Israel, A., & Cohen, D. (1966). On iterative computation of generalized inverses and associated projections. SIAM Journal on Numerical Analysis, 3(3), 410\u2013419.","journal-title":"SIAM Journal on Numerical Analysis"},{"key":"2035_CR4","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020). Language models are few-shot learners. Advances in Neural Information Processing Systems, 33, 1877\u20131901.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2035_CR5","unstructured":"Chen, K., Wang, J., Pang, J., Cao, Y., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Xu, J., et al. (2019). Mmdetection: Open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155"},{"key":"2035_CR6","doi-asserted-by":"crossref","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F. & Adam, H. (2018). Encoder-decoder with atrous separable convolution for semantic image segmentation. In European conference on computer vision (pp. 801\u2013818).","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"2035_CR7","unstructured":"Cheng, J., Grossman, M. & McKercher, T. (2014). Professional CUDA C Programming."},{"key":"2035_CR8","unstructured":"Choromanski, K., Likhosherstov, V., Dohan, D., Song, X., Gane, A., Sarlos, T., Hawkins, P., Davis, J., Mohiuddin, A., Kaiser, L., et al. (2021). Rethinking attention with performers. In International conference on learning representations."},{"key":"2035_CR9","first-page":"9355","volume":"34","author":"X Chu","year":"2021","unstructured":"Chu, X., Tian, Z., Wang, Y., Zhang, B., Ren, H., Wei, X., Xia, H., & Shen, C. (2021). Twins: Revisiting the design of spatial attention in vision transformers. Advances in Neural Information Processing Systems, 34, 9355\u20139366.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2035_CR10","doi-asserted-by":"crossref","unstructured":"Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S. & Schiele, B. (2016). The cityscapes dataset for semantic urban scene understanding. In IEEE conference on computer vision and pattern recognition (pp. 3213\u20133223).","DOI":"10.1109\/CVPR.2016.350"},{"key":"2035_CR11","first-page":"3965","volume":"34","author":"Z Dai","year":"2021","unstructured":"Dai, Z., Liu, H., Le, Q. V., & Tan, M. (2021). Coatnet: Marrying convolution and attention for all data sizes. Advances in Neural Information Processing Systems, 34, 3965\u20133977.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2035_CR12","doi-asserted-by":"crossref","unstructured":"d\u2019Ascoli, S., Touvron, H., Leavitt, M.L., Morcos, A.S., Biroli, G. & Sagun, L. (2021). Convit: Improving vision transformers with soft convolutional inductive biases. In International conference on machine learning (pp. 2286\u20132296). PMLR.","DOI":"10.1088\/1742-5468\/ac9830"},{"key":"2035_CR13","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K. & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In IEEE conference on computer vision and pattern recognition (pp. 248\u2013255).","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"2035_CR14","unstructured":"Devlin, J., Chang, M.-W., Lee, K. & Toutanova, K. (2019). Bert: Pre-training of deep bidirectional transformers for language understanding. In Conference of the North American chapter of the association for computational linguistics: human language technologies, NAACL-HLT (pp. 4171\u20134186). Association for Computational Linguistics."},{"key":"2035_CR15","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. In International conference on learning representations."},{"key":"2035_CR16","first-page":"21","volume":"4","author":"GE Fasshauer","year":"2011","unstructured":"Fasshauer, G. E. (2011). Positive definite kernels: Past, present and future. Dolomites Research Notes on Approximation, 4, 21\u201363.","journal-title":"Dolomites Research Notes on Approximation"},{"key":"2035_CR17","unstructured":"Geng, Z., Guo, M.-H., Chen, H., Li, X., Wei, K. & Lin, Z. (2021). Is attention better than matrix decomposition? In International conference on learning representations."},{"issue":"5","key":"2035_CR18","first-page":"5436","volume":"45","author":"M-H Guo","year":"2022","unstructured":"Guo, M.-H., Liu, Z.-N., Mu, T.-J., & Hu, S.-M. (2022). Beyond self-attention: External attention using two linear layers for visual tasks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(5), 5436\u20135447.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2035_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P. & Girshick, R. (2017). Mask r-cnn. In IEEE international conference on computer vision (pp. 2961\u20132969).","DOI":"10.1109\/ICCV.2017.322"},{"key":"2035_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. (2016). Deep residual learning for image recognition. In IEEE conference on computer vision and pattern recognition (pp. 770\u2013778).","DOI":"10.1109\/CVPR.2016.90"},{"key":"2035_CR21","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y. & Liu, W. (2019). Ccnet: Criss-cross attention for semantic segmentation. In IEEE international conference on computer vision (pp. 603\u2013612).","DOI":"10.1109\/ICCV.2019.00069"},{"key":"2035_CR22","unstructured":"Ioffe, S. & Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning (pp. 448\u2013456). pmlr"},{"key":"2035_CR23","unstructured":"Jaegle, A., Gimeno, F., Brock, A., Vinyals, O., Zisserman, A. & Carreira, J. (2021). Perceiver: General perception with iterative attention. In International conference on machine learning (pp. 4651\u20134664). PMLR."},{"key":"2035_CR24","doi-asserted-by":"crossref","unstructured":"Kasai, J., Peng, H., Zhang, Y., Yogatama, D., Ilharco, G., Pappas, N., Mao, Y., Chen, W. & Smith, N.A. (2021). Finetuning pretrained transformers into rnns. In Conference on empirical methods in natural language processing (pp. 10630\u201310643).","DOI":"10.18653\/v1\/2021.emnlp-main.830"},{"key":"2035_CR25","unstructured":"Katharopoulos, A., Vyas, A., Pappas, N. & Fleuret, F. (2020). Transformers are rnns: Fast autoregressive transformers with linear attention. In International conference on machine learning (pp. 5156\u20135165). PMLR."},{"key":"2035_CR26","unstructured":"Kitaev, N., Kaiser, \u0141. & Levskaya, A. (2020). Reformer: The efficient transformer. In International conference on learning representations."},{"key":"2035_CR27","unstructured":"Krizhevsky, A., Hinton, G., et al. (2009). Learning multiple layers of features from tiny images."},{"key":"2035_CR28","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K. & Doll\u00e1r, P. (2017). Focal loss for dense object detection. In IEEE international conference on computer vision (pp. 2980\u20132988).","DOI":"10.1109\/ICCV.2017.324"},{"key":"2035_CR29","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P. & Zitnick, C.L. (2014). Microsoft coco: Common objects in context. In European conference on computer vision (pp. 740\u2013755). Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2035_CR30","doi-asserted-by":"crossref","unstructured":"Liu, Z., Hu, H., Lin, Y., Yao, Z., Xie, Z., Wei, Y., Ning, J., Cao, Y., Zhang, Z., Dong, L., et al. (2022). Swin transformer v2: Scaling up capacity and resolution. In IEEE conference on computer vision and pattern recognition (pp. 12009\u201312019).","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"2035_CR31","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S. & Guo, B. (2021). Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 10012\u201310022).","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2035_CR32","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T. & Xie, S. (2022). A convnet for the 2020s. In IEEE conference on computer vision and pattern recognition (pp. 11976\u201311986).","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"2035_CR33","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E. & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. In IEEE conference on computer vision and pattern recognition (pp. 3431\u20133440).","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"2035_CR34","first-page":"21297","volume":"34","author":"J Lu","year":"2021","unstructured":"Lu, J., Yao, J., Zhang, J., Zhu, X., Xu, H., Gao, W., Xu, C., Xiang, T., & Zhang, L. (2021). Soft: Softmax-free transformer with linear complexity. Advances in Neural Information Processing Systems, 34, 21297\u201321309.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2035_CR35","unstructured":"Maas, A., Daly, R.E., Pham, P.T., Huang, D., Ng, A.Y. & Potts, C. (2011). Learning word vectors for sentiment analysis. In Proceedings of the 49th annual meeting of the association for computational linguistics: Human language technologies (pp. 142\u2013150)."},{"key":"2035_CR36","unstructured":"Mindspore: https:\/\/www.mindspore.cn\/ (2020)"},{"key":"2035_CR37","doi-asserted-by":"crossref","unstructured":"Nangia, N. & Bowman, S.R. (2018). Listops: A diagnostic dataset for latent tree learning. In Conference of the North American chapter of the association for computational linguistics, student research workshop (pp. 92\u201399).","DOI":"10.18653\/v1\/N18-4013"},{"key":"2035_CR38","unstructured":"Peng, H., Pappas, N., Yogatama, D., Schwartz, R., Smith, N.A. & Kong, L. (2021). Random feature attention. In International conference on learning representations."},{"key":"2035_CR39","doi-asserted-by":"publisher","first-page":"919","DOI":"10.1007\/s10579-012-9211-2","volume":"47","author":"DR Radev","year":"2013","unstructured":"Radev, D. R., Muthukrishnan, P., Qazvinian, V., & Abu-Jbara, A. (2013). The acl anthology network corpus. Language Resources and Evaluation, 47, 919\u2013944.","journal-title":"Language Resources and Evaluation"},{"key":"2035_CR40","doi-asserted-by":"crossref","unstructured":"Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K. & Doll\u00e1r, P. (2020). Designing network design spaces. In IEEE conference on computer vision and pattern recognition (pp. 10428\u201310436).","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"2035_CR41","unstructured":"Sun, S., Yue, X., Bai, S. & Torr, P. (2021). Visual parser: Representing part-whole hierarchies with transformers. arXiv preprint arXiv:2107.05790"},{"key":"2035_CR42","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J. & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In IEEE conference on computer vision and pattern recognition (pp. 2818\u20132826).","DOI":"10.1109\/CVPR.2016.308"},{"key":"2035_CR43","unstructured":"Tay, Y., Dehghani, M., Abnar, S., Shen, Y., Bahri, D., Pham, P., Rao, J., Yang, L., Ruder, S. & Metzler, D. (2020). Long range arena: A benchmark for efficient transformers. In International conference on learning representations."},{"issue":"6","key":"2035_CR44","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1145\/3530811","volume":"55","author":"Y Tay","year":"2023","unstructured":"Tay, Y., Dehghani, M., Bahri, D., & Metzler, D. (2023). Efficient transformers: A survey. ACM Computing Surveys, 55(6), 109\u2013110928.","journal-title":"ACM Computing Surveys"},{"key":"2035_CR45","doi-asserted-by":"crossref","unstructured":"Touvron, H., Cord, M. & J\u00e9gou, H. (2022). Deit iii: Revenge of the vit. In European conference on computer vision (pp. 516\u2013533).","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"2035_CR46","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A. & J\u00e9gou, H. (2021). Training data-efficient image transformers & distillation through attention. In International conference on machine learning (pp. 10347\u201310357). PMLR."},{"key":"2035_CR47","doi-asserted-by":"crossref","unstructured":"Touvron, H., Cord, M., Sablayrolles, A., Synnaeve, G. & J\u00e9gou, H. (2021). Going deeper with image transformers. In IEEE conference on computer vision and pattern recognition (pp. 32\u201342).","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"2035_CR48","doi-asserted-by":"crossref","unstructured":"Tsai, Y.-H.H., Bai, S., Yamada, M., Morency, L.-P. & Salakhutdinov, R. (2019). Transformer dissection: A unified understanding of transformer\u2019s attention via the lens of kernel. In Conference on empirical methods in natural language processing and international joint conference on natural language processing (EMNLP-IJCNLP) (pp. 4344\u20134353).","DOI":"10.18653\/v1\/D19-1443"},{"key":"2035_CR49","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141. & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems30"},{"key":"2035_CR50","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1007\/s11222-007-9033-z","volume":"17","author":"U Von Luxburg","year":"2007","unstructured":"Von Luxburg, U. (2007). A tutorial on spectral clustering. Statistics and Computing, 17, 395\u2013416.","journal-title":"Statistics and Computing"},{"key":"2035_CR51","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A. & He, K. (2018). Non-local neural networks. In IEEE conference on computer vision and pattern recognition (pp. 7794\u20137803).","DOI":"10.1109\/CVPR.2018.00813"},{"key":"2035_CR52","unstructured":"Wang, S., Li, B.Z., Khabsa, M., Fang, H. & Ma, H. (2020). Linformer: Self-attention with linear complexity. arXiv preprint arXiv:2006.04768"},{"key":"2035_CR53","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Fan, D.-P., Song, K., Liang, D., Lu, T., Luo, P. & Shao, L. (2021). Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In IEEE international conference on computer vision (pp. 568\u2013578).","DOI":"10.1109\/ICCV48922.2021.00061"},{"issue":"3","key":"2035_CR54","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","volume":"8","author":"W Wang","year":"2022","unstructured":"Wang, W., Xie, E., Li, X., Fan, D.-P., Song, K., Liang, D., Lu, T., Luo, P., & Shao, L. (2022). Pvt v2: Improved baselines with pyramid vision transformer. Computational Visual Media, 8(3), 415\u2013424.","journal-title":"Computational Visual Media"},{"key":"2035_CR55","unstructured":"Wightman, R. (2019). PyTorch Image Models. https:\/\/github.com\/rwightman\/pytorch-image-models"},{"key":"2035_CR56","unstructured":"Williams, C. & Seeger, M. (2000). Using the nystr\u00f6m method to speed up kernel machines. Advances in Neural Information Processing Systems13."},{"key":"2035_CR57","doi-asserted-by":"crossref","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J. (2018). Unified perceptual parsing for scene understanding. In European conference on computer vision (pp. 418\u2013434).","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"2035_CR58","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z., He, K. (2017). Aggregated residual transformations for deep neural networks. In IEEE conference on computer vision and pattern recognition (pp. 1492\u20131500).","DOI":"10.1109\/CVPR.2017.634"},{"key":"2035_CR59","doi-asserted-by":"publisher","first-page":"14138","DOI":"10.1609\/aaai.v35i16.17664","volume":"35","author":"Y Xiong","year":"2021","unstructured":"Xiong, Y., Zeng, Z., Chakraborty, R., Tan, M., Fung, G., Li, Y., & Singh, V. (2021). Nystr\u00f6mformer: A nystr\u00f6m-based algorithm for approximating self-attention. AAAI Conference on Artificial Intelligence, 35, 14138\u201314148.","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"2035_CR60","doi-asserted-by":"crossref","unstructured":"Xu, W., Xu, Y., Chang, T. & Tu, Z. (2021). Co-scale conv-attentional image transformers. In Proceedings of the IEEE\/CVF international conference on computer vision (pp. 9981\u20139990).","DOI":"10.1109\/ICCV48922.2021.00983"},{"key":"2035_CR61","unstructured":"Yoshida, Y. & Miyato, T. (2017). Spectral norm regularization for improving the generalizability of deep learning. arXiv preprint arXiv:1705.10941"},{"key":"2035_CR62","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Chen, X. & Wang, J. (2020). Object-contextual representations for semantic segmentation. In European conference on computer vision (pp. 173\u2013190).","DOI":"10.1007\/978-3-030-58539-6_11"},{"key":"2035_CR63","doi-asserted-by":"crossref","unstructured":"Yuan, L., Chen, Y., Wang, T., Yu, W., Shi, Y., Jiang, Z.-H., Tay, F.E., Feng, J. & Yan, S. (2021). Tokens-to-token vit: Training vision transformers from scratch on imagenet. In IEEE international conference on computer vision (pp. 558\u2013567).","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"2035_CR64","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J. & Yoo, Y. (2019). Cutmix: Regularization strategy to train strong classifiers with localizable features. In IEEE international conference on computer vision (pp. 6023\u20136032).","DOI":"10.1109\/ICCV.2019.00612"},{"key":"2035_CR65","unstructured":"Zhang, H., Ciss\u00e9, M., Dauphin, Y.N. & Lopez-Paz, D. (2018). mixup: Beyond empirical risk minimization. In International conference on learning representations."},{"key":"2035_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, P., Dai, X., Yang, J., Xiao, B., Yuan, L., Zhang, L. & Gao, J. (2021). Multi-scale vision longformer: A new vision transformer for high-resolution image encoding. In IEEE international conference on computer vision (pp. 2998\u20133008).","DOI":"10.1109\/ICCV48922.2021.00299"},{"key":"2035_CR67","doi-asserted-by":"crossref","unstructured":"Zhang, L., Xu, D., Arnab, A. & Torr, P.H. (2020). Dynamic graph message passing networks. In IEEE conference on computer vision and pattern recognition (pp. 3726\u20133735).","DOI":"10.1109\/CVPR42600.2020.00378"},{"key":"2035_CR68","doi-asserted-by":"crossref","unstructured":"Zhao, H., Jia, J. & Koltun, V. (2020). Exploring self-attention for image recognition. In IEEE conference on computer vision and pattern recognition (pp. 10076\u201310085).","DOI":"10.1109\/CVPR42600.2020.01009"},{"key":"2035_CR69","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X. & Jia, J. (2017). Pyramid scene parsing network. In IEEE conference on computer vision and pattern recognition (pp. 2881\u20132890).","DOI":"10.1109\/CVPR.2017.660"},{"key":"2035_CR70","doi-asserted-by":"crossref","unstructured":"Zheng, S., Lu, J., Zhao, H., Zhu, X., Luo, Z., Wang, Y., Fu, Y., Feng, J., Xiang, T., Torr, P.H., et al. (2021). Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In IEEE conference on computer vision and pattern recognition (pp. 6881\u20136890).","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"2035_CR71","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/s11263-018-1140-0","volume":"127","author":"B Zhou","year":"2019","unstructured":"Zhou, B., Zhao, H., Puig, X., Xiao, T., Fidler, S., Barriuso, A., & Torralba, A. (2019). Semantic understanding of scenes through the ade20k dataset. International Journal of Computer Vision, 127, 302\u2013321.","journal-title":"International Journal of Computer Vision"},{"key":"2035_CR72","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X. & Dai, J. (2021). Deformable detr: Deformable transformers for end-to-end object detection. In International conference on learning representations."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02035-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02035-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02035-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T14:32:49Z","timestamp":1720708369000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02035-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,13]]},"references-count":72,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["2035"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02035-5","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,13]]},"assertion":[{"value":"14 July 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 February 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 March 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}