{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T21:01:22Z","timestamp":1783803682274,"version":"3.55.0"},"reference-count":94,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2024,7,16]],"date-time":"2024-07-16T00:00:00Z","timestamp":1721088000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,7,16]],"date-time":"2024-07-16T00:00:00Z","timestamp":1721088000000},"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":[[2024,12]]},"DOI":"10.1007\/s11263-024-02173-w","type":"journal-article","created":{"date-parts":[[2024,7,16]],"date-time":"2024-07-16T19:01:49Z","timestamp":1721156509000},"page":"6142-6162","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Vision Transformers: From Semantic Segmentation to Dense Prediction"],"prefix":"10.1007","volume":"132","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1031-5420","authenticated-orcid":false,"given":"Li","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiachen","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sixiao","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinxuan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiatian","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanwei","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianfeng","family":"Feng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philip H. S.","family":"Torr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,7,16]]},"reference":[{"key":"2173_CR1","doi-asserted-by":"crossref","unstructured":"Abnar, S., & Zuidema, W. (2020). Quantifying attention flow in transformers. In Annual meeting of the association for computational linguistics, (pp. 4190\u20134197).","DOI":"10.18653\/v1\/2020.acl-main.385"},{"issue":"12","key":"2173_CR2","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan, V., Kendall, A., & Cipolla, R. (2017). Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(12), 2481\u20132495.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2173_CR3","unstructured":"Bai, S., & Torr, P., et\u00a0al. (2021). Visual parser: Representing part-whole hierarchies with transformers. arXiv preprint. arXiv:2107.05790."},{"key":"2173_CR4","unstructured":"Bao, H., Dong, L., Piao, S., & Wei, F. (2022) Beit: Bert pre-training of image transformers. In International conference on learning representations."},{"key":"2173_CR5","doi-asserted-by":"crossref","unstructured":"Bello, I., Zoph, B., Vaswani, A., Shlens, J., & Le, Q.V. (2019). Attention augmented convolutional networks. In IEEE international conference on computer vision, (pp. 10076\u201310085).","DOI":"10.1109\/ICCV.2019.00338"},{"key":"2173_CR6","doi-asserted-by":"crossref","unstructured":"Cao, Y., Xu, J., Lin, S., Wei, F., & Hu, H. (2019). Gcnet: Non-local networks meet squeeze-excitation networks and beyond. In IEEE international conference on computer vision workshops","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"2173_CR7","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020). End-to-end object detection with transformers. In European conference on computer vision, (pp. 213\u2013229).","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2173_CR8","doi-asserted-by":"crossref","unstructured":"Chen, C.-F. R., Fan, Q., & Panda, R. (2021). Crossvit: Cross-attention multi-scale vision transformer for image classification. In IEEE international conference on computer vision, (pp. 357\u2013366).","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"2173_CR9","unstructured":"Chen, C. -F., Panda, R., & Fan, Q. (2022). Regionvit: Regional-to-local attention for vision transformers. In International conference on learning representations."},{"key":"2173_CR10","unstructured":"Chen, L., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2015). Semantic image segmentation with deep convolutional nets and fully connected CRFs. In International conference on learning representations."},{"key":"2173_CR11","unstructured":"Chen, L. -C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2015). Semantic image segmentation with deep convolutional nets and fully connected CRFs. In International conference on learning representations."},{"key":"2173_CR12","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"},{"issue":"4","key":"2173_CR13","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2017","unstructured":"Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2017). Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 40(4), 834\u2013848.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2173_CR14","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In IEEE conference on computer vision and pattern recognition, (pp. 1251\u20131258).","DOI":"10.1109\/CVPR.2017.195"},{"key":"2173_CR15","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. In Advances in Neural Information Processing Systems, (pp. 9355\u20139366)."},{"key":"2173_CR16","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":"2173_CR17","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":"2173_CR18","unstructured":"Dai, Z., Liu, H., Le, Q. V., & Tan, M. (2021) Coatnet: Marrying convolution and attention for all data sizes. In Advances in Neural Information Processing Systems, (pp. 3965\u20133977)."},{"key":"2173_CR19","doi-asserted-by":"crossref","unstructured":"Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q. V., & Salakhutdinov, R. (2019). Transformer-xl: Attentive language models beyond a fixed-length context. In Annual Meeting of the Association for Computational Linguistics, (pp. 2978\u20132988). Association for Computational Linguistics.","DOI":"10.18653\/v1\/P19-1285"},{"key":"2173_CR20","first-page":"16344","volume":"35","author":"T Dao","year":"2022","unstructured":"Dao, T., Fu, D., Ermon, S., Rudra, A., & R\u00e9, C. (2022). Flashattention: Fast and memory-efficient exact attention with io-awareness. Advances in Neural Information Processing Systems, 35, 16344\u201316359.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2173_CR21","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":"2173_CR22","unstructured":"Devlin, J., Chang, M. -W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, (pp. 4171\u20134186). Association for Computational Linguistics."},{"key":"2173_CR23","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. In International conference on learning representations."},{"key":"2173_CR24","doi-asserted-by":"crossref","unstructured":"Fu, J., Liu, J., Tian, H., Fang, Z., & Lu, H. (2019). Dual attention network for scene segmentation. In IEEE conference on computer vision and pattern recognition, (pp. 3146\u20133154).","DOI":"10.1109\/CVPR.2019.00326"},{"key":"2173_CR25","first-page":"15908","volume":"34","author":"K Han","year":"2021","unstructured":"Han, K., Xiao, A., Wu, E., Guo, J., Xu, C., & Wang, Y. (2021). Transformer in transformer. Advances in Neural Information Processing Systems, 34, 15908\u201315919.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2173_CR26","doi-asserted-by":"crossref","unstructured":"Hassani, A., Walton, S., Li, J., Li, S., & Shi, H. (2023). Neighborhood attention transformer. In IEEE conference on computer vision and pattern recognition, (pp. 6185\u20136194).","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"2173_CR27","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":"2173_CR28","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":"2173_CR29","doi-asserted-by":"crossref","unstructured":"Heo, B., Yun, S., Han, D., Chun, S., Choe, J., & Oh, S. J. (2021) Rethinking spatial dimensions of vision transformers. In IEEE international conference on computer vision, (pp. 11936\u201311945).","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"2173_CR30","unstructured":"Ho, J., Kalchbrenner, N., Weissenborn, D., & Salimans, T. (2019). Axial attention in multidimensional transformers. arXiv preprint arXiv:1912.12180."},{"key":"2173_CR31","doi-asserted-by":"crossref","unstructured":"Holschneider, M., Kronland-Martinet, R., Morlet, J., & Tchamitchian, P. (1990). A real-time algorithm for signal analysis with the help of the wavelet transform. In Wavelets: Time-Frequency Methods and Phase Space Proceedings of the International Conference, Marseille, France, December 14\u201318, 1987, (pp. 286\u2013297). Springer.","DOI":"10.1007\/978-3-642-75988-8_28"},{"key":"2173_CR32","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., & Sun, G. (2018) Squeeze-and-excitation networks. In IEEE conference on computer vision and pattern recognition, (pp. 7132\u20137141).","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2173_CR33","doi-asserted-by":"crossref","unstructured":"Hu, H., Zhang, Z., Xie, Z., & Lin, S. (2019). Local relation networks for image recognition. In IEEE international conference on computer vision, (pp. 3464\u20133473).","DOI":"10.1109\/ICCV.2019.00356"},{"key":"2173_CR34","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In IEEE conference on computer vision and pattern recognition, (pp. 4700\u20134708).","DOI":"10.1109\/CVPR.2017.243"},{"key":"2173_CR35","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":"2173_CR36","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Girshick, R., He, K., & Doll\u00e1r, P. (2019). Panoptic feature pyramid networks. In IEEE conference on computer vision and pattern recognition, (pp. 6399\u20136408).","DOI":"10.1109\/CVPR.2019.00656"},{"key":"2173_CR37","unstructured":"Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems25."},{"key":"2173_CR38","unstructured":"Larsson, G., Maire, M., & Shakhnarovich, G. (2016) Fractalnet: Ultra-deep neural networks without residuals. In International conference on learning representations."},{"key":"2173_CR39","doi-asserted-by":"crossref","unstructured":"Li, Z., Liu, X., Drenkow, N., Ding, A., Creighton, F. X., Taylor, R. H., & Unberath, M. (2021). Revisiting stereo depth estimation from a sequence-to-sequence perspective with transformers. In IEEE conference on computer vision and pattern recognition, (pp. 6197\u20136206).","DOI":"10.1109\/ICCV48922.2021.00614"},{"key":"2173_CR40","unstructured":"Li, J., Yan, Y., Liao, S., Yang, X., & Shao, L. (2021). Local-to-global self-attention in vision transformers. arxiv 2021. arXiv preprint arXiv:2107.04735."},{"key":"2173_CR41","unstructured":"Li, Y., Zhang, K., Cao, J., Timofte, R., & Van\u00a0Gool, L. (2021). Localvit: Bringing locality to vision transformers. arXiv preprint. arXiv:2104.05707."},{"key":"2173_CR42","unstructured":"Li, X., Zhang, L., You, A., Yang, M., Yang, K., & Tong, Y. (2019). Global aggregation then local distribution in fully convolutional networks. In British machine vision conference, (p. 244)."},{"key":"2173_CR43","doi-asserted-by":"crossref","unstructured":"Lin, T. -Y., Doll\u00e1r, P., Girshick, R. B., He, K., Hariharan, B., & Belongie, S. J. (2017) Feature pyramid networks for object detection. In IEEE conference on computer vision and pattern recognition, (pp. 2117\u20132125).","DOI":"10.1109\/CVPR.2017.106"},{"key":"2173_CR44","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, 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":"2173_CR45","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":"2173_CR46","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\u00a0al. (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":"2173_CR47","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, X., Luo, P., Loy, C. C., & Tang, X.(2015). Semantic image segmentation via deep parsing network. In IEEE international conference on computer vision, (pp. 1377\u20131385).","DOI":"10.1109\/ICCV.2015.162"},{"key":"2173_CR48","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 IEEE international conference on computer vision, (pp. 10012\u201310022).","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2173_CR49","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":"2173_CR50","doi-asserted-by":"crossref","unstructured":"Liu, R., Yuan, Z., Liu, T., & Xiong, Z. (2021). End-to-end lane shape prediction with transformers. In IEEE winter conference on applications of computer vision, (pp. 3694\u20133702).","DOI":"10.1109\/WACV48630.2021.00374"},{"key":"2173_CR51","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":"2173_CR52","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., Chen, X., Liu, X., Cho, N. -G., Lee, S. -W., Fidler, S., Urtasun, R., & Yuille, A. (2014) The role of context for object detection and semantic segmentation in the wild. In IEEE conference on computer vision and pattern recognition, (pp. 891\u2013898).","DOI":"10.1109\/CVPR.2014.119"},{"key":"2173_CR53","doi-asserted-by":"crossref","unstructured":"Noh, H., Hong, S., & Han, B. (2015). Learning deconvolution network for semantic segmentation. In IEEE international conference on computer vision, (pp. 1520\u20131528).","DOI":"10.1109\/ICCV.2015.178"},{"key":"2173_CR54","unstructured":"OpenMMLab: mmsegmentation. https:\/\/github.com\/open-mmlab\/mmsegmentation (2020)."},{"key":"2173_CR55","doi-asserted-by":"crossref","unstructured":"Peng, C., Zhang, X., Yu, G., Luo, G., & Sun, J. (2017). Large kernel matters\u2013improve semantic segmentation by global convolutional network. In IEEE conference on computer vision and pattern recognition, (pp. 4353\u20134361).","DOI":"10.1109\/CVPR.2017.189"},{"key":"2173_CR56","unstructured":"Ramachandran, P., Parmar, N., Vaswani, A., Bello, I., Levskaya, A., & Shlens, J. (2019). Stand-alone self-attention in vision models. In Advances in Neural Information Processing Systems, (pp. 68\u201380)."},{"key":"2173_CR57","unstructured":"Recht, B., Roelofs, R., Schmidt, L., & Shankar, V. (2019). Do imagenet classifiers generalize to imagenet? In International conference on machine learning, (pp. 5389\u20135400). PMLR."},{"key":"2173_CR58","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In International conference on medical image computing and computer assisted intervention, (pp. 234\u2013241). Springer.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2173_CR59","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015). Imagenet large scale visual recognition challenge. International Journal of Computer Vision, 115, 211\u2013252.","journal-title":"International Journal of Computer Vision"},{"key":"2173_CR60","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In IEEE conference on computer vision and pattern recognition, (pp. 4510\u20134520).","DOI":"10.1109\/CVPR.2018.00474"},{"key":"2173_CR61","unstructured":"Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. In International conference on learning representations."},{"key":"2173_CR62","doi-asserted-by":"crossref","unstructured":"Song, C.H., Han, H.J., & Avrithis, Y. (2022). All the attention you need: Global-local, spatial-channel attention for image retrieval. In IEEE winter conference on applications of computer vision, (pp. 2754\u20132763).","DOI":"10.1109\/WACV51458.2022.00051"},{"key":"2173_CR63","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015). Going deeper with convolutions. In IEEE conference on computer vision and pattern recognition, (pp. 1\u20139).","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"2173_CR64","doi-asserted-by":"crossref","unstructured":"Touvron, H., Cord, M., & J\u00e9gou, H. (2022) Deit iii: Revenge of the vit. In Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXIV, (pp. 516\u2013533). Springer.","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"2173_CR65","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":"2173_CR66","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, \u0141., & Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems, (pp. 5998\u20136008)."},{"key":"2173_CR67","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., & Bengio, Y. (2018). Graph attention networks. In International conference on learning representations."},{"key":"2173_CR68","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":"2173_CR69","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"},{"key":"2173_CR70","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhu, Y., Green, B., Adam, H., Yuille, A., & Chen, L. -C. (2020). Axial-deeplab: Stand-alone axial-attention for panoptic segmentation. In European conference on computer vision, (pp. 108\u2013126). Springer.","DOI":"10.1007\/978-3-030-58548-8_7"},{"issue":"3","key":"2173_CR71","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":"2173_CR72","doi-asserted-by":"crossref","unstructured":"Wu, H., Xiao, B., Codella, N., Liu, M., Dai, X., Yuan, L., & Zhang, L. (2021). Cvt: Introducing convolutions to vision transformers. In IEEE International Conference on Computer Vision, (pp. 22\u201331).","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"2173_CR73","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":"2173_CR74","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":"2173_CR75","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":"2173_CR76","unstructured":"Yan, H., Li, Z., Li, W., Wang, C., Wu, M., & Zhang, C. (2021) Contnet: Why not use convolution and transformer at the same time? arXiv preprint arXiv:2104.13497."},{"key":"2173_CR77","unstructured":"Yang, Z., Dai, Z., Yang, Y., Carbonell, J., Salakhutdinov, R., & Le, Q. V. (2019). Xlnet: Generalized autoregressive pretraining for language understanding. In Advances in Neural Information Processing Systems, (pp. 5754\u20135764)."},{"key":"2173_CR78","unstructured":"Yang, C., Qiao, S., Yu, Q., Yuan, X., Zhu, Y., Yuille, A., Adam, H., & Chen, L.-C. (2022) Moat: Alternating mobile convolution and attention brings strong vision models. In International conference on learning representations."},{"key":"2173_CR79","doi-asserted-by":"crossref","unstructured":"Yang, M., Yu, K., Zhang, C., Li, Z., & Yang, K. (2018). Denseaspp for semantic segmentation in street scenes. In IEEE conference on computer vision and pattern recognition, (pp. 3684\u20133692).","DOI":"10.1109\/CVPR.2018.00388"},{"key":"2173_CR80","unstructured":"Yu, F., & Koltun, V. (2016). Multi-scale context aggregation by dilated convolutions. In International conference on learning representations."},{"key":"2173_CR81","doi-asserted-by":"crossref","unstructured":"Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., & Sang, N. (2018) Bisenet: Bilateral segmentation network for real-time semantic segmentation. In European conference on computer vision, (pp. 325\u2013341).","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"2173_CR82","unstructured":"Yuan, Y., & Wang, J. (2018) Ocnet: Object context network for scene parsing. arXiv preprint. arXiv preprint arXiv:1809.00916."},{"key":"2173_CR83","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). Springer.","DOI":"10.1007\/978-3-030-58539-6_11"},{"key":"2173_CR84","doi-asserted-by":"crossref","unstructured":"Zhang, H., Cisse, M., Dauphin, Y. N., & Lopez-Paz, D. (2017) mixup: Beyond empirical risk minimization. In International conference on learning representations.","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"2173_CR85","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":"2173_CR86","unstructured":"Zhang, L., Li, X., Arnab, A., Yang, K., Tong, Y., & Torr, P.H. (2019). Dual graph convolutional network for semantic segmentation. In British Machine Vision Conference, (p. 254)."},{"key":"2173_CR87","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.","DOI":"10.1109\/CVPR42600.2020.00378"},{"key":"2173_CR88","unstructured":"Zhang, Z., Zhang, H., Zhao, L., Chen, T., & Pfister, T. (2021). Aggregating nested transformers. arXiv preprint. arXiv:2105.12723"},{"key":"2173_CR89","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.","DOI":"10.1109\/CVPR42600.2020.01009"},{"key":"2173_CR90","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":"2173_CR91","doi-asserted-by":"crossref","unstructured":"Zhao, H., Zhang, Y., Liu, S., Shi, J., Change\u00a0Loy, C., Lin, D., & Jia, J. (2018). Psanet: Point-wise spatial attention network for scene parsing. In European conference on computer vision, (pp. 267\u2013283).","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"2173_CR92","doi-asserted-by":"crossref","unstructured":"Zheng, S., Jayasumana, S., Romera-Paredes, B., Vineet, V., Su, Z., Du, D., Huang, C., & Torr, P. H. S. (2015). Conditional random fields as recurrent neural networks. In IEEE international conference on computer vision, (pp. 1529\u20131537).","DOI":"10.1109\/ICCV.2015.179"},{"key":"2173_CR93","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., & Zhang, L. (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":"2173_CR94","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"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02173-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-024-02173-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-024-02173-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T10:29:41Z","timestamp":1731666581000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-024-02173-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,16]]},"references-count":94,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["2173"],"URL":"https:\/\/doi.org\/10.1007\/s11263-024-02173-w","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,16]]},"assertion":[{"value":"11 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 July 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}