{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T15:49:29Z","timestamp":1786981769950,"version":"build-2736575974"},"reference-count":82,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2023,6,9]],"date-time":"2023-06-09T00:00:00Z","timestamp":1686268800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,6,9]],"date-time":"2023-06-09T00:00:00Z","timestamp":1686268800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976094"],"award-info":[{"award-number":["61976094"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2023,10]]},"DOI":"10.1007\/s11263-023-01813-x","type":"journal-article","created":{"date-parts":[[2023,6,9]],"date-time":"2023-06-09T16:29:39Z","timestamp":1686328179000},"page":"2516-2528","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["What Limits the Performance of Local Self-attention?"],"prefix":"10.1007","volume":"131","author":[{"given":"Jingkai","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pichao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiasheng","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rong","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,6,9]]},"reference":[{"key":"1813_CR1","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., & Agarwal, S. (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":"1813_CR2","doi-asserted-by":"crossref","unstructured":"Cai, Z., & Vasconcelos, N. (2018). Cascade r-cnn: Delving into high quality object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 6154\u20146162).","DOI":"10.1109\/CVPR.2018.00644"},{"key":"1813_CR3","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 ECCV.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1813_CR4","unstructured":"Chen, B., Li, P., Li, B., Li, C., Bai, L., Lin, C., Sun, M., Yan, J., & Ouyang, W. (2021a). Psvit: Better vision transformer via token pooling and attention sharing. arXiv preprint arXiv:2108.03428"},{"key":"1813_CR5","unstructured":"Chen, C. F., Panda, R., & Fan, Q. (2021b). Regionvit: Regional-to-local attention for vision transformers. arXiv preprint arXiv:2106.02689"},{"key":"1813_CR6","doi-asserted-by":"crossref","unstructured":"Chen, J., Wang, X., Guo, Z., Zhang, X., & Sun, J. (2021c). Dynamic region-aware convolution. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00797"},{"key":"1813_CR7","unstructured":"Chen, K., Wang, J., Pang, J., Cao, Y., Xiong, Y., Li, X., Sun, S., Feng, W., Liu, Z., Xu, J., Zhang, Z., Cheng, D., Zhu, C., Cheng, T., Zhao, Q., Li, B., Lu, X., Zhu, R., Wu, Y., Dai, J., Wang, J., Shi, J., Ouyang, W., Loy, C. C., & Lin, D. (2019) MMDetection: Openmmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155"},{"key":"1813_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y., Dai, X., Liu, M., Chen, D., Yuan, L., & Liu, Z. (2020). Dynamic convolution: Attention over convolution kernels. In CVPR.","DOI":"10.1109\/CVPR42600.2020.01104"},{"key":"1813_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Y., Dai, X., Chen, D., Liu, M., Dong, X., Yuan, L., & Liu, Z. (2022) Mobile-former: Bridging mobilenet and transformer. In CVPR.","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"1813_CR10","doi-asserted-by":"crossref","unstructured":"Chen, Z., Xie, L., Niu, J., Liu, X., Wei, L., & Tian, Q. (2021d). Visformer: The vision-friendly transformer. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00063"},{"key":"1813_CR11","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhu, Y., Zhao, C., Hu, G., Zeng, W., Wang, J., & Tang, M. (2021e). Dpt: Deformable patch-based transformer for visual recognition. In ACM MM, pp 2899\u20132907","DOI":"10.1145\/3474085.3475467"},{"key":"1813_CR12","doi-asserted-by":"crossref","unstructured":"Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In PAMI.","DOI":"10.1109\/CVPR.2017.195"},{"key":"1813_CR13","unstructured":"Chu, X., Zhang, B., Tian, Z., Wei, X., & Xia, H. (2021). Do we really need explicit position encodings for vision transformers? arXiv preprint arXiv:2102.10882"},{"key":"1813_CR14","unstructured":"Contributors, M. (2020). MMSegmentation: Openmmlab semantic segmentation toolbox and benchmark. https:\/\/github.com\/open-mmlab\/mmsegmentation"},{"key":"1813_CR15","unstructured":"Dai, Z., Liu, H., Le, Q.V., & Tan, M. (2021) Coatnet: Marrying convolution and attention for all data sizes. In NeurIPS"},{"key":"1813_CR16","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 CVPR","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"1813_CR17","unstructured":"Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). Bert: Pre-training of deep bidirectional transformers for language understanding. In NAACL."},{"key":"1813_CR18","doi-asserted-by":"crossref","unstructured":"Dong, X., Bao, J., Chen, D., Zhang, W., Yu, N., Yuan, L., Chen, D., & Guo, B. (2021). Cswin transformer: A general vision transformer backbone with cross-shaped windows. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"1813_CR19","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., & Uszkoreit, J. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. In ICLR"},{"key":"1813_CR20","unstructured":"El-Nouby, A., Touvron, H., Caron, M., Bojanowski, P., Douze, M., Joulin, A., Laptev, I., Neverova, N., Synnaeve, G., & Verbeek, J. (2021) Xcit: Cross-covariance image transformers. In NeurIPS."},{"key":"1813_CR21","unstructured":"Fang, Y., Wang, X., Wu, R., & Liu, W. (2021). What makes for hierarchical vision transformer? arXiv preprint arXiv:2107.02174"},{"key":"1813_CR22","unstructured":"Gong, C., Wang, D., Li, M., Chandra, V., & Liu, Q. (2021). Improve vision transformers training by suppressing over-smoothing. arXiv preprint arXiv:2104.12753"},{"key":"1813_CR23","doi-asserted-by":"crossref","unstructured":"Graham, B., El-Nouby, A., Touvron, H., Stock, P., Joulin, A., J\u00e9gou, H., & Douze, M. (2021). Levit: A vision transformer in convnet\u2019s clothing for faster inference. In ICCV.","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"1813_CR24","doi-asserted-by":"crossref","unstructured":"Gu, J., Kwon, H., Wang, D., Ye, W., Li, M., Chen, Y.H., Lai, L., Chandra, V., & Pan, D. Z. (2021). Hrvit: Multi-scale high-resolution vision transformer. arXiv preprint arXiv:2111.01236","DOI":"10.1109\/CVPR52688.2022.01178"},{"key":"1813_CR25","doi-asserted-by":"crossref","unstructured":"Guo, J., Han, K., Wu, H., Xu, C., Tang, Y., Xu, C., & Wang, Y. (2022). Cmt: Convolutional neural networks meet vision transformers. In CVPR","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"1813_CR26","unstructured":"Han, Q., Fan, Z., Dai, Q., Sun, L., Cheng, M. M., Liu, J., & Wang, J. (2022). On the connection between local attention and dynamic depth-wise convolution. In ICLR"},{"key":"1813_CR27","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In CVPR","DOI":"10.1109\/CVPR.2016.90"},{"key":"1813_CR28","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., & Girshick, R. (2017). Mask r-cnn. In CVPR.","DOI":"10.1109\/ICCV.2017.322"},{"key":"1813_CR29","doi-asserted-by":"crossref","unstructured":"He, S., Luo, H., Wang, P., Wang, F., Li, H., & Jiang, W. (2021). Transreid: Transformer-based object re-identification. In ICCV.","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"1813_CR30","doi-asserted-by":"crossref","unstructured":"Howard, A., Sandler, M., Chu, G., Chen, L. C., Chen, B., Tan, M., Wang, W., Zhu, Y., Pang, R., Vasudevan, V., & Lee, Q. V. (2019). Searching for mobilenetv3. In ICCV.","DOI":"10.1109\/ICCV.2019.00140"},{"key":"1813_CR31","unstructured":"Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861"},{"key":"1813_CR32","unstructured":"Huang, Z., Ben, Y., Luo, G., Cheng, P., Yu, G., & Fu, B. (2021). Shuffle transformer: Rethinking spatial shuffle for vision transformer. arXiv preprint arXiv:2106.03650"},{"key":"1813_CR33","unstructured":"Jia, X., De\u00a0Brabandere, B., Tuytelaars, T., & Gool, L. V. (2016). Dynamic filter networks. In NeurIPS."},{"key":"1813_CR34","unstructured":"Jiang, Z., Hou, Q., Yuan, L., Zhou, D., Jin, X., Wang, A., & Feng, J. (2021). Token labeling: Training a 85.5% top-1 accuracy vision transformer with 56m parameters on imagenet. arXiv preprint arXiv:2104.10858"},{"key":"1813_CR35","doi-asserted-by":"crossref","unstructured":"Li, D., Hu, J., Wang, C., Li, X., She, Q., Zhu, L., Zhang, T., & Chen, Q. (2021a). Involution: Inverting the inherence of convolution for visual recognition. In CVPR.","DOI":"10.1109\/CVPR46437.2021.01214"},{"key":"1813_CR36","unstructured":"Li, J., Yan, Y., Liao, S., Yang, X., & Shao, L. (2021b). Local-to-global self-attention in vision transformers. arXiv preprint arXiv:2107.04735"},{"key":"1813_CR37","unstructured":"Li, S., Chen, X., He, D., & Hsieh, C. J. (2021c). Can vision transformers perform convolution? arXiv preprint arXiv:2111.01353"},{"key":"1813_CR38","unstructured":"Lin, M., & Ye, J. (2016). A non-convex one-pass framework for generalized factorization machine and rank-one matrix sensing. In NeurIPS."},{"key":"1813_CR39","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 ECCV.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1813_CR40","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 ICCV.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1813_CR41","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., & Wei, F. (2022a). Swin transformer v2: Scaling up capacity and resolution. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"1813_CR42","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C. Y., Feichtenhofer, C., Darrell, T., & Xie, S. (2022b). A convnet for the 2020s. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"1813_CR43","unstructured":"Loshchilov, I., & Hutter, F. (2017) Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101"},{"key":"1813_CR44","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. In NeurIPS."},{"key":"1813_CR45","doi-asserted-by":"crossref","unstructured":"Ma, N., Zhang, X., Huang, J., & Sun, J. (2020). Weightnet: Revisiting the design space of weight networks. In ECCV.","DOI":"10.1007\/978-3-030-58555-6_46"},{"key":"1813_CR46","unstructured":"Mehta, S., & Rastegari, M. (2021). Mobilevit: Light-weight, general-purpose, and mobile-friendly vision transformer. arXiv preprint arXiv:2110.02178"},{"key":"1813_CR47","doi-asserted-by":"crossref","unstructured":"Pan, Z., Zhuang, B., He, H., Liu, J., Cai, J. (2022). Less is more: Pay less attention in vision transformers. In AAAI.","DOI":"10.1609\/aaai.v36i2.20099"},{"key":"1813_CR48","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., & Desmaison, A. (2019). Pytorch: An imperative style, high-performance deep learning library. In NeurIPS."},{"issue":"4","key":"1813_CR49","doi-asserted-by":"publisher","first-page":"838","DOI":"10.1137\/0330046","volume":"30","author":"BT Polyak","year":"1992","unstructured":"Polyak, B. T., & Juditsky, A. B. (1992). Acceleration of stochastic approximation by averaging. SIAM Journal on Control and Optimization, 30(4), 838\u2013855.","journal-title":"SIAM Journal on Control and Optimization"},{"key":"1813_CR50","unstructured":"Raghu, M., Unterthiner, T., Kornblith, S., Zhang, C., & Dosovitskiy, A. (2021). Do vision transformers see like convolutional neural networks? In NeurIPS"},{"key":"1813_CR51","unstructured":"Rao, Y., Zhao, W., Tang, Y., Zhou, J., Lim, S. N., & Lu, J. (2022) Hornet: Efficient high-order spatial interactions with recursive gated convolutions. NeurIPS."},{"key":"1813_CR52","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018) Mobilenetv2: Inverted residuals and linear bottlenecks. In CVPR","DOI":"10.1109\/CVPR.2018.00474"},{"key":"1813_CR53","doi-asserted-by":"crossref","unstructured":"Su, H., Jampani, V., Sun, D., Gallo, O., Learned-Miller, E., & Kautz, J. (2019). Pixel-adaptive convolutional neural networks. In CVPR.","DOI":"10.1109\/CVPR.2019.01142"},{"key":"1813_CR54","unstructured":"Sun, P., Cao, J., Jiang, Y., Zhang, R., Xie, E., Yuan, Z., Wang, C., & Luo, P. (2020). Transtrack: Multiple-object tracking with transformer. arXiv preprint arXiv:2012.15460"},{"key":"1813_CR55","unstructured":"Tan, M., Le, Q. (2019). Efficientnet: Rethinking model scaling for convolutional neural networks. In ICML."},{"key":"1813_CR56","unstructured":"Tarvainen, A., & Valpola, H. (2017). Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. In NeurIPS."},{"key":"1813_CR57","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., & J\u00e9gou, H. (2021). Training data-efficient image transformers & distillation through attention. In ICML"},{"key":"1813_CR58","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 NeurIPS."},{"key":"1813_CR59","doi-asserted-by":"crossref","unstructured":"Vaswani, A., Ramachandran, P., Srinivas, A., Parmar, N., Hechtman, B., & Shlens, J. (2021). Scaling local self-attention for parameter efficient visual backbones. In CVPR.","DOI":"10.1109\/CVPR46437.2021.01270"},{"key":"1813_CR60","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, K., Xu, R., Liu, Z., Loy, C. C., & Lin, D. (2019). Carafe: Content-aware reassembly of features. In ICCV.","DOI":"10.1109\/ICCV.2019.00310"},{"key":"1813_CR61","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, K., Xu, R., Liu, Z., Loy, C. C , & Lin, D. (2021a). Carafe++: Unified content-aware reassembly of features. PAMI","DOI":"10.1109\/TPAMI.2021.3074370"},{"key":"1813_CR62","doi-asserted-by":"crossref","unstructured":"Wang, P., Wang, X., Luo, H., Zhou, J., Zhou, Z., Wang, F., Li, H., & Jin, R. (2022a). Scaled relu matters for training vision transformers. In AAAI.","DOI":"10.1609\/aaai.v36i3.20150"},{"key":"1813_CR63","doi-asserted-by":"crossref","unstructured":"Wang, P., Wang, X., Wang, F., Lin, M., Chang, S,. Xie, W., Li, H., & Jin, R. (2022b) Kvt: K-nn attention for boosting vision transformers. In ECCV.","DOI":"10.1007\/978-3-031-20053-3_17"},{"key":"1813_CR64","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Fan, D. P., Song, K., Liang, D., Lu, T., Luo, P., & Shao, L. (2021b). Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In ICCV","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"1813_CR65","unstructured":"Wang, W., Yao, L., Chen, L., Cai, D., He, X., & Liu, W. (2021c). Crossformer: A versatile vision transformer based on cross-scale attention. arXiv preprint arXiv:2108.00154"},{"key":"1813_CR66","doi-asserted-by":"publisher","unstructured":"Wightman, R. (2019). Pytorch image models. https:\/\/github.com\/rwightman\/pytorch-image-models, https:\/\/doi.org\/10.5281\/zenodo.4414861","DOI":"10.5281\/zenodo.4414861"},{"key":"1813_CR67","doi-asserted-by":"crossref","unstructured":"Wu, K., Peng, H., Chen, M., Fu, J., & Chao, H. (2021). Rethinking and improving relative position encoding for vision transformer. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00988"},{"key":"1813_CR68","doi-asserted-by":"crossref","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., & Sun, J. (2018). Unified perceptual parsing for scene understanding. In ECCV","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"1813_CR69","unstructured":"Xiao, T., Singh, M., Mintun, E., Darrell, T., Doll\u00e1r, P., & Girshick, R. (2021). Early convolutions help transformers see better. In NeurIPS."},{"key":"1813_CR70","unstructured":"Yang, B., Bender, G., Le, Q. V., & Ngiam, J. (2019). Condconv: Conditionally parameterized convolutions for efficient inference. In NeurIPS."},{"key":"1813_CR71","unstructured":"Yang, J., Li, C., Zhang, P., Dai, X., Xiao, B., Yuan, L., & Gao, J. (2021). Focal self-attention for local-global interactions in vision transformers. arXiv preprint arXiv:2107.00641"},{"key":"1813_CR72","doi-asserted-by":"crossref","unstructured":"Yuan, L., Chen, Y., Wang, T., Yu, W., Shi, Y., Jiang, Z., Tay, F. E., Feng, J., & Yan, S. (2021a). Tokens-to-token vit: Training vision transformers from scratch on imagenet. In ICCV","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"1813_CR73","doi-asserted-by":"crossref","unstructured":"Yuan, L., Hou, Q., Jiang, Z., Feng, J., & Yan, S. (2022). Volo: Vision outlooker for visual recognition. PAMI.","DOI":"10.1109\/TPAMI.2022.3206108"},{"key":"1813_CR74","unstructured":"Yuan, Y., Fu, R., Huang, L., Lin, W., Zhang, C., Chen, X., & Wang, J. (2021b). Hrformer: High-resolution transformer for dense prediction. In NeurIPS."},{"key":"1813_CR75","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 CVPR.","DOI":"10.1109\/ICCV.2019.00612"},{"key":"1813_CR76","unstructured":"Zhang, H., Cisse, M., Dauphin, Y. N., & Lopez-Paz, D. (2017). Mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412"},{"key":"1813_CR77","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 ICCV","DOI":"10.1109\/ICCV48922.2021.00299"},{"key":"1813_CR78","unstructured":"Zhang, Y., Zhang, J., Wang, Q., & Zhong, Z. (2020). Dynet: Dynamic convolution for accelerating convolutional neural networks. arXiv preprint arXiv:2004.10694"},{"key":"1813_CR79","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 CVPR","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"1813_CR80","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., Puig, X., Fidler, S., Barriuso, A., & Torralba, A. (2017) Scene parsing through ade20k dataset. In CVPR","DOI":"10.1109\/CVPR.2017.544"},{"key":"1813_CR81","unstructured":"Zhou, D., Shi, Y., Kang, B., Yu, W., Jiang, Z., Li, Y., Jin, X., Hou, Q., & Feng, J. (2021a). Refiner: Refining self-attention for vision transformers. arXiv preprint arXiv:2106.03714"},{"key":"1813_CR82","doi-asserted-by":"crossref","unstructured":"Zhou, J., Jampani, V., Pi, Z., Liu, Q., & Yang, M. H. (2021b). Decoupled dynamic filter networks. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00658"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01813-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-023-01813-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-023-01813-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,18]],"date-time":"2023-08-18T22:05:45Z","timestamp":1692396345000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-023-01813-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,9]]},"references-count":82,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2023,10]]}},"alternative-id":["1813"],"URL":"https:\/\/doi.org\/10.1007\/s11263-023-01813-x","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,9]]},"assertion":[{"value":"12 June 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 May 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 June 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}