{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T04:25:37Z","timestamp":1785212737119,"version":"3.55.0"},"publisher-location":"Singapore","reference-count":53,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819609710","type":"print"},{"value":"9789819609727","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T00:00:00Z","timestamp":1733788800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T00:00:00Z","timestamp":1733788800000},"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\/978-981-96-0972-7_26","type":"book-chapter","created":{"date-parts":[[2024,12,9]],"date-time":"2024-12-09T08:06:05Z","timestamp":1733731565000},"page":"445-462","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["DeBiFormer: Vision Transformer with\u00a0Deformable Agent Bi-level Routing Attention"],"prefix":"10.1007","author":[{"given":"NguyenHuu","family":"BaoLong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenyu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuzhi","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tsubasa","family":"Hirakawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takayoshi","family":"Yamashita","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tohgoroh","family":"Matsui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hironobu","family":"Fujiyoshi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,10]]},"reference":[{"key":"26_CR1","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Proceedings of the IEEE\/CVF European Conference on Computer Vision (ECCV) (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"26_CR2","unstructured":"Chen, C.F., Panda, R., Fan, Q.: Regionvit: Regional-to-local attention for vision transformers. arXiv preprint arXiv:2106.02689 (2021)"},{"key":"26_CR3","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.: MMDetection: Open mmlab detection toolbox and benchmark. arXiv preprint arXiv:1906.07155 (2019)"},{"key":"26_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Q., Wu, Q., Wang, J., Hu, Q., Hu, T., Ding, E., Cheng, J., Wang, J.: Mixformer: Mixing features across windows and dimensions (2022)","DOI":"10.1109\/CVPR52688.2022.00518"},{"key":"26_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Z., Zhu, Y., Zhao, C., Hu, G., Zeng, W., Wang, J., Tang, M.: Dpt: Deformable patch-based transformer for visual recognition. In: Proceedings of the ACM International Conference on Multimedia (2021)","DOI":"10.1145\/3474085.3475467"},{"key":"26_CR6","unstructured":"Child, R., Gray, S., Radford, A., Sutskever, I.: Generating long sequences with sparse transformers. URL https:\/\/openai.com\/blog\/sparse-transformers (2019)"},{"key":"26_CR7","unstructured":"Chu, X., Tian, Z., Wang, Y., Zhang, B., Ren, H., Wei, X., Xia, H., Shen, C.: Twins: Revisiting the design of spatial attention in vision transformers. In: NeurIPS 2021 (2021), https:\/\/openreview.net\/forum?id=5kTlVBkzSRx"},{"key":"26_CR8","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.: Randaugment: Practical automated data augmentation with a reduced search space. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems. vol.\u00a033, pp. 18613\u201318624. Curran Associates, Inc. (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"26_CR9","doi-asserted-by":"crossref","unstructured":"Dai, Z., Yang, Z., Yang, Y., Carbonell, J., Le, Q.V., Salakhutdinov, R.: Transformer-xl: Attentive language models beyond a fixed-length context (2019)","DOI":"10.18653\/v1\/P19-1285"},{"key":"26_CR10","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"26_CR11","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, Y., Ge, Y., Zhao, S., Song, L., Yue, X., Shan, Y.: Unireplknet: A universal perception large-kernel convnet for audio, video, point cloud, time-series and image recognition. arXiv preprint arXiv:2311.15599 (2023)","DOI":"10.1109\/CVPR52733.2024.00527"},{"key":"26_CR12","unstructured":"Dong, K., Xue, J., Lan, X., Lu, K.: Biunet: Towards more effective unet with bi-level routing attention. In: The British Machine Vision Conference (November 2023)"},{"key":"26_CR13","doi-asserted-by":"crossref","unstructured":"Dong, X., Bao, J., Chen, D., Zhang, W., Yu, N., Yuan, L., Chen, D., Guo, B.: Cswin transformer: A general vision transformer backbone with cross-shaped windows. In: Proceedings of the IEEE\/CVF Computer Vision and Pattern Recognition Conference (CVPR). pp. 12124\u201312134 (2022)","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"26_CR14","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.: An image is worth 16x16 words: Transformers for image recognition at scale. ICLR (2021)"},{"key":"26_CR15","unstructured":"Girshick, R., Radosavovic, I., Gkioxari, G., Doll\u00e1r, P., He, K.: Focal loss for dense object detection. https:\/\/github.com\/facebookresearch\/detectron (2018)"},{"key":"26_CR16","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: LVIS: A dataset for large vocabulary instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"26_CR17","doi-asserted-by":"crossref","unstructured":"Han, D., Ye, T., Han, Y., Xia, Z., Song, S., Huang, G.: Agent attention: On the integration of softmax and linear attention. arXiv preprint arXiv:2312.08874 (2023)","DOI":"10.1007\/978-3-031-72973-7_8"},{"key":"26_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"26_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition (2015)","DOI":"10.1109\/CVPR.2016.90"},{"key":"26_CR20","unstructured":"Ho, J., Kalchbrenner, N., Weissenborn, D., Salimans, T.: Axial attention in multidimensional transformers (2019)"},{"key":"26_CR21","unstructured":"Hou, Q., Lu, C.Z., Cheng, M.M., Feng, J.: Conv2former: A simple transformer-style convnet for visual recognition. arXiv preprint arXiv:2211.11943 (2022)"},{"key":"26_CR22","doi-asserted-by":"crossref","unstructured":"Huang, G., Sun, Y., Liu, Z., Sedra, D., Weinberger, K.: Deep networks with stochastic depth (2016)","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"26_CR23","doi-asserted-by":"crossref","unstructured":"Jiao, J., Tang, Y.M., Lin, K.Y., Gao, Y., Ma, J., Wang, Y., Zheng, W.S.: Dilateformer: Multi-scale dilated transformer for visual recognition. IEEE Transactions on Multimedia (2023)","DOI":"10.1109\/TMM.2023.3243616"},{"key":"26_CR24","unstructured":"Lan, L., Cai, P., Jiang, L., Liu, X., Li, Y., Zhang, Y.: Brau-net++: U-shaped hybrid cnn-transformer network for medical image segmentation. arXiv preprint arXiv:2401.00722 (2024)"},{"key":"26_CR25","unstructured":"Li, K., Wang, Y., Gao, P., Song, G., Liu, Y., Li, H., Qiao, Y.: Uniformer: Unified transformer for efficient spatiotemporal representation learning (2022)"},{"key":"26_CR26","unstructured":"Liu, S., Chen, T., Chen, X., Chen, X., Xiao, Q., Wu, B., Pechenizkiy, M., Mocanu, D., Wang, Z.: More convnets in the 2020s: Scaling up kernels beyond 51x51 using sparsity. arXiv preprint arXiv:2207.03620 (2022)"},{"key":"26_CR27","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., Guo, B.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"26_CR28","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 (CVPR). pp. 11976\u201311986 (June 2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"26_CR29","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization (2017)"},{"key":"26_CR30","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 (CVPR). pp. 2082\u20132091 (June 2023)","DOI":"10.1109\/CVPR52729.2023.00207"},{"key":"26_CR31","doi-asserted-by":"crossref","unstructured":"Ren, S., Zhou, D., He, S., Feng, J., Wang, X.: Shunted self-attention via multi-scale token aggregation (2021)","DOI":"10.1109\/CVPR52688.2022.01058"},{"issue":"3","key":"26_CR32","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., Berg, A.C., Fei-Fei, L.: ImageNet Large Scale Visual Recognition Challenge. Int. J. Comput. Vision 115(3), 211\u2013252 (2015). https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int. J. Comput. Vision"},{"key":"26_CR33","doi-asserted-by":"publisher","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: Visual explanations from deep networks via gradient-based localization (2016) https:\/\/doi.org\/10.1007\/s11263-019-01228-7","DOI":"10.1007\/s11263-019-01228-7"},{"key":"26_CR34","unstructured":"Tang, S., Zhang, J., Zhu, S., Tan, P.: Quadtree attention for vision transformers. ICLR (2022)"},{"key":"26_CR35","unstructured":"Tolstikhin, I., Houlsby, N., Kolesnikov, A., Beyer, L., Zhai, X., Unterthiner, T., Yung, J., Steiner, A., Keysers, D., Uszkoreit, J., Lucic, M., Dosovitskiy, A.: Mlp-mixer: An all-mlp architecture for vision. arXiv preprint arXiv:2105.01601 (2021)"},{"key":"26_CR36","unstructured":"Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., Jegou, H.: Training data-efficient image transformers distillation through attention. In: International Conference on Machine Learning. vol.\u00a0139, pp. 10347\u201310357 (July 2021)"},{"key":"26_CR37","doi-asserted-by":"crossref","unstructured":"Tu, Z., Talebi, H., Zhang, H., Yang, F., Milanfar, P., Bovik, A., Li, Y.: Maxvit: Multi-axis vision transformer. ECCV (2022)","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"26_CR38","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L.u., Polosukhin, I.: Attention is all you need. In: Guyon, I., Von\u00a0Luxburg, U., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Advances in Neural Information Processing Systems. vol.\u00a030. Curran Associates, Inc. (2017)"},{"key":"26_CR39","unstructured":"Wang, S., Li, B.Z., Khabsa, M., Fang, H., Ma, H.: Linformer: Self-attention with linear complexity (2020)"},{"key":"26_CR40","doi-asserted-by":"crossref","unstructured":"Wang, W., Dai, J., Chen, Z., Huang, Z., Li, Z., Zhu, X., Hu, X., Lu, T., Lu, L., Li, H., et\u00a0al.: Internimage: Exploring large-scale vision foundation models with deformable convolutions. arXiv preprint arXiv:2211.05778 (2022)","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"26_CR41","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Fan, D.P., Song, K., Liang, D., Lu, T., Luo, P., Shao, L.: Pyramid vision transformer: A versatile backbone for dense prediction without convolutions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV). pp. 568\u2013578 (2021)","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"26_CR42","unstructured":"Wang, W., Yao, L., Chen, L., Lin, B., Cai, D., He, X., Liu, W.: Crossformer: A versatile vision transformer hinging on cross-scale attention. In: Proceedings of the International Conference on Learning Representations (ICLR) (2022), https:\/\/openreview.net\/forum?id=_PHymLIxuI"},{"key":"26_CR43","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.Y., Girshick, R.: Detectron2. https:\/\/github.com\/facebookresearch\/detectron2 (2019)"},{"key":"26_CR44","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 (CVPR). pp. 4794\u20134803 (June 2022)","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"26_CR45","doi-asserted-by":"crossref","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: European Conference on Computer Vision. Springer (2018)","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"26_CR46","unstructured":"Yang, J., Li, C., Zhang, P., Dai, X., Xiao, B., Yuan, L., Gao, J.: Focal attention for long-range interactions in vision transformers. In: Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P., Vaughan, J.W. (eds.) Advances in Neural Information Processing Systems. vol.\u00a034, pp. 30008\u201330022. Curran Associates, Inc. (2021)"},{"key":"26_CR47","unstructured":"Yang, J., Li, C., Zhang, P., Dai, X., Xiao, B., Yuan, L., Gao, J.: Focal self-attention for local-global interactions in vision transformers (2021)"},{"key":"26_CR48","doi-asserted-by":"crossref","unstructured":"Yang, R., Ma, H., Wu, J., Tang, Y., Xiao, X., Zheng, M., Li, X.: Scalablevit: Rethinking the context-oriented generalization of vision transformer (2022)","DOI":"10.1007\/978-3-031-20053-3_28"},{"key":"26_CR49","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: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"26_CR50","doi-asserted-by":"crossref","unstructured":"Zeng, W., Jin, S., Liu, W., Qian, C., Luo, P., Ouyang, W., Wang, X.: Not all tokens are equal: Human-centric visual analysis via token clustering transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 11101\u201311111 (2022)","DOI":"10.1109\/CVPR52688.2022.01082"},{"key":"26_CR51","unstructured":"Zhang, H., Cisse, M., Dauphin, Y.N., Lopez-Paz, D.: mixup: Beyond empirical risk minimization. International Conference on Learning Representations (2018), https:\/\/openreview.net\/forum?id=r1Ddp1-Rb"},{"issue":"3","key":"26_CR52","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.: Semantic understanding of scenes through the ade20k dataset. Int. J. Comput. Vision 127(3), 302\u2013321 (2019)","journal-title":"Int. J. Comput. Vision"},{"key":"26_CR53","doi-asserted-by":"crossref","unstructured":"Zhu, L., Wang, X., Ke, Z., Zhang, W., Lau, R.: Biformer: Vision transformer with bi-level routing attention. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00995"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0972-7_26","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,9]],"date-time":"2024-12-09T09:11:57Z","timestamp":1733735517000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0972-7_26"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,10]]},"ISBN":["9789819609710","9789819609727"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0972-7_26","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,10]]},"assertion":[{"value":"10 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}