{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T20:14:24Z","timestamp":1743020064040,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819785049"},{"type":"electronic","value":"9789819785056"}],"license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"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\/978-981-97-8505-6_22","type":"book-chapter","created":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T22:02:02Z","timestamp":1730930522000},"page":"312-325","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Real-Time Detection Transformer with Bi-Level Routing Attention"],"prefix":"10.1007","author":[{"given":"Xin","family":"Zhao","sequence":"first","affiliation":[]},{"given":"Shiqian","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"Boyue","family":"Li","sequence":"additional","affiliation":[]},{"given":"Rushi","family":"Lan","sequence":"additional","affiliation":[]},{"given":"Xiaonan","family":"Luo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"key":"22_CR1","unstructured":"Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade r-cnn: delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., et\u00a0al.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"22_CR4","unstructured":"Chen, Q., Chen, X., Zeng, G., Wang, J.: Group detr: fast training convergence with decoupled one-to-many label assignment. arXiv preprint arXiv:2207.130852(3),\u00a012 (2022)"},{"key":"22_CR5","unstructured":"Ge, Z., Liu, S., Wang, F., et\u00a0al.: Yolox: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"22_CR7","unstructured":"Glenn, J.: Yolov8. In: https:\/\/github.com\/ultralytics\/ultralytics\/tree\/main (2023)"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"22_CR9","unstructured":"Jocher, G., Chaurasia, A., Stoken, A., et\u00a0al.: Yolov5 release v7.0. https:\/\/github.com\/ultralytics\/yolov5\/tree\/v7.0 Zenodo (2022)"},{"key":"22_CR10","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25 (2012)"},{"key":"22_CR11","unstructured":"Li, C., Li, L., Geng, Y., et\u00a0al.: Yolov6 v3. 0: a full-scale reloading. arXiv preprint arXiv:2301.05586 (2023)"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Li, F., Zhang, H., Liu, S., Guo, J., Ni, L.M., Zhang, L.: Dn-detr: accelerate detr training by introducing query denoising. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13619\u201313627 (2022)","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"22_CR13","unstructured":"Li, H., Li, J., Wei, H., et\u00a0al.: Slim-neck by gsconv: a better design paradigm of detector architectures for autonomous vehicles. arXiv preprint arXiv:2206.02424 (2022)"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., et\u00a0al.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"22_CR16","unstructured":"Liu, S., Li, F., Zhang, H., Yang, X., Qi, X., Su, H., Zhu, J., Zhang, L.: Dab-detr: dynamic anchor boxes are better queries for detr. arXiv preprint arXiv:2201.12329 (2022)"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Liu, W., Lu, H., Fu, H., et\u00a0al.: Learning to upsample by learning to sample. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6027\u20136037 (2023)","DOI":"10.1109\/ICCV51070.2023.00554"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Meng, D., Chen, X., Fan, Z., Zeng, G., Li, H., Yuan, Y., Sun, L., Wang, J.: Conditional detr for fast training convergence. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3651\u20133660 (2021)","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Neubeck, A., Van\u00a0Gool, L.: Efficient non-maximum suppression. In: 18th International Conference on Pattern Recognition (ICPR\u201906), vol.\u00a03, pp. 850\u2013855. IEEE (2006)","DOI":"10.1109\/ICPR.2006.479"},{"key":"22_CR20","unstructured":"Ren, S., He, K., Girshick, R., et\u00a0al.: Faster r-cnn: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"22_CR21","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Sun, P., Zhang, R., Jiang, Y., et\u00a0al.: Sparse r-cnn: end-to-end object detection with learnable proposals. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14454\u201314463 (2021)","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., et\u00a0al.: Fcos: fully convolutional one-stage object detection. arxiv 2019. arXiv preprint arXiv:1904.01355 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., Liao, H.Y.M.: Yolov7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7464\u20137475 (2023)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Wang, J., Song, L., Li, Z., Sun, H., Sun, J., Zheng, N.: End-to-end object detection with fully convolutional network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15849\u201315858 (2021)","DOI":"10.1109\/CVPR46437.2021.01559"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, X., Yang, T., Sun, J.: Anchor detr: query design for transformer-based detector. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 2567\u20132575 (2022)","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"22_CR27","unstructured":"Yao, Z., Ai, J., Li, B., Zhang, C.: Efficient detr: improving end-to-end object detector with dense prior. arXiv preprint arXiv:2104.01318 (2021)"},{"key":"22_CR28","unstructured":"Zhang, H., Li, F., Liu, S., Zhang, L., Su, H., Zhu, J., Ni, L.M., Shum, H.Y.: Dino: Detr with improved denoising anchor boxes for end-to-end object detection. arXiv preprint arXiv:2203.03605 (2022)"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lv, W., Xu, S., et\u00a0al.: Detrs beat yolos on real-time object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16965\u201316974 (2024)","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Zhu, L., Wang, X., Ke, Z., et\u00a0al.: Biformer: vision transformer with bi-level routing attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10323\u201310333 (2023)","DOI":"10.1109\/CVPR52729.2023.00995"},{"key":"22_CR31","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8505-6_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T22:06:47Z","timestamp":1730930807000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8505-6_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"ISBN":["9789819785049","9789819785056"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8505-6_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,7]]},"assertion":[{"value":"7 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}