{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T23:55:24Z","timestamp":1767138924967,"version":"build-2238731810"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819788576","type":"print"},{"value":"9789819788583","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-981-97-8858-3_28","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T18:04:28Z","timestamp":1730570668000},"page":"404-417","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["End-To-End High-Quality Transformer Object Detection Model Applied to Human Head Detection"],"prefix":"10.1007","author":[{"given":"Zhen","family":"Zhou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rongchun","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingfei","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"28_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: European Conference on Computer Vision, pp. 213\u2013229 (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"28_CR2","unstructured":"Chen, K., et al.: MMDetection: Open mmlab detection toolbox and benchmark (2019). arXiv:1906.07155"},{"key":"28_CR3","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: Transformers for image recognition at scale (2020). arXiv:2010.11929"},{"key":"28_CR4","doi-asserted-by":"crossref","unstructured":"Han, J., Wang, X., Wang, X., Lv, X.: CFNet: Head detection network based on multi-layer feature fusion and attention mechanism. IET Image Process. 17(7), 2032\u20132042 (2023)","DOI":"10.1049\/ipr2.12770"},{"key":"28_CR5","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":"28_CR6","doi-asserted-by":"crossref","unstructured":"Hu, J., Yang, Z.: Single-shot global and local context refinement neural network for head detection. Future Internet 14(12), 384 (2022)","DOI":"10.3390\/fi14120384"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Jia, D., et al.: Detrs with hybrid matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19702\u201319712 (2023)","DOI":"10.1109\/CVPR52729.2023.01887"},{"key":"28_CR8","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":"28_CR9","doi-asserted-by":"crossref","unstructured":"Li, R., Zhang, B., Huang, Z., Zhao, X., Qiao, P., & Dou, Y.: Spatial attention network for head detection. In: Advances in Multimedia Information Processing\u2013PCM 2018: 19th Pacific-Rim Conference on Multimedia, pp. 547\u2013557 (2018)","DOI":"10.1007\/978-3-030-00767-6_51"},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"Li, R., Zhang, J., Liu, Y., Dou, Y.: Towards precise end-to-end semi-supervised human head detection network. In: International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138 (2020)","DOI":"10.1109\/IJCNN48605.2020.9207207"},{"key":"28_CR11","unstructured":"Li, X., et al.: Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection. In: Advances in Neural Information Processing Systems, pp. 21002\u201321012 (2020)"},{"key":"28_CR12","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":"28_CR13","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: 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":"28_CR14","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: Common objects in context. In: European Conference on Computer Vision, pp. 740\u2013755 (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"28_CR15","unstructured":"Liu, S., et al.: Dab-detr: Dynamic anchor boxes are better queries for detr (2022). arXiv:2201.12329"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Liu, W., et al.: Ssd: Single shot multibox detector. In: European Conference on Computer Vision, pp. 21\u201337 (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"28_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"28_CR18","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"28_CR19","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"28_CR20","doi-asserted-by":"crossref","unstructured":"Stewart, R., Andriluka, M., Ng, A.Y.: End-to-end people detection in crowded scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2325\u20132333 (2016)","DOI":"10.1109\/CVPR.2016.255"},{"key":"28_CR21","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Chen, H., He, T.: FCOS: Fully convolutional one-stage object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9627\u20139636 (2019)","DOI":"10.1109\/ICCV.2019.00972"},{"key":"28_CR22","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 6000\u20136010 (2017)"},{"key":"28_CR23","doi-asserted-by":"crossref","unstructured":"Zhang, H., Chang, H., Ma, B., Wang, N., Chen, X.: Dynamic R-CNN: Towards high quality object detection via dynamic training. In: European Conference on Computer Vision, pp. 260\u2013275 (2020)","DOI":"10.1007\/978-3-030-58555-6_16"},{"key":"28_CR24","unstructured":"Zhang, H., et al.: Dino: Detr with improved denoising anchor boxes for end-to-end object detection. In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wang, Y., Dayoub, F., Sunderhauf, N.: Varifocalnet: An iou-aware dense object detector. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8514\u20138523 (2021)","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"28_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, J., Liu, Y., Li, R., Dou, Y.: End-to-end spatial attention network with feature mimicking for head detection. In: 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), pp. 199\u2013206 (2020)","DOI":"10.1109\/FG47880.2020.00072"},{"key":"28_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, S., Chi, C., Yao, Y., Lei, Z., Li, S. Z.: Bridging the gap between anchor-based and anchor-free detection via adaptive training sample selection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9759\u20139768 (2020)","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"28_CR28","doi-asserted-by":"crossref","unstructured":"Zheng, D., Dong, W., Hu, H., Chen, X., Wang, Y.: Less is more: focus attention for efficient detr. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6674\u20136683 (2023)","DOI":"10.1109\/ICCV51070.2023.00614"},{"key":"28_CR29","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: Deformable transformers for end-to-end object detection (2020). arXiv:2010.04159"},{"key":"28_CR30","doi-asserted-by":"crossref","unstructured":"Zong, Z., Song, G., Liu, Y.: Detrs with collaborative hybrid assignments training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6748\u20136758 (2023)","DOI":"10.1109\/ICCV51070.2023.00621"}],"updated-by":[{"DOI":"10.1007\/978-981-97-8858-3_40","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2025,2,14]],"date-time":"2025-02-14T00:00:00Z","timestamp":1739491200000}}],"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\/978-981-97-8858-3_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,13]],"date-time":"2025-02-13T12:27:46Z","timestamp":1739449666000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8858-3_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9789819788576","9789819788583"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8858-3_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"14 February 2025","order":2,"name":"change_date","label":"Change Date","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Correction","order":3,"name":"change_type","label":"Change Type","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"A correction has been published.","order":4,"name":"change_details","label":"Change Details","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"}}]}}