{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T20:00:52Z","timestamp":1790366452639,"version":"4.1.0"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032376237","type":"print"},{"value":"9783032376244","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37624-4_19","type":"book-chapter","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T05:53:13Z","timestamp":1789537993000},"page":"301-317","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["DETRPose: Real-Time End-to-End Multi-person Pose Estimation via\u00a0Modified Transformer Decoder and\u00a0Novel Denoising Keypoints"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9637-7408","authenticated-orcid":false,"given":"Sebastian","family":"Janampa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1574-1827","authenticated-orcid":false,"given":"Marios","family":"Pattichis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,17]]},"reference":[{"key":"19_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"19_CR2","unstructured":"Jocher, G., Chaurasia, A., Qiu, J.: Ultralytics yolov8 (2023). https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"19_CR3","unstructured":"Jocher, G., Qiu, J.: Ultralytics yolo11 (2024). https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"19_CR4","unstructured":"Jocher, G., Qiu, J.: Ultralytics yolo26 (2026). https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything, arXiv:2304.02643 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"19_CR6","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":"19_CR7","doi-asserted-by":"crossref","unstructured":"Li, F., et al.: Mask dino: towards a unified transformer-based framework for object detection and segmentation (2022)","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, C., Zhu, H., Mao, Y., Fang, H.S., Lu, C.: Crowdpose: efficient crowded scenes pose estimation and a new benchmark. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10863\u201310872 (2019)","DOI":"10.1109\/CVPR.2019.01112"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, W., Hu, X., Li, J., Tang, J., Yang, J.: Generalized focal loss v2: Learning reliable localization quality estimation for dense object detection. arXiv preprint arXiv:2011.12885 (2020)","DOI":"10.1109\/CVPR46437.2021.01146"},{"key":"19_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Liu, H., et al.: Group pose: a simple baseline for end-to-end multi-person pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01380"},{"key":"19_CR12","unstructured":"Liu, S., et al.: Dab-detr: dynamic anchor boxes are better queries for detr. arXiv preprint arXiv:2201.12329 (2022)"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Lu, P., Jiang, T., Li, Y., Li, X., Chen, K., Yang, W.: RTMO: towards high-performance one-stage real-time multi-person pose estimation (2023)","DOI":"10.1109\/CVPR52733.2024.00148"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Maji, D., Nagori, S., Mathew, M., Poddar, D.: Yolo-pose: enhancing yolo for multi person pose estimation using object keypoint similarity loss. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2637\u20132646 (2022)","DOI":"10.1109\/CVPRW56347.2022.00297"},{"key":"19_CR15","doi-asserted-by":"crossref","unstructured":"Mao, W., Tian, Z., Wang, X., Shen, C.: Fcpose: fully convolutional multi-person pose estimation with dynamic instance-aware convolutions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9034\u20139043 (2021)","DOI":"10.1109\/CVPR46437.2021.00892"},{"key":"19_CR16","doi-asserted-by":"crossref","unstructured":"McNally, W., Vats, K., Wong, A., McPhee, J.: Rethinking keypoint representations: Modeling keypoints and poses as objects for multi-person human pose estimation. arXiv preprint arXiv:2111.08557 (2021)","DOI":"10.1007\/978-3-031-20068-7_3"},{"key":"19_CR17","unstructured":"Peng, Y., Li, H., Wu, P., Zhang, Y., Sun, X., Wu, F.: D-fine: Redefine regression task in detrs as fine-grained distribution refinement (2024)"},{"key":"19_CR18","unstructured":"Ravi, N., et al.: Sam 2: segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)"},{"key":"19_CR19","unstructured":"Robinson, I., Robicheaux, P., Popov, M.: Rf-detr (2025). https:\/\/github.com\/roboflow\/rf-detr, sOTA Real-Time Object Detection Model"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Shao, S., et al.: Objects365: a large-scale, high-quality dataset for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8425\u20138434 (2019)","DOI":"10.1109\/ICCV.2019.00852"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Shi, D., Wei, X., Li, L., Ren, Y., Tan, W.: End-to-end multi-person pose estimation with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11069\u201311078 (2022)","DOI":"10.1109\/CVPR52688.2022.01079"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Shi, D., Wei, X., Yu, X., Tan, W., Ren, Y., Pu, S.: Inspose: instance-aware networks for single-stage multi-person pose estimation. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 3079\u20133087 (2021)","DOI":"10.1145\/3474085.3475447"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Huang, S., Lu, Z., Shen, X.C.Y.Y.X.Z., X.: Deim: Detr with improved matching for fast convergence (2025)","DOI":"10.1109\/CVPR52734.2025.01412"},{"key":"19_CR24","unstructured":"Tian, Z., Chen, H., Shen, C.: Directpose: direct end-to-end multi-person pose estimation, arXiv preprint arXiv:1911.07451 (2019)"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Wang, D., Zhang, S.: Contextual instance decoupling for robust multi-person pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11060\u201311068 (2022)","DOI":"10.1109\/CVPR52688.2022.01078"},{"key":"19_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. 36, pp. 2567\u20132575 (2022)","DOI":"10.1609\/aaai.v36i3.20158"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Xiao, Y., et al.: Querypose: sparse multi-person pose regression via spatial-aware part-level query. In: Advances in Neural Information Processing Systems, pp. 1\u201314 (2022)","DOI":"10.52202\/068431-0905"},{"key":"19_CR28","unstructured":"Yang, J., Zeng, A., Liu, S., Li, F., Zhang, R., Zhang, L.: Explicit box detection unifies end-to-end multi-person pose estimation. In: International Conference on Learning Representations, pp. 1\u201317 (2023)"},{"key":"19_CR29","unstructured":"Zhang, H., et al.: Dino: Detr with improved denoising anchor boxes for end-to-end object detection. In: International Conference on Learning Representations, pp. 1\u201318 (2022)"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wang, Y., Dayoub, F., S\u00fcnderhauf, N.: Varifocalnet: an iou-aware dense object detector. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00841"},{"key":"19_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, S.H., et al.: Pose2seg: detection free human instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00098"},{"key":"19_CR32","doi-asserted-by":"crossref","unstructured":"Zhao, Y., et al.: Detrs beat yolos on real-time object detection (2023)","DOI":"10.1109\/CVPR52733.2024.01605"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37624-4_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T05:53:26Z","timestamp":1789538006000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37624-4_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032376237","9783032376244"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37624-4_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"17 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}