{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:03:26Z","timestamp":1777655006486,"version":"3.51.4"},"publisher-location":"Cham","reference-count":93,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726484","type":"print"},{"value":"9783031726491","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-72649-1_8","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:01:50Z","timestamp":1727593310000},"page":"126-146","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["You Only Learn One Query: Learning Unified Human Query for\u00a0Single-Stage Multi-person Multi-task Human-Centric Perception"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5736-7434","authenticated-orcid":false,"given":"Sheng","family":"Jin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0180-4248","authenticated-orcid":false,"given":"Shuhuai","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9993-2581","authenticated-orcid":false,"given":"Tong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6587-9878","authenticated-orcid":false,"given":"Wentao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8761-5563","authenticated-orcid":false,"given":"Chen","family":"Qian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6685-7950","authenticated-orcid":false,"given":"Ping","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"issue":"11","key":"8_CR1","doi-asserted-by":"publisher","first-page":"1949","DOI":"10.1109\/TMM.2015.2477680","volume":"17","author":"AH Abdulnabi","year":"2015","unstructured":"Abdulnabi, A.H., Wang, G., Lu, J., Jia, K.: Multi-task cnn model for attribute prediction. IEEE Trans. Multimedia 17(11), 1949\u20131959 (2015)","journal-title":"IEEE Trans. Multimedia"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Agustsson, E., Timofte, R., Escalera, S., Baro, X., Guyon, I., Rothe, R.: Apparent and real age estimation in still images with deep residual regressors on appa-real database. In: IEEE International Conference on Automation Face & Gesture Recognition, pp. 87\u201394 (2017)","DOI":"10.1109\/FG.2017.20"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Alp\u00a0G\u00fcler, R., Neverova, N., Kokkinos, I.: Densepose: dense human pose estimation in the wild. In: IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00762"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Andriluka, M., et al.: Posetrack: a benchmark for human pose estimation and tracking. In: IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00542"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2d human pose estimation: new benchmark and state of the art analysis. In: IEEE Conference on Computer Vision and Pattern Recognition (2014)","DOI":"10.1109\/CVPR.2014.471"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Bolya, D., Zhou, C., Xiao, F., Lee, Y.J.: Yolact: real-time instance segmentation. In: International Conference on Computer Vision, pp. 9157\u20139166 (2019)","DOI":"10.1109\/ICCV.2019.00925"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.E., Sheikh, Y.: Realtime multi-person 2d pose estimation using part affinity fields. In: IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"8_CR8","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":"8_CR9","doi-asserted-by":"crossref","unstructured":"Chen, W., et al.: Beyond appearance: a semantic controllable self-supervised learning framework for human-centric visual tasks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 15050\u201315061 (2023)","DOI":"10.1109\/CVPR52729.2023.01445"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Cheng, B., Xiao, B., Wang, J., Shi, H., Huang, T.S., Zhang, L.: Higherhrnet: scale-aware representation learning for bottom-up human pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5386\u20135395 (2020)","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Ci, Y., et al.: Unihcp: a unified model for human-centric perceptions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 17840\u201317852 (2023)","DOI":"10.1109\/CVPR52729.2023.01711"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Deng, Y., Luo, P., Loy, C.C., Tang, X.: Pedestrian attribute recognition at far distance. In: ACM International Conference on Multimedia, pp. 789\u2013792 (2014)","DOI":"10.1145\/2647868.2654966"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Doering, A., Chen, D., Zhang, S., Schiele, B., Gall, J.: Posetrack21: a dataset for person search, multi-object tracking and multi-person pose tracking. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 20963\u201320972 (2022)","DOI":"10.1109\/CVPR52688.2022.02029"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Doll\u00e1r, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: a benchmark. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 304\u2013311 (2009)","DOI":"10.1109\/CVPRW.2009.5206631"},{"key":"8_CR15","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: International Conference on Learning Representation (2021)"},{"key":"8_CR16","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Geng, Z., Sun, K., Xiao, B., Zhang, Z., Wang, J.: Bottom-up human pose estimation via disentangled keypoint regression. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 14676\u201314686 (2021)","DOI":"10.1109\/CVPR46437.2021.01444"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Gong, K., Liang, X., Li, Y., Chen, Y., Yang, M., Lin, L.: Instance-level human parsing via part grouping network. In: European Conference on Computer Vision, pp. 770\u2013785 (2018)","DOI":"10.1007\/978-3-030-01225-0_47"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: International Conference Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Hong, F., Pan, L., Cai, Z., Liu, Z.: Versatile multi-modal pre-training for human-centric perception. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 16156\u201316166 (2022)","DOI":"10.1109\/CVPR52688.2022.01568"},{"key":"8_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1007\/978-3-319-46466-4_3","volume-title":"Computer Vision \u2013 ECCV 2016","author":"E Insafutdinov","year":"2016","unstructured":"Insafutdinov, E., Pishchulin, L., Andres, B., Andriluka, M., Schiele, B.: DeeperCut: a deeper, stronger, and faster multi-person pose estimation model. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 34\u201350. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_3"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6m: large scale datasets and predictive methods for 3d human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2013)","DOI":"10.1109\/TPAMI.2013.248"},{"key":"8_CR24","unstructured":"Jia, J., Huang, H., Yang, W., Chen, X., Huang, K.: Rethinking of pedestrian attribute recognition: realistic datasets with efficient method. arXiv preprint arXiv:2005.11909 (2020)"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Jiang, W., Jin, S., Liu, W., Qian, C., Luo, P., Liu, S.: Posetrans: a simple yet effective pose transformation augmentation for human pose estimation. In: European Conference on Computer Vision, pp. 643\u2013659 (2022)","DOI":"10.1007\/978-3-031-20065-6_37"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Jin, S., Liu, W., Ouyang, W., Qian, C.: Multi-person articulated tracking with spatial and temporal embeddings. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5664\u20135673 (2019)","DOI":"10.1109\/CVPR.2019.00581"},{"key":"8_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"718","DOI":"10.1007\/978-3-030-58571-6_42","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Jin","year":"2020","unstructured":"Jin, S., Liu, W., Xie, E., Wang, W., Qian, C., Ouyang, W., Luo, P.: Differentiable hierarchical graph grouping for multi-person pose estimation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 718\u2013734. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_42"},{"key":"8_CR28","doi-asserted-by":"crossref","unstructured":"Jin, S., et al.: Whole-body human pose estimation in the wild. In: European Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-58545-7_12"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Jin, S., et al.: Unifs: universal few-shot instance perception with point representations. In: European Conference on Computer Vision (2024)","DOI":"10.1007\/978-3-031-73397-0_27"},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Joo, H., Neverova, N., Vedaldi, A.: Exemplar fine-tuning for 3d human model fitting towards in-the-wild 3d human pose estimation. In: International Conference on 3D Vision, pp. 42\u201352. IEEE (2021)","DOI":"10.1109\/3DV53792.2021.00015"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Ju, X., Zeng, A., Wang, J., Xu, Q., Zhang, L.: Human-art: a versatile human-centric dataset bridging natural and artificial scenes. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 618\u2013629 (2023)","DOI":"10.1109\/CVPR52729.2023.00067"},{"key":"8_CR32","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Black, M.J., Jacobs, D.W., Malik, J.: End-to-end recovery of human shape and pose. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7122\u20137131 (2018)","DOI":"10.1109\/CVPR.2018.00744"},{"key":"8_CR33","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Levinkov, E., Andres, B., Savchynskyy, B., Rother, C.: Instancecut: from edges to instances with multicut. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5008\u20135017 (2017)","DOI":"10.1109\/CVPR.2017.774"},{"key":"8_CR34","doi-asserted-by":"crossref","unstructured":"Kong, S., Fowlkes, C.C.: Recurrent pixel embedding for instance grouping. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 9018\u20139028 (2018)","DOI":"10.1109\/CVPR.2018.00940"},{"key":"8_CR35","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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 13619\u201313627 (2022)","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Li, F., et al.: Mask dino: towards a unified transformer-based framework for object detection and segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3041\u20133050 (2023)","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"8_CR37","unstructured":"Li, J., et al.: Multiple-human parsing in the wild. arXiv preprint arXiv:1705.07206 (2017)"},{"key":"8_CR38","doi-asserted-by":"crossref","unstructured":"Li, K., Wang, S., Zhang, X., Xu, Y., Xu, W., Tu, Z.: Pose recognition with cascade transformers. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1944\u20131953 (2021)","DOI":"10.1109\/CVPR46437.2021.00198"},{"key":"8_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"684","DOI":"10.1007\/978-3-319-46466-4_41","volume-title":"Computer Vision \u2013 ECCV 2016","author":"Y Li","year":"2016","unstructured":"Li, Y., Huang, C., Loy, C.C., Tang, X.: Human attribute recognition by deep hierarchical contexts. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 684\u2013700. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_41"},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"Liang, J., Song, G., Leng, B., Liu, Y.: Unifying visual perception by dispersible points learning. In: European Conference on Computer Vision, pp. 439\u2013456 (2022)","DOI":"10.1007\/978-3-031-20077-9_26"},{"key":"8_CR41","doi-asserted-by":"crossref","unstructured":"Lin, J., Zeng, A., Wang, H., Zhang, L., Li, Y.: One-stage 3d whole-body mesh recovery with component aware transformer. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 21159\u201321168 (2023)","DOI":"10.1109\/CVPR52729.2023.02027"},{"key":"8_CR42","doi-asserted-by":"crossref","unstructured":"Lin, K., Wang, L., Liu, Z.: End-to-end human pose and mesh reconstruction with transformers. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1954\u20131963 (2021)","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"8_CR43","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":"8_CR44","unstructured":"Lin, Y., Shen, J., Wang, Y., Pantic, M.: Fp-age: leveraging face parsing attention for facial age estimation in the wild. IEEE Trans. Image Process (2022)"},{"key":"8_CR45","unstructured":"Liu, S., et al.: Dab-detr: dynamic anchor boxes are better queries for detr. In: International Conference on Learning Representation (2022)"},{"key":"8_CR46","doi-asserted-by":"crossref","unstructured":"Liu, X., et al.: Hydraplus-net: attentive deep features for pedestrian analysis. In: International Conference on Computer Vision, pp.\u00a01\u20139 (2017)","DOI":"10.1109\/ICCV.2017.46"},{"key":"8_CR47","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"8_CR48","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: International Conference on Computer Vision (2015)","DOI":"10.1109\/ICCV.2015.425"},{"key":"8_CR49","doi-asserted-by":"crossref","unstructured":"Luo, Z., Wang, Z., Huang, Y., Wang, L., Tan, T., Zhou, E.: Rethinking the heatmap regression for bottom-up human pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 13264\u201313273 (2021)","DOI":"10.1109\/CVPR46437.2021.01306"},{"key":"8_CR50","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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 9034\u20139043 (2021)","DOI":"10.1109\/CVPR46437.2021.00892"},{"key":"8_CR51","unstructured":"Newell, A., Huang, Z., Deng, J.: Associative embedding: end-to-end learning for joint detection and grouping. Adv. Neural Inform. Process. Syst. (2017)"},{"key":"8_CR52","doi-asserted-by":"crossref","unstructured":"Nie, X., Feng, J., Yan, S.: Mutual learning to adapt for joint human parsing and pose estimation. In: European Conference on Computer Vision, pp. 502\u2013517 (2018)","DOI":"10.1007\/978-3-030-01228-1_31"},{"key":"8_CR53","doi-asserted-by":"crossref","unstructured":"Nie, X., Feng, J., Zhang, J., Yan, S.: Single-stage multi-person pose machines. In: International Conference on Computer Vision, pp. 6951\u20136960 (2019)","DOI":"10.1109\/ICCV.2019.00705"},{"key":"8_CR54","doi-asserted-by":"crossref","unstructured":"Nie, X., Feng, J., Zuo, Y., Yan, S.: Human pose estimation with parsing induced learner. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2100\u20132108 (2018)","DOI":"10.1109\/CVPR.2018.00224"},{"key":"8_CR55","first-page":"26034","volume":"35","author":"HE Pang","year":"2022","unstructured":"Pang, H.E., Cai, Z., Yang, L., Zhang, T., Liu, Z.: Benchmarking and analyzing 3d human pose and shape estimation beyond algorithms. Adv. Neural. Inf. Process. Syst. 35, 26034\u201326051 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR56","doi-asserted-by":"crossref","unstructured":"Papandreou, G., Zhu, T., Chen, L.C., Gidaris, S., Tompson, J., Murphy, K.: Personlab: person pose estimation and instance segmentation with a bottom-up, part-based, geometric embedding model. In: European Conference on Computer Vision, pp. 269\u2013286 (2018)","DOI":"10.1007\/978-3-030-01264-9_17"},{"key":"8_CR57","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. (2015)"},{"key":"8_CR58","doi-asserted-by":"crossref","unstructured":"Rothe, R., Timofte, R., Van\u00a0Gool, L.: Dex: deep expectation of apparent age from a single image. In: International Conference on Computer Vision Workshop, pp. 10\u201315 (2015)","DOI":"10.1109\/ICCVW.2015.41"},{"key":"8_CR59","unstructured":"Shao, S., Zhao, Z., Li, B., Xiao, T., Yu, G., Zhang, X., Sun, J.: Crowdhuman: a benchmark for detecting human in a crowd. arXiv preprint arXiv:1805.00123 (2018)"},{"key":"8_CR60","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: IEEE Conference on Computer Vision and Pattern Recognition, pp. 11069\u201311078 (2022)","DOI":"10.1109\/CVPR52688.2022.01079"},{"key":"8_CR61","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: ACM International Conference on Multimedia, pp. 3079\u20133087 (2021)","DOI":"10.1145\/3474085.3475447"},{"key":"8_CR62","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5693\u20135703 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"8_CR63","doi-asserted-by":"crossref","unstructured":"Sun, Y., Bao, Q., Liu, W., Fu, Y., Black, M.J., Mei, T.: Monocular, one-stage, regression of multiple 3d people. In: International Conference on Computer Vision, pp. 11179\u201311188 (2021)","DOI":"10.1109\/ICCV48922.2021.01099"},{"key":"8_CR64","doi-asserted-by":"crossref","unstructured":"Tang, S., et\u00a0al.: Humanbench: towards general human-centric perception with projector assisted pretraining. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 21970\u201321982 (2023)","DOI":"10.1109\/CVPR52729.2023.02104"},{"key":"8_CR65","doi-asserted-by":"crossref","unstructured":"Tian, Y., Luo, P., Wang, X., Tang, X.: Pedestrian detection aided by deep learning semantic tasks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5079\u20135087 (2015)","DOI":"10.1109\/CVPR.2015.7299143"},{"key":"8_CR66","unstructured":"Tian, Z., Chen, H., Shen, C.: Directpose: direct end-to-end multi-person pose estimation. arXiv preprint arXiv:1911.07451 (2019)"},{"key":"8_CR67","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/978-3-030-58452-8_17","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Tian","year":"2020","unstructured":"Tian, Z., Shen, C., Chen, H.: Conditional convolutions for instance segmentation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 282\u2013298. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_17"},{"key":"8_CR68","doi-asserted-by":"crossref","unstructured":"Wang, D., Zhang, S.: Contextual instance decoupling for robust multi-person pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 11060\u201311068 (2022)","DOI":"10.1109\/CVPR52688.2022.01078"},{"key":"8_CR69","unstructured":"Wang, J., et al.: Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2020)"},{"key":"8_CR70","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/978-3-030-58621-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Wang","year":"2020","unstructured":"Wang, Z., Zheng, L., Liu, Y., Li, Y., Wang, S.: Towards real-time multi-object tracking. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 107\u2013122. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_7"},{"key":"8_CR71","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"527","DOI":"10.1007\/978-3-030-58607-2_31","volume-title":"Computer Vision \u2013 ECCV 2020","author":"F Wei","year":"2020","unstructured":"Wei, F., Sun, X., Li, H., Wang, J., Lin, S.: Point-set anchors for object detection, instance segmentation and pose estimation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12355, pp. 527\u2013544. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58607-2_31"},{"key":"8_CR72","doi-asserted-by":"crossref","unstructured":"Wojke, N., Bewley, A., Paulus, D.: Simple online and realtime tracking with a deep association metric. In: IEEE International Conference on Image Processing, pp. 3645\u20133649 (2017)","DOI":"10.1109\/ICIP.2017.8296962"},{"key":"8_CR73","doi-asserted-by":"crossref","unstructured":"Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: European Conference on Computer Vision (2018)","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"8_CR74","doi-asserted-by":"crossref","unstructured":"Xie, E., et al.: Polarmask: single shot instance segmentation with polar representation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 12193\u201312202 (2020)","DOI":"10.1109\/CVPR42600.2020.01221"},{"key":"8_CR75","doi-asserted-by":"crossref","unstructured":"Xu, L., et al.: Vipnas: efficient video pose estimation via neural architecture search. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 16072\u201316081 (2021)","DOI":"10.1109\/CVPR46437.2021.01581"},{"issue":"4","key":"8_CR76","first-page":"5296","volume":"45","author":"L Xu","year":"2022","unstructured":"Xu, L., et al.: Zoomnas: searching for whole-body human pose estimation in the wild. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 5296\u20135313 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"8_CR77","first-page":"38571","volume":"35","author":"Y Xu","year":"2022","unstructured":"Xu, Y., Zhang, J., Zhang, Q., Tao, D.: Vitpose: simple vision transformer baselines for human pose estimation. Adv. Neural Inform. Process. Syst. 35, 38571\u201338584 (2022)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"8_CR78","doi-asserted-by":"crossref","unstructured":"Xue, N., Wu, T., Xia, G.S., Zhang, L.: Learning local-global contextual adaptation for multi-person pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 13065\u201313074 (2022)","DOI":"10.1109\/CVPR52688.2022.01272"},{"key":"8_CR79","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 Representation (2023)"},{"key":"8_CR80","doi-asserted-by":"crossref","unstructured":"Zeng, W., et al.: Not all tokens are equal: human-centric visual analysis via token clustering transformer. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 11101\u201311111 (2022)","DOI":"10.1109\/CVPR52688.2022.01082"},{"key":"8_CR81","doi-asserted-by":"crossref","unstructured":"Zeng, W., Ouyang, W., Luo, P., Liu, W., Wang, X.: 3d human mesh regression with dense correspondence. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7054\u20137063 (2020)","DOI":"10.1109\/CVPR42600.2020.00708"},{"key":"8_CR82","unstructured":"Zhang, H., et al.: Dino: detr with improved denoising anchor boxes for end-to-end object detection. In: International Conference on Learning Representation (2023)"},{"key":"8_CR83","doi-asserted-by":"crossref","unstructured":"Zhang, N., Paluri, M., Ranzato, M., Darrell, T., Bourdev, L.: Panda: pose aligned networks for deep attribute modeling. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1637\u20131644 (2014)","DOI":"10.1109\/CVPR.2014.212"},{"key":"8_CR84","doi-asserted-by":"crossref","unstructured":"Zhang, R., Tian, Z., Shen, C., You, M., Yan, Y.: Mask encoding for single shot instance segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 10226\u201310235 (2020)","DOI":"10.1109\/CVPR42600.2020.01024"},{"key":"8_CR85","doi-asserted-by":"crossref","unstructured":"Zhang, S., Benenson, R., Schiele, B.: Citypersons: a diverse dataset for pedestrian detection. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3213\u20133221 (2017)","DOI":"10.1109\/CVPR.2017.474"},{"key":"8_CR86","doi-asserted-by":"crossref","unstructured":"Zhang, S.H., et al.: Pose2seg: detection free human instance segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 889\u2013898 (2019)","DOI":"10.1109\/CVPR.2019.00098"},{"key":"8_CR87","doi-asserted-by":"publisher","first-page":"7649","DOI":"10.1109\/TIP.2021.3107210","volume":"30","author":"X Zhang","year":"2021","unstructured":"Zhang, X., Ma, B., Chang, H., Shan, S., Chen, X.: Location sensitive network for human instance segmentation. IEEE Trans. Image Process. 30, 7649\u20137662 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"8_CR88","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zeng, W., Jin, S., Qian, C., Luo, P., Liu, W.: When pedestrian detection meets multi-modal learning: Generalist model and benchmark dataset. In: European Conference on Computer Vision (2024)","DOI":"10.1007\/978-3-031-73195-2_25"},{"key":"8_CR89","doi-asserted-by":"publisher","first-page":"3069","DOI":"10.1007\/s11263-021-01513-4","volume":"129","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Wang, C., Wang, X., Zeng, W., Liu, W.: Fairmot: on the fairness of detection and re-identification in multiple object tracking. Int. J. Comput. Vis. 129, 3069\u20133087 (2021)","journal-title":"Int. J. Comput. Vis."},{"key":"8_CR90","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Liu, L., Li, C., Loy, C.C.: Quantifying facial age by posterior of age comparisons. In: British Machine Vision Conference (2017)","DOI":"10.5244\/C.31.108"},{"key":"8_CR91","doi-asserted-by":"crossref","unstructured":"Zheng, A., Zhang, Y., Zhang, X., Qi, X., Sun, J.: Progressive end-to-end object detection in crowded scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 857\u2013866 (2022)","DOI":"10.1109\/CVPR52688.2022.00093"},{"key":"8_CR92","unstructured":"Zhou, X., Wang, D., Kr\u00e4henb\u00fchl, P.: Objects as points. arXiv preprint arXiv:1904.07850 (2019)"},{"key":"8_CR93","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable detr: deformable transformers for end-to-end object detection. In: International Conference on Learning Representation (2021)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72649-1_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:18:57Z","timestamp":1732828737000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72649-1_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031726484","9783031726491"],"references-count":93,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72649-1_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}