{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T11:18:02Z","timestamp":1726226282372},"reference-count":41,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,4,1]],"date-time":"2023-04-01T00:00:00Z","timestamp":1680307200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62006041","62276061"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2023,4]]},"DOI":"10.1016\/j.patcog.2022.109232","type":"journal-article","created":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T17:01:44Z","timestamp":1670259704000},"page":"109232","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":16,"special_numbering":"C","title":["Detecting and grouping keypoints for multi-person pose estimation using instance-aware attention"],"prefix":"10.1016","volume":"136","author":[{"given":"Sen","family":"Yang","sequence":"first","affiliation":[]},{"given":"Ze","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Zhicheng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yanjie","family":"Li","sequence":"additional","affiliation":[]},{"given":"Shoukui","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Zhibin","family":"Quan","sequence":"additional","affiliation":[]},{"given":"Shu-tao","family":"Xia","sequence":"additional","affiliation":[]},{"given":"Wankou","family":"Yang","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2022.109232_bib0001","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"34","article-title":"DeeperCut: a deeper, stronger, and faster multi-person pose estimation model","author":"Insafutdinov","year":"2016"},{"key":"10.1016\/j.patcog.2022.109232_bib0002","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"7291","article-title":"Realtime multi-person 2D pose estimation using part affinity fields","author":"Cao","year":"2017"},{"key":"10.1016\/j.patcog.2022.109232_bib0003","series-title":"Advances in Neural Information Processing Systems","article-title":"Associative embedding: end-to-end learning for joint detection and grouping","volume":"Vol.\u00a030","author":"Newell","year":"2017"},{"key":"10.1016\/j.patcog.2022.109232_bib0004","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"269","article-title":"PersonLab: person pose estimation and instance segmentation with a bottom-up, part-based, geometric embedding model","author":"Papandreou","year":"2018"},{"key":"10.1016\/j.patcog.2022.109232_bib0005","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11977","article-title":"PifPaf: composite fields for human pose estimation","author":"Kreiss","year":"2019"},{"key":"10.1016\/j.patcog.2022.109232_bib0006","unstructured":"X. Zhou, D. Wang, P. Kr\u00e4henb\u00fchl, Objects as points, arXiv preprint arXiv:1904.07850(2019)."},{"key":"10.1016\/j.patcog.2022.109232_bib0007","series-title":"Advances in Neural Information Processing Systems","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.patcog.2022.109232_bib0008","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, et\u00a0al., An image is worth 16x16 words: transformers for image recognition at scale, arXiv preprint arXiv:2010.11929(2020)."},{"key":"10.1016\/j.patcog.2022.109232_bib0009","unstructured":"H. Touvron, M. Cord, M. Douze, F. Massa, A. Sablayrolles, H. J\u00e9gou, Training data-efficient image transformers & distillation through attention, arXiv preprint arXiv:2012.12877(2020)."},{"key":"10.1016\/j.patcog.2022.109232_bib0010","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"213","article-title":"End-to-end object detection with transformers","author":"Carion","year":"2020"},{"key":"10.1016\/j.patcog.2022.109232_bib0011","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6881","article-title":"Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers","author":"Zheng","year":"2021"},{"key":"10.1016\/j.patcog.2022.109232_bib0012","unstructured":"P. Sun, Y. Jiang, R. Zhang, E. Xie, J. Cao, X. Hu, T. Kong, Z. Yuan, C. Wang, P. Luo, TransTrack: multiple-object tracking with transformer, arXiv preprint arXiv:2012.15460(2020)."},{"key":"10.1016\/j.patcog.2022.109232_bib0013","doi-asserted-by":"crossref","unstructured":"T. Meinhardt, A. Kirillov, L. Leal-Taixe, C. Feichtenhofer, TrackFormer: multi-object tracking with transformers, arXiv preprint arXiv:2101.02702(2021).","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"10.1016\/j.patcog.2022.109232_bib0014","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"1954","article-title":"End-to-end human pose and mesh reconstruction with transformers","author":"Lin","year":"2021"},{"key":"10.1016\/j.patcog.2022.109232_bib0015","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","article-title":"Transpose: keypoint localization via transformer","author":"Yang","year":"2021"},{"key":"10.1016\/j.patcog.2022.109232_bib0016","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","article-title":"TokenPose: learning keypoint tokens for human pose estimation","author":"Li","year":"2021"},{"key":"10.1016\/j.patcog.2022.109232_bib0017","unstructured":"L. Stoffl, M. Vidal, A. Mathis, End-to-trainable multi-instance pose estimation with transformers, arXiv preprint arXiv:2103.12115(2021)."},{"key":"10.1016\/j.patcog.2022.109232_bib0018","series-title":"2011 International Conference on Computer Vision","first-page":"2142","article-title":"Object detection and segmentation from joint embedding of parts and pixels","author":"Maire","year":"2011"},{"issue":"4","key":"10.1016\/j.patcog.2022.109232_bib0019","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1007\/s11222-007-9033-z","article-title":"A tutorial on spectral clustering","volume":"17","author":"Von Luxburg","year":"2007","journal-title":"Stat. Comput."},{"issue":"7","key":"10.1016\/j.patcog.2022.109232_bib0020","doi-asserted-by":"crossref","first-page":"1387","DOI":"10.1016\/j.patcog.2003.10.017","article-title":"A probabilistic spectral framework for grouping and segmentation","volume":"37","author":"Robles-Kelly","year":"2004","journal-title":"Pattern Recognit."},{"issue":"8","key":"10.1016\/j.patcog.2022.109232_bib0021","doi-asserted-by":"crossref","first-page":"888","DOI":"10.1109\/34.868688","article-title":"Normalized cuts and image segmentation","volume":"22","author":"Shi","year":"2000","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2022.109232_bib0022","doi-asserted-by":"crossref","first-page":"107074","DOI":"10.1016\/j.patcog.2019.107074","article-title":"Cluster-wise learning network for multi-person pose estimation","volume":"98","author":"Zhao","year":"2020","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2022.109232_bib0023","doi-asserted-by":"crossref","first-page":"108046","DOI":"10.1016\/j.patcog.2021.108046","article-title":"Monocular multi-person pose estimation: a survey","volume":"118","author":"dos Reis","year":"2021","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2022.109232_bib0024","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4903","article-title":"Towards accurate multi-person pose estimation in the wild","author":"Papandreou","year":"2017"},{"key":"10.1016\/j.patcog.2022.109232_bib0025","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2961","article-title":"Mask R-CNN","author":"He","year":"2017"},{"key":"10.1016\/j.patcog.2022.109232_bib0026","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"7103","article-title":"Cascaded pyramid network for multi-person pose estimation","author":"Chen","year":"2018"},{"key":"10.1016\/j.patcog.2022.109232_bib0027","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"466","article-title":"Simple baselines for human pose estimation and tracking","author":"Xiao","year":"2018"},{"key":"10.1016\/j.patcog.2022.109232_bib0028","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5693","article-title":"Deep high-resolution representation learning for human pose estimation","author":"Sun","year":"2019"},{"key":"10.1016\/j.patcog.2022.109232_bib0029","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"5207","article-title":"LSTM pose machines","author":"Luo","year":"2018"},{"key":"10.1016\/j.patcog.2022.109232_bib0030","doi-asserted-by":"crossref","first-page":"107258","DOI":"10.1016\/j.patcog.2020.107258","article-title":"Exploring temporal consistency for human pose estimation in videos","volume":"103","author":"Li","year":"2020","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2022.109232_bib0031","doi-asserted-by":"crossref","first-page":"108652","DOI":"10.1016\/j.patcog.2022.108652","article-title":"Searching part-specific neural fabrics for human pose estimation","volume":"128","author":"Yang","year":"2022","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2022.109232_bib0032","doi-asserted-by":"crossref","first-page":"108579","DOI":"10.1016\/j.patcog.2022.108579","article-title":"Low-resolution human pose estimation","volume":"126","author":"Wang","year":"2022","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2022.109232_bib0033","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"6951","article-title":"Single-stage multi-person pose machines","author":"Nie","year":"2019"},{"key":"10.1016\/j.patcog.2022.109232_bib0034","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2359","article-title":"Fully convolutional instance-aware semantic segmentation","author":"Li","year":"2017"},{"key":"10.1016\/j.patcog.2022.109232_bib0035","doi-asserted-by":"crossref","unstructured":"B. De Brabandere, D. Neven, L. Van Gool, Semantic instance segmentation with a discriminative loss function, arXiv preprint arXiv:1708.02551(2017).","DOI":"10.1109\/CVPRW.2017.66"},{"key":"10.1016\/j.patcog.2022.109232_bib0036","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"issue":"1\u20132","key":"10.1016\/j.patcog.2022.109232_bib0037","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1002\/nav.3800020109","article-title":"The hungarian method for the assignment problem","volume":"2","author":"Kuhn","year":"1955","journal-title":"Nav. Res. Logist. Q."},{"key":"10.1016\/j.patcog.2022.109232_bib0038","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"740","article-title":"Microsoft COCO: common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.patcog.2022.109232_bib0039","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5386","article-title":"HigherHRNet: scale-aware representation learning for bottom-up human pose estimation","author":"Cheng","year":"2020"},{"key":"10.1016\/j.patcog.2022.109232_bib0040","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"14676","article-title":"Bottom-up human pose estimation via disentangled keypoint regression","author":"Geng","year":"2021"},{"key":"10.1016\/j.patcog.2022.109232_bib0041","series-title":"IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, October 22\u201329, 2017","first-page":"369","article-title":"Benchmarking and error diagnosis in multi-instance pose estimation","author":"Ronchi","year":"2017"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320322007117?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320322007117?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2023,1,16]],"date-time":"2023-01-16T16:30:53Z","timestamp":1673886653000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320322007117"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4]]},"references-count":41,"alternative-id":["S0031320322007117"],"URL":"http:\/\/dx.doi.org\/10.1016\/j.patcog.2022.109232","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2023,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Detecting and grouping keypoints for multi-person pose estimation using instance-aware attention","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2022.109232","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2023 Elsevier Ltd. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"109232"}}
