{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T15:10:01Z","timestamp":1755875401822,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":25,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,8]],"date-time":"2023-12-08T00:00:00Z","timestamp":1701993600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,12,8]]},"DOI":"10.1145\/3638584.3638641","type":"proceedings-article","created":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T11:15:19Z","timestamp":1710414919000},"page":"205-211","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Single-Camera 3D Human Pose Estimation: Addressing Occlusion Challenges and Predictive Quality Assessment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2056-3762","authenticated-orcid":false,"given":"Simran","family":"Kumar","sequence":"first","affiliation":[{"name":"Mathematics and Scientific Computing, National Institute of Technology, Hamirpur, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3340-4455","authenticated-orcid":false,"given":"Isha","family":"Sahni","sequence":"additional","affiliation":[{"name":"Ibm, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3856-5927","authenticated-orcid":false,"given":"Srushti","family":"Jagtap","sequence":"additional","affiliation":[{"name":"JP Morgan Chase, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3968-6755","authenticated-orcid":false,"given":"Manish","family":"Bhurtel","sequence":"additional","affiliation":[{"name":"British Model College, Nepal"}]}],"member":"320","published-online":{"date-parts":[[2024,3,14]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Deeplearning-based human pose estimation: A survey. In: arXiv.org. (link)","author":"Zheng C","year":"2022","unstructured":"Zheng C, Wu W, Chen C, Yang T, Zhu S, Shen J, Kehtarnavaz N, Shah M (2022) Deeplearning-based human pose estimation: A survey. In: arXiv.org. (link)."},{"volume-title":"InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2022 (pp. 13147-13156)","author":"Li W","unstructured":"Li W, Liu H, Tang H, Wang P, Van Gool L. Mhformer: Multi-hypothesis transformer for 3dhuman pose estimation. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2022 (pp. 13147-13156).","key":"e_1_3_2_1_2_1"},{"volume-title":"Motion guided 3d pose estimation from videos. InEuropeanConference on Computer Vision 2020 Aug 23 (pp. 764-780)","author":"Wang J","unstructured":"Wang J, Yan S, Xiong Y, Lin D. Motion guided 3d pose estimation from videos. InEuropeanConference on Computer Vision 2020 Aug 23 (pp. 764-780). Springer, Cham.","key":"e_1_3_2_1_3_1"},{"volume-title":"InProceedings ofthe IEEE conference on computer vision and pattern recognition 2016 (pp. 770-778)","author":"He K","unstructured":"He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. InProceedings ofthe IEEE conference on computer vision and pattern recognition 2016 (pp. 770-778).","key":"e_1_3_2_1_4_1"},{"key":"e_1_3_2_1_5_1","first-page":"1483","volume":"2","author":"Cai Z","unstructured":"Cai Z, Vasconcelos N. Cascade R-CNN: high quality object detection and instance segmentation. IEEE transactions on pattern analysis and machine intelligence. 2019 Nov 28;43(5):1483-98.","journal-title":"Nov"},{"volume-title":"InProceedings of the IEEE\/CVF international conference on computer vision 2019 (pp. 9627-9636)","author":"Tian Z","unstructured":"Tian Z, Shen C, Chen H, He T. Fcos: Fully convolutional one-stage object detection. InProceedings of the IEEE\/CVF international conference on computer vision 2019 (pp. 9627-9636).","key":"e_1_3_2_1_6_1"},{"volume-title":"InProceedings of the IEEE\/CVF international conference on computer vision 2019 (pp. 6569-6578)","author":"Duan K","unstructured":"Duan K, Bai S, Xie L, Qi H, Huang Q, Tian Q. Centernet: Keypoint triplets for object detection. InProceedings of the IEEE\/CVF international conference on computer vision 2019 (pp. 6569-6578).","key":"e_1_3_2_1_7_1"},{"volume-title":"InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2019 (pp. 4974-4983)","author":"Chen K","unstructured":"Chen K, Pang J, Wang J, Xiong Y, Li X, Sun S, Feng W, Liu Z, Shi J, Ouyang W, Loy CC.Hybrid task cascade for instance segmentation. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2019 (pp. 4974-4983).","key":"e_1_3_2_1_8_1"},{"key":"e_1_3_2_1_9_1","first-page":"13153","volume":"2021","author":"Zhang J","unstructured":"Zhang J, Cai Y, Yan S, Feng J. Direct multi-view multi-person 3d pose estimation. Advancesin Neural Information Processing Systems. 2021 Dec 6;34:13153-64.","journal-title":"Advancesin Neural Information Processing Systems."},{"doi-asserted-by":"crossref","unstructured":"Kevin Lin Lijuan Wang and Zicheng Liu. 2021. End-to-end human pose and mesh reconstruction with transformers. In CVPR. 1954\u20131963.","key":"e_1_3_2_1_10_1","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"e_1_3_2_1_11_1","first-page":"1954","volume":"2021","author":"Lin K","unstructured":"Lin K, Wang L, Liu Z. End-to-end human pose and mesh reconstruction with transformers.InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2021 (pp. 1954-1963).","journal-title":"Pattern Recognition"},{"key":"e_1_3_2_1_12_1","volume-title":"Hierarchical multi-person ordinal relations for monocular multi-person 3d pose estimation. arXiv","author":"Li J","year":"2020","unstructured":"Li J, Wang C, Liu W, Qian C, Lu CH. Hierarchical multi-person ordinal relations for monocular multi-person 3d pose estimation. arXiv 2020. arXiv preprint arXiv:2008.00206."},{"key":"e_1_3_2_1_13_1","first-page":"1157","volume-title":"InProceedings of the AAAI Conference on Artificial Intelligence 2021 May 18 (Vol. 35","author":"Cheng Y","unstructured":"Cheng Y, Wang B, Yang B, Tan RT. Graph and temporal convolutional networks for 3dmulti-person pose estimation in monocular videos. InProceedings of the AAAI Conference on Artificial Intelligence 2021 May 18 (Vol. 35, No. 2, pp. 1157-1165)."},{"volume-title":"InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2018 (pp. 2148-2157)","author":"Zanfir A","unstructured":"Zanfir A, Marinoiu E, Sminchisescu C. Monocular 3d pose and shape estimation of multiplepeople in natural scenes-the importance of multiple scene constraints. InProceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2018 (pp. 2148-2157).","key":"e_1_3_2_1_14_1"},{"volume-title":"InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2020 (pp. 7204-7213)","author":"Fabbri M","unstructured":"Fabbri M, Lanzi F, Calderara S, Alletto S, Cucchiara R. Compressed volumetric heatmaps formulti-person 3d pose estimation. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2020 (pp. 7204-7213).","key":"e_1_3_2_1_15_1"},{"volume-title":"InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2020 (pp. 6856-6865)","author":"Benzine A","unstructured":"Benzine A, Chabot F, Luvison B, Pham QC, Achard C. Pandanet: Anchor-based single-shotmulti-person 3d pose estimation. InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2020 (pp. 6856-6865).","key":"e_1_3_2_1_16_1"},{"volume-title":"InEuropean Conference on Computer Vision 2020 Aug 23 (pp. 550-566)","author":"Zhen J","unstructured":"Zhen J, Fang Q, Sun J, Liu W, Jiang W, Bao H, Zhou X. Smap: Single-shot multi-personabsolute 3d pose estimation. InEuropean Conference on Computer Vision 2020 Aug 23 (pp. 550-566). Springer, Cham.","key":"e_1_3_2_1_17_1"},{"doi-asserted-by":"crossref","unstructured":"Ma H Chen L Kong D Wang Z Liu X Tang H Yan X Xie Y Lin SY Xie X. Transfusion: Cross-view fusion with transformer for 3d human pose estimation. arXiv preprint arXiv:2110.09554. 2021 Oct 18.","key":"e_1_3_2_1_18_1","DOI":"10.5244\/C.35.5"},{"key":"e_1_3_2_1_19_1","first-page":"13686","volume":"2020","author":"Xie R","unstructured":"Xie R, Wang C, Wang Y. Metafuse: A pre-trained fusion model for human pose estimation.InProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2020 (pp. 13686-13695).","journal-title":"Pattern Recognition"},{"key":"e_1_3_2_1_20_1","first-page":"1325","volume":"1","author":"Ionescu C","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 transactions on pattern analysis and machine intelligence. 2013 Dec 12;36(7):1325-39.","journal-title":"Dec"},{"volume-title":"In2017 international conference on 3D vision (3DV) 2017 Oct 10 (pp. 506-516)","author":"Mehta D","unstructured":"Mehta D, Rhodin H, Casas D, Fua P, Sotnychenko O, Xu W, Theobalt C. Monocular 3dhuman pose estimation in the wild using improved cnn supervision. In2017 international conference on 3D vision (3DV) 2017 Oct 10 (pp. 506-516). IEEE.","key":"e_1_3_2_1_21_1"},{"volume-title":"In2018 International Conference on 3D Vision (3DV) 2018 Sep 5 (pp. 120-130)","author":"Mehta D","unstructured":"Mehta D, Sotnychenko O, Mueller F, Xu W, Sridhar S, Pons-Moll G, Theobalt C. Single-shotmulti-person 3d pose estimation from monocular rgb. In2018 International Conference on 3D Vision (3DV) 2018 Sep 5 (pp. 120-130). IEEE.","key":"e_1_3_2_1_22_1"},{"key":"e_1_3_2_1_23_1","volume-title":"OpenMMLab Pose Estimation Toolbox and Benchmark","author":"Pose Contributors","year":"2020","unstructured":"MMPose Contributors. OpenMMLab Pose Estimation Toolbox and Benchmark, 2020. Available at: https:\/\/github.com\/open-mmlab\/mmpose."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_24_1","DOI":"10.1109\/ICCV.2015.169"},{"doi-asserted-by":"crossref","unstructured":"He K. Zhang X. Ren S. and Sun J. 2016. Deep residual learning for image recognition.In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770778).","key":"e_1_3_2_1_25_1","DOI":"10.1109\/CVPR.2016.90"}],"event":{"acronym":"CSAI 2023","name":"CSAI 2023: 2023 7th International Conference on Computer Science and Artificial Intelligence","location":"Beijing China"},"container-title":["Proceedings of the 2023 7th International Conference on Computer Science and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3638584.3638641","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3638584.3638641","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T14:56:38Z","timestamp":1755874598000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3638584.3638641"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,8]]},"references-count":25,"alternative-id":["10.1145\/3638584.3638641","10.1145\/3638584"],"URL":"https:\/\/doi.org\/10.1145\/3638584.3638641","relation":{},"subject":[],"published":{"date-parts":[[2023,12,8]]},"assertion":[{"value":"2024-03-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}