{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:08:41Z","timestamp":1755907721550,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,18]],"date-time":"2023-11-18T00:00:00Z","timestamp":1700265600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0102"],"award-info":[{"award-number":["2021SHZDZX0102"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,18]]},"DOI":"10.1145\/3603273.3636495","type":"proceedings-article","created":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T18:12:40Z","timestamp":1704823960000},"page":"101-106","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Human Pose Estimation with Combined Feature Maps and Joint Embeddings"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1216-3538","authenticated-orcid":false,"given":"Tianyuan","family":"Han","sequence":"first","affiliation":[{"name":"SJTU Paris Elite Institute of Technology, Shanghai Jiao Tong University, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8636-3221","authenticated-orcid":false,"given":"Ganyu","family":"Huang","sequence":"additional","affiliation":[{"name":"SJTU Paris Elite Institute of Technology, Shanghai Jiao Tong University, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6876-2822","authenticated-orcid":false,"given":"Chunhui","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electronic, Information and Electrical Engineering, Shanghai Jiao Tong University, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2688-1868","authenticated-orcid":false,"given":"Liping","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, China"}]}],"member":"320","published-online":{"date-parts":[[2024,1,9]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"481","volume-title":"H and Wei Y 2018 Simple baselines for human pose estimation and tracking Proc. of the European Conf. on Computer Vision 6","author":"Xiao B","unstructured":"Xiao B, Wu, H and Wei Y 2018 Simple baselines for human pose estimation and tracking Proc. of the European Conf. on Computer Vision 6 pp 466\u2013481."},{"key":"e_1_3_2_1_2_1","first-page":"13127","volume-title":"Lin X and Zou Q 2022 Location-free human pose estimation Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition","author":"Xu X","unstructured":"Xu X, Gao Y, Yan K, Lin X and Zou Q 2022 Location-free human pose estimation Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition pp 13127-13136."},{"key":"e_1_3_2_1_3_1","first-page":"8074","volume-title":"Wang X and Hua G 2021 Learning dynamics via graph neural networks for human pose estimation and tracking Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition","author":"Yang Y","unstructured":"Yang Y, Ren Z, Li H, Zhou C, Wang X and Hua G 2021 Learning dynamics via graph neural networks for human pose estimation and tracking Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition pp 8074-8084."},{"key":"e_1_3_2_1_4_1","first-page":"534","volume-title":"Yang B and Wang X 2021 Deep dual consecutive network for human pose estimation Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition","author":"Liu Z","unstructured":"Liu Z, Chen H, Feng R, Wu S, Ji S, Yang B and Wang X 2021 Deep dual consecutive network for human pose estimation Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition pp 525\u2013534."},{"key":"e_1_3_2_1_5_1","first-page":"10996","volume-title":"Gao Y and Wang X 2022 Temporal feature alignment and mutual information maximization for video-based human pose estimation Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition","author":"Liu Z","unstructured":"Liu Z, Feng R, Chen H, Wu S, Gao Y, Gao Y and Wang X 2022 Temporal feature alignment and mutual information maximization for video-based human pose estimation Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition pp 10996-11006."},{"key":"e_1_3_2_1_6_1","first-page":"1321","volume-title":"Li K and Liu Y 2020 4D association graph for realtime multi-person motion capture using multiple video cameras Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition","author":"Zhang Y","unstructured":"Zhang Y, An L, Yu T, Li X, Li K and Liu Y 2020 4D association graph for realtime multi-person motion capture using multiple video cameras Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition pp 1321-1330."},{"key":"e_1_3_2_1_7_1","first-page":"1302","volume-title":"Wei S and Sheikh Y 2017 Realtime multi-person 2d pose estimation using part affinity fields Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition","author":"Cao Z","unstructured":"Cao Z, Simon T, Wei S and Sheikh Y 2017 Realtime multi-person 2d pose estimation using part affinity fields Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition pp 1302-1310."},{"volume-title":"P\u00e9rez P and Theobalt C 2021 Neural monocular 3d human motion capture with physical awareness ACM Transactions on Graphics 40(4): 1-15","author":"Shimada S","key":"e_1_3_2_1_8_1","unstructured":"Shimada S, Golyanik V, Xu W, P\u00e9rez P and Theobalt C 2021 Neural monocular 3d human motion capture with physical awareness ACM Transactions on Graphics 40(4): 1-15."},{"key":"e_1_3_2_1_9_1","first-page":"4628","volume-title":"IEEE Conf. on Computer Vision and Pattern Recognition","author":"Raaj Y","year":"2019","unstructured":"Raaj Y, Idrees H, Hidalgo G and Yaser Sheikh 2019 Efficient online multi-person 2d pose tracking with recurrent spatio-temporal affinity fields Proc. IEEE Conf. on Computer Vision and Pattern Recognition pp 4620\u20134628."},{"key":"e_1_3_2_1_10_1","first-page":"11096","volume-title":"Tighe J and Modolo D 2020 Combining detection and tracking for human pose estimation in videos Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition","author":"Wang M","unstructured":"Wang M, Tighe J and Modolo D 2020 Combining detection and tracking for human pose estimation in videos Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition pp 11088\u201311096."},{"key":"e_1_3_2_1_11_1","first-page":"488","volume-title":"Han X and Cui S 2020 Peeking into occluded joints: a novel framework for crowd pose estimation. Proc. European Conf. on Computer Vision 19","author":"Qiu L","unstructured":"Qiu L, Zhang X, Li Y, Li G, Wu X, Xiong Z, Han X and Cui S 2020 Peeking into occluded joints: a novel framework for crowd pose estimation. Proc. European Conf. on Computer Vision 19 pp 488-504."},{"key":"e_1_3_2_1_12_1","first-page":"5167","volume-title":"Gall J and Schiele B 2018 PoseTrack: a benchmark for human pose estimation and tracking Proc. IEEE Conf. on Computer Vision and Pattern Recognition","author":"Andriluka M","unstructured":"Andriluka M, Iqbal U, Insafutdinov E, Pishchulin L, Milan A, Gall J and Schiele B 2018 PoseTrack: a benchmark for human pose estimation and tracking Proc. IEEE Conf. on Computer Vision and Pattern Recognition pp 5167-5176."},{"key":"e_1_3_2_1_13_1","first-page":"2980","volume-title":"Doll\u00e1r P and Girshick R B 2017 Mask R-CNN Proc. of the IEEE Int. Conf. on Computer Vision","author":"He K","unstructured":"He K, Gkioxari G, Doll\u00e1r P and Girshick R B 2017 Mask R-CNN Proc. of the IEEE Int. Conf. on Computer Vision pp 2980-2988."},{"key":"e_1_3_2_1_14_1","first-page":"350","volume-title":"Paluri M and Tran D 2018 Detect-and-track: efficient pose estimation in videos Proc. IEEE Conf. on Computer Vision and Pattern Recognition","author":"Girdhar R","unstructured":"Girdhar R, Gkioxari G, Torresani L, Paluri M and Tran D 2018 Detect-and-track: efficient pose estimation in videos Proc. IEEE Conf. on Computer Vision and Pattern Recognition pp 350-359."},{"key":"e_1_3_2_1_15_1","first-page":"5253","volume-title":"Athanasiou N and Black M J 2020 VIBE: video inference for human body pose and shape estimation Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition","author":"Kocabas M","unstructured":"Kocabas M, Athanasiou N and Black M J 2020 VIBE: video inference for human body pose and shape estimation Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition pp 5253-5263."},{"key":"e_1_3_2_1_16_1","first-page":"7753","volume-title":"Grangier D and Auli M 2019 3D human pose estimation in video with temporal convolutions and semi-supervised training Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition","author":"Pavllo D","unstructured":"Pavllo D, Feichtenhofer C, Grangier D and Auli M 2019 3D human pose estimation in video with temporal convolutions and semi-supervised training Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition pp 7753-7762."},{"key":"e_1_3_2_1_17_1","first-page":"5673","volume-title":"Ouyang W and Qian C 2019 Multi-person articulated tracking with spatial and temporal embeddings Proc. IEEE Conf. on Computer Vision and Pattern Recognition","author":"Jin S","unstructured":"Jin S, Liu W, Ouyang W and Qian C 2019 Multi-person articulated tracking with spatial and temporal embeddings Proc. IEEE Conf. on Computer Vision and Pattern Recognition pp 5664\u20135673."},{"key":"e_1_3_2_1_18_1","first-page":"5693","volume-title":"Wang J 2019 Deep high-resolution representation learning for human pose estimation Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition","author":"Sun H","unstructured":"Sun H, Xiao B, Liu D, Wang J 2019 Deep high-resolution representation learning for human pose estimation Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition pp 5693-5703."},{"key":"e_1_3_2_1_19_1","first-page":"1944","volume-title":"Xu W and Tu Z 2021 Pose recognition with cascade transformers Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition","author":"Li K","unstructured":"Li K, Wang S, Zhang X, Xu Y, Xu W and Tu Z 2021 Pose recognition with cascade transformers Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition pp 1944-1953."},{"key":"e_1_3_2_1_20_1","first-page":"9308","volume-title":"Lin S and Dai J 2019 Deformable convnets v2: more deformable, better results Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition","author":"Zhu X","unstructured":"Zhu X, Hu H, Lin S and Dai J 2019 Deformable convnets v2: more deformable, better results Proc. IEEE\/CVF Conf. on Computer Vision and Pattern Recognition pp 9308-9316."},{"volume-title":"Li\u00f2 P and Bengio Y 2018 Graph Attention Networks Int. Conf. on Learning Representations Poster","author":"Veli\u010dkovi\u0107 P","key":"e_1_3_2_1_21_1","unstructured":"Veli\u010dkovi\u0107 P, Cucurull G, Casanova A, Romero A, Li\u00f2 P and Bengio Y 2018 Graph Attention Networks Int. Conf. on Learning Representations Poster"},{"key":"e_1_3_2_1_22_1","first-page":"6008","volume-title":"Proc. Conf. on Neural Information Processing Systems","author":"Vaswani A","year":"2017","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez A N, Kaiser L and Polosukhin I, 2017, Attention is all you need, Proc. Conf. on Neural Information Processing Systems, pp. 5998\u20136008."},{"volume-title":"Zhang R and Li J 2019 Differentiable learning-to-normalize via switchable normalization Int. Conf. on Learning Representations Poster","author":"Luo P","key":"e_1_3_2_1_23_1","unstructured":"Luo P, Ren J, Peng Z, Zhang R and Li J 2019 Differentiable learning-to-normalize via switchable normalization Int. Conf. on Learning Representations Poster"},{"key":"e_1_3_2_1_24_1","unstructured":"Hendrycks D and Gimpel K 2016 Bridging nonlinearities and stochastic regularizers with gaussian error linear units arXiv preprint."},{"key":"e_1_3_2_1_25_1","first-page":"740","volume-title":"Doll\u00e1r P and Zitnick C L 2014 Microsoft COCO: common objects in context Proc. European Conf. on Computer Vision 5","author":"Lin T","unstructured":"Lin T, Maire M, Belongie S J, Hays J, Perona P, Ramanan D, Doll\u00e1r P and Zitnick C L 2014 Microsoft COCO: common objects in context Proc. European Conf. on Computer Vision 5 pp 740-755."},{"volume-title":"Ba J 2015 Adam: a method for stochastic optimization Int. Conf. on Learning Representations Poster.","author":"Kingma D P","key":"e_1_3_2_1_26_1","unstructured":"Kingma D P and Ba J 2015 Adam: a method for stochastic optimization Int. Conf. on Learning Representations Poster."},{"key":"e_1_3_2_1_27_1","unstructured":"Redmon J and Farhadi A 2018 Yolov3: an incremental improvement arXiv preprint."},{"volume-title":"Li Y and Lu C 2022 AlphaPose: whole-body regional multi-person pose estimation and tracking in real-time arXiv preprint.","author":"Fang H","key":"e_1_3_2_1_28_1","unstructured":"Fang H, Li J, Tang H, Xu C, Zhu H, Xiu Y, Li Y and Lu C 2022 AlphaPose: whole-body regional multi-person pose estimation and tracking in real-time arXiv preprint."},{"key":"e_1_3_2_1_29_1","first-page":"3038","volume-title":"Shi J and Torresani L 2019 Learning temporal pose estimation from sparsely-labeled videos Proc. Conf. on Neural Information Processing Systems","author":"Bertasius G","unstructured":"Bertasius G, Feichtenhofer C, Tran D, Shi J and Torresani L 2019 Learning temporal pose estimation from sparsely-labeled videos Proc. Conf. on Neural Information Processing Systems pp 3027\u20133038."}],"event":{"name":"AAIA 2023: 2023 International Conference on Advances in Artificial Intelligence and Applications","acronym":"AAIA 2023","location":"Wuhan China"},"container-title":["Proceedings of the 2023 International Conference on Advances in Artificial Intelligence and Applications"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3603273.3636495","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3603273.3636495","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T19:34:55Z","timestamp":1755891295000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3603273.3636495"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,18]]},"references-count":29,"alternative-id":["10.1145\/3603273.3636495","10.1145\/3603273"],"URL":"https:\/\/doi.org\/10.1145\/3603273.3636495","relation":{},"subject":[],"published":{"date-parts":[[2023,11,18]]},"assertion":[{"value":"2024-01-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}