{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T15:55:18Z","timestamp":1758815718103,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":61,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T00:00:00Z","timestamp":1729987200000},"content-version":"vor","delay-in-days":367,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"U.S. Department of Commerce's National Institute of Standards and Technology","award":["60NANB17D156"],"award-info":[{"award-number":["60NANB17D156"]}]},{"name":"US Department of Transportation","award":["69A3551747111"],"award-info":[{"award-number":["69A3551747111"]}]},{"DOI":"10.13039\/100006754","name":"Army Research Laboratory","doi-asserted-by":"publisher","award":["W911NF-17-5-0003"],"award-info":[{"award-number":["W911NF-17-5-0003"]}],"id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006602","name":"Air Force Research Laboratory","doi-asserted-by":"publisher","award":["FA8750-19-2-0200"],"award-info":[{"award-number":["FA8750-19-2-0200"]}],"id":[{"id":"10.13039\/100006602","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100011039","name":"Intelligence Advanced Research Projects Activity","doi-asserted-by":"publisher","award":["D17PC00340"],"award-info":[{"award-number":["D17PC00340"]}],"id":[{"id":"10.13039\/100011039","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3612366","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:26:54Z","timestamp":1698391614000},"page":"5746-5755","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["KeyPosS: Plug-and-Play Facial Landmark Detection through GPS-Inspired True-Range Multilateration"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2402-4855","authenticated-orcid":false,"given":"Xu","family":"Bao","sequence":"first","affiliation":[{"name":"DAMO Academy, Alibaba Group, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1720-2085","authenticated-orcid":false,"given":"Zhi-Qi","family":"Cheng","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6628-6924","authenticated-orcid":false,"given":"Jun-Yan","family":"He","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4373-2610","authenticated-orcid":false,"given":"Wangmeng","family":"Xiang","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6473-5784","authenticated-orcid":false,"given":"Chenyang","family":"Li","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9828-3265","authenticated-orcid":false,"given":"Jingdong","family":"Sun","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5988-2306","authenticated-orcid":false,"given":"Hanbing","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7113-9582","authenticated-orcid":false,"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9427-8251","authenticated-orcid":false,"given":"Bin","family":"Luo","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3257-2746","authenticated-orcid":false,"given":"Yifeng","family":"Geng","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5746-9457","authenticated-orcid":false,"given":"Xuansong","family":"Xie","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0667-3"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929257"},{"key":"e_1_3_2_1_3_1","volume-title":"Attention-Driven Cropping for Very High Resolution Facial Landmark Detection. In IEEE Conference on Computer Vision and Pattern Recognition.","author":"Chandran Prashanth","year":"2020","unstructured":"Prashanth Chandran, Derek Bradley, Markus H. Gross, and Thabo Beeler. 2020. Attention-Driven Cropping for Very High Resolution Facial Landmark Detection. In IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_2_1_4_1","volume-title":"HDFormer: High-order Directed Transformer for 3D Human Pose Estimation. arXiv preprint arXiv:2302.01825","author":"Chen Hanyuan","year":"2023","unstructured":"Hanyuan Chen, Jun-Yan He, Wangmeng Xiang, Wei Liu, Zhi-Qi Cheng, Hanbing Liu, Bin Luo, Yifeng Geng, and Xuansong Xie. 2023. HDFormer: High-order Directed Transformer for 3D Human Pose Estimation. arXiv preprint arXiv:2302.01825 (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01902"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547943"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00625"},{"key":"e_1_3_2_1_8_1","volume-title":"Improving the Learning of Multi-column Convolutional Neural Network for Crowd Counting. In ACM International Conference on Multimedia. 1897--1906","author":"Cheng Zhi-Qi","year":"2019","unstructured":"Zhi-Qi Cheng, Jun-Xiu Li, Qi Dai, Xiao Wu, Jun-Yan He, and Alexander G Hauptmann. 2019b. Improving the Learning of Multi-column Convolutional Neural Network for Crowd Counting. In ACM International Conference on Multimedia. 1897--1906."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2964326"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240518"},{"key":"e_1_3_2_1_11_1","volume-title":"Video ecommerce: Toward large scale online video advertising","author":"Cheng Zhi-Qi","year":"2017","unstructured":"Zhi-Qi Cheng, Xiao Wu, Yang Liu, and Xian-Sheng Hua. 2017a. Video ecommerce: Toward large scale online video advertising. IEEE transactions on multimedia, Vol. 19, 6 (2017), 1170--1183."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.444"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3079025"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2008.01.024"},{"key":"e_1_3_2_1_15_1","volume-title":"DeCaFA: Deep Convolutional Cascade for Face Alignment in the Wild. In IEEE International Conference on Computer Vision. 6892--6900","author":"Dapogny Arnaud","year":"2019","unstructured":"Arnaud Dapogny, Matthieu Cord, and Kevin Bailly. 2019. DeCaFA: Deep Convolutional Cascade for Face Alignment in the Wild. In IEEE International Conference on Computer Vision. 6892--6900."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956683"},{"key":"e_1_3_2_1_17_1","volume-title":"Wing Loss for Robust Facial Landmark Localisation With Convolutional Neural Networks. In IEEE Conference on Computer Vision and Pattern Recognition. 2235--2245","author":"Feng Zhen-Hua","year":"2018","unstructured":"Zhen-Hua Feng, Josef Kittler, Muhammad Awais, Patrik Huber, and Xiao-Jun Wu. 2018. Wing Loss for Robust Facial Landmark Localisation With Convolutional Neural Networks. In IEEE Conference on Computer Vision and Pattern Recognition. 2235--2245."},{"key":"e_1_3_2_1_18_1","volume-title":"Dynamic Attention-Controlled Cascaded Shape Regression Exploiting Training Data Augmentation and Fuzzy-Set Sample Weighting. In IEEE Conference on Computer Vision and Pattern Recognition. 3681--3690","author":"Feng Zhen-Hua","year":"2017","unstructured":"Zhen-Hua Feng, Josef Kittler, William J. Christmas, Patrik Huber, and Xiaojun Wu. 2017. Dynamic Attention-Controlled Cascaded Shape Regression Exploiting Training Data Augmentation and Fuzzy-Set Sample Weighting. In IEEE Conference on Computer Vision and Pattern Recognition. 3681--3690."},{"key":"e_1_3_2_1_19_1","volume-title":"DAMO-StreamNet: Optimizing Streaming Perception in Autonomous Driving. arXiv preprint arXiv:2303.17144","author":"He Jun-Yan","year":"2023","unstructured":"Jun-Yan He, Zhi-Qi Cheng, Chenyang Li, Wangmeng Xiang, Binghui Chen, Bin Luo, Yifeng Geng, and Xuansong Xie. 2023. DAMO-StreamNet: Optimizing Streaming Perception in Autonomous Driving. arXiv preprint arXiv:2303.17144 (2023)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.05.118"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.391410"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240588"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053070"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25176"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01521-4"},{"key":"e_1_3_2_1_26_1","volume-title":"Whole-Body Human Pose Estimation in the Wild. In European Conference on Computer Vision","volume":"12354","author":"Jin Sheng","year":"2020","unstructured":"Sheng Jin, Lumin Xu, Jin Xu, Can Wang, Wentao Liu, Chen Qian, Wanli Ouyang, and Ping Luo. 2020. Whole-Body Human Pose Estimation in the Wild. In European Conference on Computer Vision, Vol. 12354. 196--214."},{"volume-title":"Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations, Yoshua Bengio and Yann LeCun (Eds.).","author":"Diederik","key":"e_1_3_2_1_27_1","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In International Conference on Learning Representations, Yoshua Bengio and Yann LeCun (Eds.)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130513"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00826"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094971"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094855"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00414"},{"key":"e_1_3_2_1_33_1","volume-title":"Repformer: Refinement pyramid transformer for robust facial landmark detection. arXiv preprint arXiv:2207.03917","author":"Li Jinpeng","year":"2022","unstructured":"Jinpeng Li, Haibo Jin, Shengcai Liao, Ling Shao, and Pheng-Ann Heng. 2022b. Repformer: Refinement pyramid transformer for robust facial landmark detection. arXiv preprint arXiv:2207.03917 (2022)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_16"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_16"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.393"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.393"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-88693-8_37"},{"key":"e_1_3_2_1_39_1","volume-title":"Stacked Hourglass Networks for Human Pose Estimation. In European Conference on Computer Vision","volume":"9912","author":"Newell Alejandro","year":"2016","unstructured":"Alejandro Newell, Kaiyu Yang, and Jia Deng. 2016. Stacked Hourglass Networks for Human Pose Estimation. In European Conference on Computer Vision, Vol. 9912. 483--499."},{"key":"e_1_3_2_1_40_1","unstructured":"Phuong Anh Nguyen Qing Li Zhi-Qi Cheng Yi-Jie Lu Hao Zhang Xiao Wu and Chong-Wah Ngo. 2017. Vireo@ TRECVID 2017: Video-to-text ad-hoc video search and video hyperlinking. (2017)."},{"key":"e_1_3_2_1_41_1","volume-title":"Prendergast","author":"Nibali Aiden","year":"2018","unstructured":"Aiden Nibali, Zhen He, Stuart Morgan, and Luke A. Prendergast. 2018. Numerical Coordinate Regression with Convolutional Neural Networks. CoRR, Vol. abs\/1801.07372 (2018)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01025"},{"volume-title":"Medical Image Computing and Computer-Assisted Intervention","author":"Ronneberger Olaf","key":"e_1_3_2_1_43_1","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. In Medical Image Computing and Computer-Assisted Intervention. Springer, 234--241."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2016.01.002"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-5245-1"},{"key":"e_1_3_2_1_47_1","volume-title":"Deep High-Resolution Representation Learning for Human Pose Estimation. In IEEE Conference on Computer Vision and Pattern Recognition. 5693--5703","author":"Sun Ke","year":"2019","unstructured":"Ke Sun, Bin Xiao, Dong Liu, and Jingdong Wang. 2019. Deep High-Resolution Representation Learning for Human Pose Estimation. In IEEE Conference on Computer Vision and Pattern Recognition. 5693--5703."},{"volume-title":"Quantized Densely Connected U-Nets for Efficient Landmark Localization. In European Conference on Computer Vision. 348--364","author":"Tang Zhiqiang","key":"e_1_3_2_1_48_1","unstructured":"Zhiqiang Tang, Xi Peng, Shijie Geng, Lingfei Wu, Shaoting Zhang, and Dimitris N. Metaxas. 2018. Quantized Densely Connected U-Nets for Efficient Landmark Localization. In European Conference on Computer Vision. 348--364."},{"key":"e_1_3_2_1_49_1","volume-title":"Implicit temporal modeling with learnable alignment for video recognition. arXiv preprint arXiv:2304.10465","author":"Tu Shuyuan","year":"2023","unstructured":"Shuyuan Tu, Qi Dai, Zuxuan Wu, Zhi-Qi Cheng, Han Hu, and Yu-Gang Jiang. 2023. Implicit temporal modeling with learnable alignment for video recognition. arXiv preprint arXiv:2304.10465 (2023)."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3261749"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00707"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00227"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00402"},{"key":"e_1_3_2_1_54_1","volume-title":"Distribution-Aware Coordinate Representation for Human Pose Estimation. In IEEE Conference on Computer Vision and Pattern Recognition. 7091--7100","author":"Zhang Feng","year":"2020","unstructured":"Feng Zhang, Xiatian Zhu, Hanbin Dai, Mao Ye, and Ce Zhu. 2020. Distribution-Aware Coordinate Representation for Human Pose Estimation. In IEEE Conference on Computer Vision and Pattern Recognition. 7091--7100."},{"key":"e_1_3_2_1_55_1","volume-title":"2023 a. Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness. arXiv preprint arXiv:2305.11468","author":"Zhou Yuxuan","year":"2023","unstructured":"Yuxuan Zhou, Zhi-Qi Cheng, Jun-Yan He, Bin Luo, Yifeng Geng, Xuansong Xie, and Margret Keuper. 2023 a. Overcoming Topology Agnosticism: Enhancing Skeleton-Based Action Recognition through Redefined Skeletal Topology Awareness. arXiv preprint arXiv:2305.11468 (2023)."},{"key":"e_1_3_2_1_56_1","volume-title":"Hypergraph transformer for skeleton-based action recognition. arXiv preprint arXiv:2211.09590","author":"Zhou Yuxuan","year":"2022","unstructured":"Yuxuan Zhou, Chao Li, Zhi-Qi Cheng, Yifeng Geng, Xuansong Xie, and Margret Keuper. 2022. Hypergraph transformer for skeleton-based action recognition. arXiv preprint arXiv:2211.09590 (2022)."},{"key":"e_1_3_2_1_57_1","volume-title":"STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 15475--15484","author":"Zhou Zhenglin","year":"2023","unstructured":"Zhenglin Zhou, Huaxia Li, Hong Liu, Nanyang Wang, Gang Yu, and Rongrong Ji. 2023 b. STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 15475--15484."},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00360"},{"key":"e_1_3_2_1_59_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition. 4998--5006","author":"Zhu Shizhan","year":"2015","unstructured":"Shizhan Zhu, Cheng Li, Chen Change Loy, and Xiaoou Tang. 2015a. Face alignment by coarse-to-fine shape searching. In IEEE Conference on Computer Vision and Pattern Recognition. 4998--5006."},{"key":"e_1_3_2_1_60_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition. 4998--5006","author":"Zhu Shizhan","year":"2015","unstructured":"Shizhan Zhu, Cheng Li, Chen Change Loy, and Xiaoou Tang. 2015b. Face alignment by coarse-to-fine shape searching. In IEEE Conference on Computer Vision and Pattern Recognition. 4998--5006."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00023"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Ottawa ON Canada","acronym":"MM '23"},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612366","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612366","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3612366","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:03:07Z","timestamp":1755820987000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3612366"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":61,"alternative-id":["10.1145\/3581783.3612366","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3612366","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}