{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T22:35:55Z","timestamp":1768343755643,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,30]],"date-time":"2024-05-30T00:00:00Z","timestamp":1717027200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62172421, 62072459"],"award-info":[{"award-number":["62172421, 62072459"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,30]]},"DOI":"10.1145\/3652583.3658048","type":"proceedings-article","created":{"date-parts":[[2024,6,7]],"date-time":"2024-06-07T06:30:40Z","timestamp":1717741840000},"page":"37-45","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["PoseRec: 3D Human Pose Driven Online Advertisement Recommendation for Micro-videos"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6324-1712","authenticated-orcid":false,"given":"Zhaoxin","family":"Fan","sequence":"first","affiliation":[{"name":"Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8828-2767","authenticated-orcid":false,"given":"Fengxin","family":"Li","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4902-1078","authenticated-orcid":false,"given":"Hongyan","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1511-7554","authenticated-orcid":false,"given":"Jun","family":"He","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5757-9135","authenticated-orcid":false,"given":"Xiaoyong","family":"Du","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2024,6,7]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"BlazePose: On-device Real-time Body Pose tracking. CoRR","author":"Bazarevsky Valentin","year":"2020","unstructured":"Valentin Bazarevsky, Ivan Grishchenko, Karthik Raveendran, Tyler Zhu, Fan Zhang, and Matthias Grundmann. 2020. BlazePose: On-device Real-time Body Pose tracking. CoRR, Vol. abs\/2006.10204 (2020)."},{"key":"e_1_3_2_1_2_1","volume-title":"Quoc Cuong Pham, and Catherine Achard","author":"Benzine Abdallah","year":"2021","unstructured":"Abdallah Benzine, Bertrand Luvison, Quoc Cuong Pham, and Catherine Achard. 2021. Single-shot 3D multi-person pose estimation in complex images. Pattern Recognit. (2021)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Diane Bouchacourt Ryota Tomioka and Sebastian Nowozin. 2018. Multi-Level Variational Autoencoder: Learning Disentangled Representations From Grouped Observations. In AAAI-19.","DOI":"10.1609\/aaai.v32i1.11867"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3059508"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Da Cao Lianhai Miao Huigui Rong Zheng Qin and Liqiang Nie. 2020. Hashtag our stories: Hashtag recommendation for micro-videos via harnessing multiple modalities. Knowl. Based Syst. (2020).","DOI":"10.1016\/j.knosys.2020.106114"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"e_1_3_2_1_7_1","volume-title":"Adaptive Factorization Network: Learning Adaptive-Order Feature Interactions. In AAAI","author":"Cheng Weiyu","year":"2020","unstructured":"Weiyu Cheng, Yanyan Shen, and Linpeng Huang. 2020. Adaptive Factorization Network: Learning Adaptive-Order Feature Interactions. In AAAI 2020."},{"key":"e_1_3_2_1_8_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. 2017. Video eCommerce: Toward Large Scale Online Video Advertising. IEEE Trans. Multim. (2017)."},{"key":"e_1_3_2_1_9_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT 2019."},{"key":"e_1_3_2_1_10_1","volume-title":"RMPE: Regional Multi-person Pose Estimation. In ICCV","author":"Fang Haoshu","year":"2017","unstructured":"Haoshu Fang, Shuqin Xie, Yu-Wing Tai, and Cewu Lu. 2017. RMPE: Regional Multi-person Pose Estimation. In ICCV 2017."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00847"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/239"},{"key":"e_1_3_2_1_13_1","volume-title":"Neural Collaborative Filtering. In WWW","author":"He Xiangnan","year":"2017","unstructured":"Xiangnan He, Lizi Liao, Hanwang Zhang, Liqiang Nie, Xia Hu, and Tat-Seng Chua. 2017. Neural Collaborative Filtering. In WWW 2017."},{"key":"e_1_3_2_1_14_1","volume-title":"ICLR","author":"Higgins Irina","year":"2017","unstructured":"Irina Higgins, Lo\u00efc Matthey, Arka Pal, Christopher P. Burgess, Xavier Glorot, Matthew M. Botvinick, Shakir Mohamed, and Alexander Lerchner. 2017. beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework. In ICLR 2017."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413653"},{"key":"e_1_3_2_1_16_1","volume-title":"Personalized Micro-video Recommendation Based on Multi-modal Features and User Interest Evolution. In ICIG 2019 (Lecture Notes in Computer Science).","author":"Jin Yingying","year":"2019","unstructured":"Yingying Jin, Juan Xu, and Xin He. 2019. Personalized Micro-video Recommendation Based on Multi-modal Features and User Interest Evolution. In ICIG 2019 (Lecture Notes in Computer Science)."},{"key":"e_1_3_2_1_17_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In ICLR 2015."},{"key":"e_1_3_2_1_18_1","volume-title":"MultiPoseNet: Fast Multi-Person Pose Estimation Using Pose Residual Network. In ECCV","author":"Kocabas Muhammed","year":"2018","unstructured":"Muhammed Kocabas, Salih Karagoz, and Emre Akbas. 2018. MultiPoseNet: Fast Multi-Person Pose Estimation Using Pose Residual Network. In ECCV 2019."},{"key":"e_1_3_2_1_19_1","volume-title":"PifPaf: Composite Fields for Human Pose Estimation. In CVPR","author":"Kreiss Sven","year":"2019","unstructured":"Sven Kreiss, Lorenzo Bertoni, and Alexandre Alahi. 2019. PifPaf: Composite Fields for Human Pose Estimation. In CVPR 2019."},{"key":"e_1_3_2_1_20_1","volume-title":"SEMI: A Sequential Multi-Modal Information Transfer Network for E-Commerce Micro-Video Recommendations. In KDD '21","author":"Lei Chenyi","year":"2021","unstructured":"Chenyi Lei, Yong Liu, Lingzi Zhang, Guoxin Wang, Haihong Tang, Houqiang Li, and Chunyan Miao. 2021. SEMI: A Sequential Multi-Modal Information Transfer Network for E-Commerce Micro-Video Recommendations. In KDD '21."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01112"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00339"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350950"},{"key":"e_1_3_2_1_24_1","unstructured":"Chen-Yi Lin Tung-Shou Chen Jeanne Chen and Chih-Yu Chen. 2021. Personalized live streaming channel recommendation based on most similar neighbors. Multim. Tools Appl. (2021)."},{"key":"e_1_3_2_1_25_1","volume-title":"Sen-Ching Samson Cheung, and Vijayan K. Asari","author":"Liu Ruixu","year":"2021","unstructured":"Ruixu Liu, Ju Shen, He Wang, Chen Chen, Sen-Ching Samson Cheung, and Vijayan K. Asari. 2021b. Enhanced 3D Human Pose Estimation from Videos by Using Attention-Based Neural Network with Dilated Convolutions. Int. J. Comput. Vis. (2021)."},{"key":"e_1_3_2_1_26_1","volume-title":"User Conditional Hashtag Recommendation for Micro-Videos. In ICME","author":"Liu Shang","year":"2020","unstructured":"Shang Liu, Jiayi Xie, Cong Zou, and Zhenzhong Chen. 2020. User Conditional Hashtag Recommendation for Micro-Videos. In ICME 2020."},{"key":"e_1_3_2_1_27_1","volume-title":"Concept-Aware Denoising Graph Neural Network for Micro-Video Recommendation. In CIKM '21","author":"Liu Yiyu","year":"2021","unstructured":"Yiyu Liu, Qian Liu, Yu Tian, Changping Wang, Yanan Niu, Yang Song, and Chenliang Li. 2021a. Concept-Aware Denoising Graph Neural Network for Micro-Video Recommendation. In CIKM '21."},{"key":"e_1_3_2_1_28_1","volume-title":"Multi-trends Enhanced Dynamic Micro-video Recommendation. CoRR","author":"Lu Yujie","year":"2021","unstructured":"Yujie Lu, Yingxuan Huang, Shengyu Zhang, Wei Han, Hui Chen, Zhou Zhao, and Fei Wu. 2021. Multi-trends Enhanced Dynamic Micro-video Recommendation. CoRR (2021)."},{"key":"e_1_3_2_1_29_1","volume-title":"NeurIPS","author":"Ma Jianxin","year":"2019","unstructured":"Jianxin Ma, Chang Zhou, Peng Cui, Hongxia Yang, and Wenwu Zhu. 2019. Learning Disentangled Representations for Recommendation. In NeurIPS 2019."},{"key":"e_1_3_2_1_30_1","volume-title":"Disentangled Self-Supervision in Sequential Recommenders. In KDD '20","author":"Ma Jianxin","year":"2020","unstructured":"Jianxin Ma, Chang Zhou, Hongxia Yang, Peng Cui, Xin Wang, and Wenwu Zhu. 2020. Disentangled Self-Supervision in Sequential Recommenders. In KDD '20."},{"key":"e_1_3_2_1_31_1","volume-title":"Ju Yong Chang, and Kyoung Mu Lee","author":"Moon Gyeongsik","year":"2019","unstructured":"Gyeongsik Moon, Ju Yong Chang, and Kyoung Mu Lee. 2019. PoseFix: Model-Agnostic General Human Pose Refinement Network. In CVPR 2019."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"e_1_3_2_1_33_1","volume-title":"Factorization Machines. In ICDM","author":"Rendle Steffen","year":"2010","unstructured":"Steffen Rendle. 2010. Factorization Machines. In ICDM 2010, Geoffrey I. Webb, Bing Liu, Chengqi Zhang, Dimitrios Gunopulos, and Xindong Wu (Eds.)."},{"key":"e_1_3_2_1_34_1","volume-title":"Sequential Modeling with Multiple Attributes for Watchlist Recommendation in E-Commerce. In WSDM '22","author":"Singer Uriel","year":"2022","unstructured":"Uriel Singer, Haggai Roitman, Yotam Eshel, Alexander Nus, Ido Guy, Or Levi, Idan Hasson, and Eliyahu Kiperwasser. 2022. Sequential Modeling with Multiple Attributes for Watchlist Recommendation in E-Commerce. In WSDM '22."},{"key":"e_1_3_2_1_35_1","volume-title":"Deep High-Resolution Representation Learning for Human Pose Estimation. In CVPR","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 CVPR 2019."},{"key":"e_1_3_2_1_36_1","volume-title":"C3D: Generic Features for Video Analysis. CoRR","author":"Tran Du","year":"2014","unstructured":"Du Tran, Lubomir D. Bourdev, Rob Fergus, Lorenzo Torresani, and Manohar Paluri. 2014. C3D: Generic Features for Video Analysis. CoRR, Vol. abs\/1412.0767 (2014)."},{"key":"e_1_3_2_1_37_1","volume-title":"Video Classification With Channel-Separated Convolutional Networks. In ICCV","author":"Tran Du","year":"2019","unstructured":"Du Tran, Heng Wang, Matt Feiszli, and Lorenzo Torresani. 2019. Video Classification With Channel-Separated Convolutional Networks. In ICCV 2019."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/UEMCON.2017.8248975"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531970"},{"key":"e_1_3_2_1_40_1","volume-title":"Veracity-aware and Event-driven Personalized News Recommendation for Fake News Mitigation. In WWW '22","author":"Wang Shoujin","year":"2022","unstructured":"Shoujin Wang, Xiaofei Xu, Xiuzhen Zhang, Yan Wang, and Wenzhuo Song. 2022b. Veracity-aware and Event-driven Personalized News Recommendation for Fake News Mitigation. In WWW '22."},{"key":"e_1_3_2_1_41_1","volume-title":"Convolutional Pose Machines. In CVPR","author":"Wei Shih-En","year":"2016","unstructured":"Shih-En Wei, Varun Ramakrishna, Takeo Kanade, and Yaser Sheikh. 2016. Convolutional Pose Machines. In CVPR 2016."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351034"},{"key":"e_1_3_2_1_43_1","volume-title":"FeedRec: News Feed Recommendation with Various User Feedbacks. In WWW '22","author":"Wu Chuhan","year":"2022","unstructured":"Chuhan Wu, Fangzhao Wu, Tao Qi, Qi Liu, Xuan Tian, Jie Li, Wei He, Yongfeng Huang, and Xing Xie. 2022. FeedRec: News Feed Recommendation with Various User Feedbacks. In WWW '22."},{"key":"e_1_3_2_1_44_1","volume-title":"Fairness-aware News Recommendation with Decomposed Adversarial Learning. In AAAI","author":"Wu Chuhan","year":"2021","unstructured":"Chuhan Wu, Fangzhao Wu, Xiting Wang, Yongfeng Huang, and Xing Xie. 2021. Fairness-aware News Recommendation with Decomposed Adversarial Learning. In AAAI 2021."},{"key":"e_1_3_2_1_45_1","volume-title":"Simple Baselines for Human Pose Estimation and Tracking. In ECCV","author":"Xiao Bin","year":"2018","unstructured":"Bin Xiao, Haiping Wu, and Yichen Wei. 2018. Simple Baselines for Human Pose Estimation and Tracking. In ECCV 2019."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01584"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"Sijie Yan Yuanjun Xiong and Dahua Lin. 2018. Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition. In AAAI-19.","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2989473"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00947"},{"key":"e_1_3_2_1_50_1","unstructured":"Xinyu Yi Yuxiao Zhou and Feng Xu. 2021. TransPose: real-time 3D human translation and pose estimation with six inertial sensors. ACM Trans. Graph. (2021)."},{"key":"e_1_3_2_1_51_1","volume-title":"CVPR","author":"Yuan Ye","year":"2021","unstructured":"Ye Yuan, Shih-En Wei, Tomas Simon, Kris Kitani, and Jason M. Saragih. 2021. SimPoE: Simulated Character Control for 3D Human Pose Estimation. In CVPR 2021."},{"key":"e_1_3_2_1_52_1","volume-title":"Hysia: Serving DNN-Based Video-to-Retail Applications in Cloud. In MM '20","author":"Zhang Huaizheng","year":"2020","unstructured":"Huaizheng Zhang, Yuanming Li, Qiming Ai, Yong Luo, Yonggang Wen, Yichao Jin, and Ta Nguyen Binh Duong. 2020a. Hysia: Serving DNN-Based Video-to-Retail Applications in Cloud. In MM '20."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"crossref","unstructured":"Shuai Zhang Hongyan Liu Lang Mei Jun He and Xiaoyong Du. 2022. Predicting viewer's watching behavior and live streaming content change for anchor recommendation. Appl. Intell. (2022).","DOI":"10.1007\/s10489-021-02560-7"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3383313.3412239"},{"key":"e_1_3_2_1_55_1","volume-title":"Disentangling User Interest and Conformity for Recommendation with Causal Embedding. In WWW '21","author":"Zheng Yu","year":"2021","unstructured":"Yu Zheng, Chen Gao, Xiang Li, Xiangnan He, Yong Li, and Depeng Jin. 2021. Disentangling User Interest and Conformity for Recommendation with Causal Embedding. In WWW '21."},{"key":"e_1_3_2_1_56_1","volume-title":"The Recommendation Model of MiaoPai Short Video Based on Microblog. In ITQM 2019 (Procedia Computer Science).","author":"Zhu Manqing","year":"2019","unstructured":"Manqing Zhu, Yue He, Yong Huang, and Dan Zhang. 2019. The Recommendation Model of MiaoPai Short Video Based on Microblog. In ITQM 2019 (Procedia Computer Science)."}],"event":{"name":"ICMR '24: International Conference on Multimedia Retrieval","location":"Phuket Thailand","acronym":"ICMR '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia","SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 2024 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658048","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652583.3658048","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T08:51:49Z","timestamp":1755766309000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652583.3658048"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,30]]},"references-count":56,"alternative-id":["10.1145\/3652583.3658048","10.1145\/3652583"],"URL":"https:\/\/doi.org\/10.1145\/3652583.3658048","relation":{},"subject":[],"published":{"date-parts":[[2024,5,30]]},"assertion":[{"value":"2024-06-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}