{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:01:27Z","timestamp":1791910887676,"version":"4.3.4"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681452","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"5547-5555","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Monocular Human-Object Reconstruction in the Wild"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0520-788X","authenticated-orcid":false,"given":"Chaofan","family":"Huo","sequence":"first","affiliation":[{"name":"ShanghaiTech University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2302-4980","authenticated-orcid":false,"given":"Ye","family":"Shi","sequence":"additional","affiliation":[{"name":"ShanghaiTech University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1122-0634","authenticated-orcid":false,"given":"Jingya","family":"Wang","sequence":"additional","affiliation":[{"name":"ShanghaiTech University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"BEHAVE: Dataset and Method for Tracking Human Object Interactions. In CVPR. 15935--15946.","author":"Bhatnagar Bharat Lal","year":"2022","unstructured":"Bharat Lal Bhatnagar, Xianghui Xie, Ilya A. Petrov, Cristian Sminchisescu, Christian Theobalt, and Gerard Pons-Moll. 2022. BEHAVE: Dataset and Method for Tracking Human Object Interactions. In CVPR. 15935--15946."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00524"},{"key":"e_1_3_2_1_3_1","first-page":"11454","article-title":"SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation","volume":"36","author":"Cai Zhongang","year":"2023","unstructured":"Zhongang Cai, Wanqi Yin, Ailing Zeng, CHEN WEI, Qingping SUN, Wang Yanjun, Hui En Pang, Haiyi Mei, Mingyuan Zhang, Lei Zhang, Chen Change Loy, Lei Yang, and Ziwei Liu. 2023. SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation. In NeurIPS, Vol. 36. 11454--11468.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Zhe Cao Ilija Radosavovic Angjoo Kanazawa and Jitendra Malik. 2021. Reconstructing Hand-Object Interactions in the Wild. In ICCV. 12417--12426.","DOI":"10.1109\/ICCV48922.2021.01219"},{"key":"e_1_3_2_1_5_1","volume-title":"Rehg","author":"Chen Ching-Hang","year":"2019","unstructured":"Ching-Hang Chen, Ambrish Tyagi, Amit Agrawal, Dylan Drover, Rohith MV, Stefan Stojanov, and James M. Rehg. 2019. Unsupervised 3D Pose Estimation With Geometric Self-Supervision. In CVPR."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Hansheng Chen Pichao Wang Fan Wang Wei Tian Lu Xiong and Hao Li. 2022. EPro-PnP: Generalized End-to-End Probabilistic Perspective-N-Points for Monocular Object Pose Estimation. In CVPR. 2781--2790.","DOI":"10.1109\/CVPR52688.2022.00280"},{"key":"e_1_3_2_1_7_1","volume-title":"Object-Centric Domain Randomization for 3D Shape Reconstruction in the Wild. arXiv preprint arXiv:2403.14539","author":"Cho Junhyeong","year":"2024","unstructured":"Junhyeong Cho, Kim Youwang, Hunmin Yang, and Tae-Hyun Oh. 2024. Object-Centric Domain Randomization for 3D Shape Reconstruction in the Wild. arXiv preprint arXiv:2403.14539 (2024)."},{"key":"e_1_3_2_1_8_1","volume-title":"The Web Conference.","author":"Dong Wei","unstructured":"Wei Dong, Moses Charikar, and K. Li. 2011. Efficient k-nearest neighbor graph construction for generic similarity measures. In The Web Conference."},{"key":"e_1_3_2_1_9_1","volume-title":"3D Human Reconstruction in the Wild with Synthetic Data Using Generative Models. arXiv preprint arXiv:2403.11111","author":"Ge Yongtao","year":"2024","unstructured":"Yongtao Ge, Wenjia Wang, Yongfan Chen, Hao Chen, and Chunhua Shen. 2024. 3D Human Reconstruction in the Wild with Synthetic Data Using Generative Models. arXiv preprint arXiv:2403.11111 (2024)."},{"key":"e_1_3_2_1_10_1","volume-title":"Learning 3D Object Shape and Layout without 3D Supervision. CVPR","author":"Gkioxari Georgia","year":"2022","unstructured":"Georgia Gkioxari, Nikhila Ravi, and Justin Johnson. 2022. Learning 3D Object Shape and Layout without 3D Supervision. CVPR (2022), 1685--1694."},{"key":"e_1_3_2_1_11_1","unstructured":"Sookwan Han and Hanbyul Joo. 2023. Learning Canonicalized 3D Human-Object Spatial Relations from Unbounded Synthesized Images. In ICCV."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Yana Hasson Gul Varol Dimitrios Tzionas Igor Kalevatykh Michael J. Black Ivan Laptev and Cordelia Schmid. 2019. Learning Joint Reconstruction of Hands and Manipulated Objects. In CVPR.","DOI":"10.1109\/CVPR.2019.01208"},{"key":"e_1_3_2_1_13_1","unstructured":"Chaofan Huo Ye Shi Yuexin Ma Lan Xu Jingyi Yu and Jingya Wang. 2023. StackFLOW: Monocular Human-Object Reconstruction by Stacked Normalizing Flow with Offset. In IJCAI."},{"key":"e_1_3_2_1_14_1","volume-title":"2021 International Conference on 3D Vision (3DV)","author":"Joo Hanbyul","year":"2020","unstructured":"Hanbyul Joo, Natalia Neverova, and Andrea Vedaldi. 2020. Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimation. 2021 International Conference on 3D Vision (3DV) (2020), 42--52."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Angjoo Kanazawa Michael J. Black David W. Jacobs and Jitendra Malik. 2018. End-to-end Recovery of Human Shape and Pose. In CVPR.","DOI":"10.1109\/CVPR.2018.00744"},{"key":"e_1_3_2_1_16_1","volume-title":"NeurIPS","volume":"31","author":"Kingma Durk P","year":"2018","unstructured":"Durk P Kingma and Prafulla Dhariwal. 2018. Glow: Generative Flow with Invertible 1x1 Convolutions. In NeurIPS, Vol. 31."},{"key":"e_1_3_2_1_17_1","volume-title":"Piotr Dollar, and Ross Girshick","author":"Kirillov Alexander","year":"2023","unstructured":"Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C. Berg, Wan-Yen Lo, Piotr Dollar, and Ross Girshick. 2023. Segment Anything. In ICCV. 4015--4026."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Nikos Kolotouros Georgios Pavlakos Dinesh Jayaraman and Kostas Daniilidis. 2021. Probabilistic Modeling for Human Mesh Recovery. In ICCV.","DOI":"10.1109\/ICCV48922.2021.01140"},{"key":"e_1_3_2_1_19_1","volume-title":"CDPN: Coordinates-Based Disentangled Pose Network for Real-Time RGB-Based 6-DoF Object Pose Estimation. In ICCV.","author":"Li Zhigang","year":"2019","unstructured":"Zhigang Li, Gu Wang, and Xiangyang Ji. 2019. CDPN: Coordinates-Based Disentangled Pose Network for Real-Time RGB-Based 6-DoF Object Pose Estimation. In ICCV."},{"key":"e_1_3_2_1_20_1","volume-title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset. NeurIPS","author":"Lin Jing","year":"2023","unstructured":"Jing Lin, Ailing Zeng, Shunlin Lu, Yuanhao Cai, Ruimao Zhang, Haoqian Wang, and Lei Zhang. 2023. Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset. NeurIPS (2023)."},{"key":"e_1_3_2_1_21_1","volume-title":"One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer. CVPR","author":"Lin Jing","year":"2023","unstructured":"Jing Lin, Ailing Zeng, Haoqian Wang, Lei Zhang, and Yu Li. 2023. One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer. CVPR (2023)."},{"key":"e_1_3_2_1_22_1","volume-title":"Learning 3D Scene Priors with 2D Supervision. CVPR","author":"Nie Yinyu","year":"2022","unstructured":"Yinyu Nie, Angela Dai, Xiaoguang Han, and Matthias Nie\u00dfner. 2022. Learning 3D Scene Priors with 2D Supervision. CVPR (2022), 792--802."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Junyi Pan Xiaoguang Han Weikai Chen Jiapeng Tang and Kui Jia. 2019. Deep Mesh Reconstruction From Single RGB Images via Topology Modification Networks. In ICCV.","DOI":"10.1109\/ICCV.2019.01006"},{"key":"e_1_3_2_1_24_1","volume-title":"Learning Hand-Held Object Reconstruction from In-The-Wild Videos. ArXiv","author":"Prakash Aditya","year":"2023","unstructured":"Aditya Prakash, Matthew Chang, Matthew Jin, and Saurabh Gupta. 2023. Learning Hand-Held Object Reconstruction from In-The-Wild Videos. ArXiv, Vol. abs\/2305.03036 (2023)."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the 32nd International Conference on International Conference on Machine Learning -","volume":"37","author":"Rezende Danilo Jimenez","year":"2015","unstructured":"Danilo Jimenez Rezende and Shakir Mohamed. 2015. Variational inference with normalizing flows. In Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37 (ICML'15). 1530--1538."},{"key":"e_1_3_2_1_26_1","volume-title":"Reconstructing Action-Conditioned Human-Object Interactions Using Commonsense Knowledge Priors. 2022 International Conference on 3D Vision (3DV)","author":"Wang Xi","year":"2022","unstructured":"Xi Wang, Gengyan Li, Yen-Ling Kuo, Muhammed Kocabas, Emre Aksan, and Otmar Hilliges. 2022. Reconstructing Action-Conditioned Human-Object Interactions Using Commonsense Knowledge Priors. 2022 International Conference on 3D Vision (3DV) (2022), 353--362."},{"key":"e_1_3_2_1_27_1","volume-title":"Jan Eric Lenssen, and Gerard Pons-Moll.","author":"Xie Xianghui","year":"2024","unstructured":"Xianghui Xie, Bharat Lal Bhatnagar, Jan Eric Lenssen, and Gerard Pons-Moll. 2024. Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generation. In CVPR."},{"key":"e_1_3_2_1_28_1","volume-title":"Bharat Lal Bhatnagar, and Gerard Pons-Moll","author":"Xie Xianghui","year":"2022","unstructured":"Xianghui Xie, Bharat Lal Bhatnagar, and Gerard Pons-Moll. 2022. CHORE: Contact, Human and Object REconstruction from a single RGB image. In ECCV. 125--145."},{"key":"e_1_3_2_1_29_1","volume-title":"Bharat Lal Bhatnagar, and Gerard Pons-Moll","author":"Xie Xianghui","year":"2023","unstructured":"Xianghui Xie, Bharat Lal Bhatnagar, and Gerard Pons-Moll. 2023. Visibility Aware Human-Object Interaction Tracking from Single RGB Camera. In CVPR."},{"key":"e_1_3_2_1_30_1","unstructured":"Yufei Xu Jing Zhang Qiming Zhang and Dacheng Tao. 2022. ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation. In NeurIPS."},{"key":"e_1_3_2_1_31_1","volume-title":"Towards Alleviating the Modeling Ambiguity of Unsupervised Monocular 3D Human Pose Estimation. ICCV","author":"Yu Zhenbo","year":"2021","unstructured":"Zhenbo Yu, Bingbing Ni, Jingwei Xu, Junjie Wang, Chenglong Zhao, and Wenjun Zhang. 2021. Towards Alleviating the Modeling Ambiguity of Unsupervised Monocular 3D Human Pose Estimation. ICCV (2021), 8631--8631."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Jason Y. Zhang Sam Pepose Hanbyul Joo Deva Ramanan Jitendra Malik and Angjoo Kanazawa. 2020. Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild. In ECCV. 34--51.","DOI":"10.1007\/978-3-030-58610-2_3"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681452","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681452","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:47Z","timestamp":1750294667000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681452"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":32,"alternative-id":["10.1145\/3664647.3681452","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681452","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}