{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:15:57Z","timestamp":1778080557828,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":45,"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:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Natural Science Foundation of China","award":["No. 62203476"],"award-info":[{"award-number":["No. 62203476"]}]},{"name":"Shenzhen Innovation in Science and Technology Foundation for The Excellent Youth Scholars","award":["No. RCYX20231211090248064"],"award-info":[{"award-number":["No. RCYX20231211090248064"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680597","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"273-281","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["ClickDiff: Click to Induce Semantic Contact Map for Controllable Grasp Generation with Diffusion Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1869-7043","authenticated-orcid":false,"given":"Peiming","family":"Li","sequence":"first","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5169-1464","authenticated-orcid":false,"given":"Ziyi","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4036-9315","authenticated-orcid":false,"given":"Mengyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7498-6541","authenticated-orcid":false,"given":"Hong","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3957-7061","authenticated-orcid":false,"given":"Chen","family":"Chen","sequence":"additional","affiliation":[{"name":"Center for Research in Computer Vision, University of Central Florida, Orlando, FL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00891"},{"key":"e_1_3_2_2_2_1","volume-title":"ContactPose: A Dataset of Grasps with Object Contact and Hand Pose. ArXiv","author":"Brahmbhatt Samarth","year":"2020","unstructured":"Samarth Brahmbhatt, Chengcheng Tang, Christopher D. Twigg, Charles C. Kemp, and James Hays. 2020. ContactPose: A Dataset of Grasps with Object Contact and Hand Pose. ArXiv, Vol. abs\/2007.09545 (2020)."},{"key":"e_1_3_2_2_3_1","volume-title":"SuctionNet-1Billion: A Large-Scale Benchmark for Suction Grasping","author":"Cao Hanwen","year":"2021","unstructured":"Hanwen Cao, Hao-Shu Fang, Wenhai Liu, and Cewu Lu. 2021. SuctionNet-1Billion: A Large-Scale Benchmark for Suction Grasping. IEEE Robotics and Automation Letters (2021), 8718--8725."},{"key":"e_1_3_2_2_4_1","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 77--85","author":"Charles R. Qi","unstructured":"R. Qi Charles, Hao Su, Mo Kaichun, and Leonidas J. Guibas. 2017. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 77--85."},{"key":"e_1_3_2_2_5_1","volume-title":"AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstruction. ArXiv","author":"Chen Zerui","year":"2022","unstructured":"Zerui Chen, Yana Hasson, Cordelia Schmid, and Ivan Laptev. 2022. AlignSDF: Pose-Aligned Signed Distance Fields for Hand-Object Reconstruction. ArXiv (2022)."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00462"},{"key":"e_1_3_2_2_7_1","volume-title":"HOPE-Net: A Graph-Based Model for Hand-Object Pose Estimation. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Doosti Bardia","year":"2020","unstructured":"Bardia Doosti, Shujon Naha, Majid Mirbagheri, and David J. Crandall. 2020. HOPE-Net: A Graph-Based Model for Hand-Object Pose Estimation. 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020), 6607--6616."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00011"},{"key":"e_1_3_2_2_9_1","volume-title":"ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation. In 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 12943--12954","author":"Fan Zicong","year":"2023","unstructured":"Zicong Fan, Omid Taheri, Dimitrios Tzionas, Muhammed Kocabas, Manuel Kaufmann, Michael J. Black, and Otmar Hilliges. 2023. ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation. In 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 12943--12954."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00152"},{"key":"e_1_3_2_2_11_1","volume-title":"Learning Joint Reconstruction of Hands and Manipulated Objects. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 11799--11808","author":"Hasson Yana","year":"2019","unstructured":"Yana Hasson, G\u00fcl Varol, Dimitrios Tzionas, Igor Kalevatykh, Michael J. Black, Ivan Laptev, and Cordelia Schmid. 2019. Learning Joint Reconstruction of Hands and Manipulated Objects. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 11799--11808."},{"key":"e_1_3_2_2_12_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840--6851."},{"key":"e_1_3_2_2_13_1","volume-title":"Efficient Physics-Based Implementation for Realistic Hand-Object Interaction in Virtual Reality. In 2018 IEEE Conference on Virtual Reality and 3D User Interfaces (VR). 175--182","author":"H\u00f6ll Markus","year":"2018","unstructured":"Markus H\u00f6ll, Markus Oberweger, Clemens Arth, and Vincent Lepetit. 2018. Efficient Physics-Based Implementation for Realistic Hand-Object Interaction in Virtual Reality. In 2018 IEEE Conference on Virtual Reality and 3D User Interfaces (VR). 175--182."},{"key":"e_1_3_2_2_14_1","volume-title":"Planning with Diffusion for Flexible Behavior Synthesis. In International Conference on Machine Learning.","author":"Janner Michael","year":"2022","unstructured":"Michael Janner, Yilun Du, Joshua B. Tenenbaum, and Sergey Levine. 2022. Planning with Diffusion for Flexible Behavior Synthesis. In International Conference on Machine Learning."},{"key":"e_1_3_2_2_15_1","volume-title":"Hand-Object Contact Consistency Reasoning for Human Grasps Generation. In 2021 IEEE\/CVF International Conference on Computer Vision (ICCV). 11087--11096","author":"Jiang Hanwen","year":"2021","unstructured":"Hanwen Jiang, Shaowei Liu, Jiashun Wang, and Xiaolong Wang. 2021. Hand-Object Contact Consistency Reasoning for Human Grasps Generation. In 2021 IEEE\/CVF International Conference on Computer Vision (ICCV). 11087--11096."},{"key":"e_1_3_2_2_16_1","volume-title":"Guided Motion Diffusion for Controllable Human Motion Synthesis. 2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Karunratanakul Korrawe","year":"2023","unstructured":"Korrawe Karunratanakul, Konpat Preechakul, Supasorn Suwajanakorn, and Siyu Tang. 2023. Guided Motion Diffusion for Controllable Human Motion Synthesis. 2023 IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00012"},{"key":"e_1_3_2_2_18_1","volume-title":"Grasping Field: Learning Implicit Representations for Human Grasps. In 2020 International Conference on 3D Vision (3DV","author":"Karunratanakul Korrawe","year":"2020","unstructured":"Korrawe Karunratanakul, Jinlong Yang, Yan Zhang, Michael Black, Krikamol Muandet, and Siyu Tang. 2020. Grasping Field: Learning Implicit Representations for Human Grasps. In 2020 International Conference on 3D Vision (3DV 2020). 333--344."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25996"},{"key":"e_1_3_2_2_20_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2014","unstructured":"Diederik P. Kingma and Jimmy Ba. 2014. Adam: A Method for Stochastic Optimization. CoRR, Vol. abs\/1412.6980 (2014)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01644"},{"key":"e_1_3_2_2_22_1","volume-title":"Chen Change Loy, and Bo Dai","author":"Li Quanzhou","year":"2023","unstructured":"Quanzhou Li, Jingbo Wang, Chen Change Loy, and Bo Dai. 2023. Task-Oriented Human-Object Interactions Generation with Implicit Neural Representations. ArXiv, Vol. abs\/2303.13129 (2023)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01884"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01445"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_33"},{"key":"e_1_3_2_2_27_1","volume-title":"State-Only Imitation Learning for Dexterous Manipulation. 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Radosavovic Ilija","year":"2020","unstructured":"Ilija Radosavovic, Xiaolong Wang, Lerrel Pinto, and Jitendra Malik. 2020. State-Only Imitation Learning for Dexterous Manipulation. 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (2020), 7865--7871."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01322"},{"key":"e_1_3_2_2_29_1","volume-title":"Black","author":"Romero Javier","year":"2017","unstructured":"Javier Romero, Dimitrios Tzionas, and Michael J. Black. 2017. Embodied hands: modeling and capturing hands and bodies together. ACM Transactions on Graphics (2017)."},{"key":"e_1_3_2_2_30_1","volume-title":"Hand-Object Interaction Detection with Fully Convolutional Networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 1236--1243","author":"Schr\u00f6der Matthias","year":"2017","unstructured":"Matthias Schr\u00f6der and Helge Ritter. 2017. Hand-Object Interaction Detection with Fully Convolutional Networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 1236--1243."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00117"},{"key":"e_1_3_2_2_32_1","volume-title":"2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Taheri Omid","year":"2021","unstructured":"Omid Taheri, Vasileios Choutas, Michael J. Black, and Dimitrios Tzionas. 2021. GOAL: Generating 4D Whole-Body Motion for Hand-Object Grasping. 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021), 13253--13263."},{"key":"e_1_3_2_2_33_1","volume-title":"GRAB: A Dataset of Whole-Body Human Grasping of Objects. In European Conference on Computer Vision.","author":"Taheri Omid","year":"2020","unstructured":"Omid Taheri, Nima Ghorbani, Michael J. Black, and Dimitrios Tzionas. 2020. GRAB: A Dataset of Whole-Body Human Grasping of Objects. In European Conference on Computer Vision."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00464"},{"key":"e_1_3_2_2_35_1","volume-title":"FLEX: Full-Body Grasping Without Full-Body Grasps. In 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 21179--21189","author":"Tendulkar Purva","year":"2023","unstructured":"Purva Tendulkar, D\u00eddac Sur\u00eds, and Carl Vondrick. 2023. FLEX: Full-Body Grasping Without Full-Body Grasps. In 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 21179--21189."},{"key":"e_1_3_2_2_36_1","volume-title":"Human motion diffusion model. arXiv preprint arXiv:2209.14916","author":"Tevet Guy","year":"2022","unstructured":"Guy Tevet, Sigal Raab, Brian Gordon, Yonatan Shafir, Daniel Cohen-Or, and Amit H Bermano. 2022. Human motion diffusion model. arXiv preprint arXiv:2209.14916 (2022)."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICINFA.2010.5512333"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0895-4"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2003.814758"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2020.102802"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01467"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00203"},{"key":"e_1_3_2_2_43_1","volume-title":"Motiondiffuse: Text-driven human motion generation with diffusion model","author":"Zhang Mingyuan","year":"2024","unstructured":"Mingyuan Zhang, Zhongang Cai, Liang Pan, Fangzhou Hong, Xinying Guo, Lei Yang, and Ziwei Liu. 2024. Motiondiffuse: Text-driven human motion generation with diffusion model. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)."},{"key":"e_1_3_2_2_44_1","first-page":"518","article-title":"COUCH","volume":"2022","author":"Zhang Xiaohan","year":"2022","unstructured":"Xiaohan Zhang, Bharat Lal Bhatnagar, Sebastian Starke, Vladimir Guzov, and Gerard Pons-Moll. 2022. COUCH: Towards Controllable Human-Chair Interactions. In Computer Vision - ECCV 2022. 518--535.","journal-title":"Towards Controllable Human-Chair Interactions. In Computer Vision - ECCV"},{"key":"e_1_3_2_2_45_1","volume-title":"Hauser","author":"Zhou Yilun","year":"2017","unstructured":"Yilun Zhou and Kris K. Hauser. 2017. Grasp Planning by Optimizing a Deep Learning Scoring Function."}],"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\/3664647.3680597","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680597","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:56Z","timestamp":1750295876000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680597"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":45,"alternative-id":["10.1145\/3664647.3680597","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680597","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"}}]}}