{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:03:21Z","timestamp":1750309401366,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":89,"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":"Guangdong Basic and Applied Basic Research Foundation","award":["2024B1515020082, 2023A1515010007"],"award-info":[{"award-number":["2024B1515020082, 2023A1515010007"]}]},{"name":"the Guangdong Provincial Key Laboratory of Human Digital Twin","award":["2022B1212010004"],"award-info":[{"award-number":["2022B1212010004"]}]},{"name":"the 2024 Tencent AI Lab Rhino-Bird Focused Research Program"},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076101"],"award-info":[{"award-number":["62076101"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the TCL Young Scholars Program"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681065","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"768-777","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning Context with Priors for 3D Interacting Hand-Object Pose Estimation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1085-8700","authenticated-orcid":false,"given":"Zengsheng","family":"Kuang","sequence":"first","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7232-3181","authenticated-orcid":false,"given":"Changxing","family":"Ding","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6426-9379","authenticated-orcid":false,"given":"Huan","family":"Yao","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Zhe Cao Ilija Radosavovic Angjoo Kanazawa and Jitendra Malik. 2021. Reconstructing hand-object interactions in the wild. In CVPR.","DOI":"10.1109\/ICCV48922.2021.01219"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Nicolas Carion Francisco Massa Gabriel Synnaeve Nicolas Usunier Alexander Kirillov and Sergey Zagoruyko. 2020. End-to-end object detection with transformers. In ECCV.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"e_1_3_2_1_3_1","volume-title":"Umar Iqbal, Stan Birchfield, et al.","author":"Chao Yu-Wei","year":"2021","unstructured":"Yu-Wei Chao, Wei Yang, Yu Xiang, Pavlo Molchanov, Ankur Handa, Jonathan Tremblay, Yashraj S Narang, Karl Van Wyk, Umar Iqbal, Stan Birchfield, et al. 2021. DexYCB: A benchmark for capturing hand grasping of objects. In CVPR."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Xingyu Chen Yufeng Liu Yajiao Dong Xiong Zhang Chongyang Ma Yanmin Xiong Yuan Zhang and Xiaoyan Guo. 2022. MobRecon: Mobile-friendly hand mesh reconstruction from monocular image. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01989"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Xingyu Chen Yufeng Liu Chongyang Ma Jianlong Chang Huayan Wang Tian Chen Xiaoyan Guo Pengfei Wan and Wen Zheng. 2021. Camera-space hand mesh recovery via semantic aggregation and adaptive 2D-1D registration. In CVPR.","DOI":"10.1109\/CVPR46437.2021.01307"},{"key":"e_1_3_2_1_6_1","volume-title":"Joint hand-object 3D reconstruction from a single image with cross-branch feature fusion. TIP","author":"Chen Yujin","year":"2021","unstructured":"Yujin Chen, Zhigang Tu, Di Kang, Ruizhi Chen, Linchao Bao, Zhengyou Zhang, and Junsong Yuan. 2021. Joint hand-object 3D reconstruction from a single image with cross-branch feature fusion. TIP (2021)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Zerui Chen Shizhe Chen Cordelia Schmid and Ivan Laptev. 2023. gSDF: Geometry-driven signed distance functions for 3D hand-object reconstruction. In CVPR.","DOI":"10.1109\/CVPR52729.2023.01239"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Zerui Chen Yana Hasson Cordelia Schmid and Ivan Laptev. 2022. AlignSDF: Pose-aligned signed distance fields for hand-object Reconstruction. In ECCV.","DOI":"10.1007\/978-3-031-19769-7_14"},{"key":"e_1_3_2_1_9_1","unstructured":"Junhyeong Cho Kim Youwang and Tae-Hyun Oh. 2022. Cross-attention of disentangled modalities for 3D human mesh recovery with transformers. In ECCV."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Hongsuk Choi Gyeongsik Moon and Kyoung Mu Lee. 2020. Pose2Mesh: Graph convolutional network for 3D human pose and mesh recovery from a 2D human pose. In ECCV.","DOI":"10.1007\/978-3-030-58571-6_45"},{"key":"e_1_3_2_1_11_1","volume":"202","author":"Doosti Bardia","unstructured":"Bardia Doosti, Shujon Naha, Majid Mirbagheri, and David J Crandall. 2020. Hope-net: A graph-based model for hand-object pose estimation. In CVPR.","journal-title":"David J Crandall."},{"key":"e_1_3_2_1_12_1","volume-title":"Tore: Token reduction for efficient human mesh recovery with transformer. In ICCV.","author":"Dou Zhiyang","year":"2023","unstructured":"Zhiyang Dou, Qingxuan Wu, Cheng Lin, Zeyu Cao, Qiangqiang Wu, Weilin Wan, Taku Komura, and Wenping Wang. 2023. Tore: Token reduction for efficient human mesh recovery with transformer. In ICCV."},{"key":"e_1_3_2_1_13_1","unstructured":"Zicong Fan Adrian Spurr Muhammed Kocabas Siyu Tang Michael J Black and Otmar Hilliges. 2021. Learning to disambiguate strongly interacting hands via probabilistic per-pixel part segmentation. In 3DV."},{"key":"e_1_3_2_1_14_1","volume-title":"Juan Carlos Niebles, and Kris M. Kitani","author":"Fu Qichen","year":"2023","unstructured":"Qichen Fu, Xingyu Liu, Ran Xu, Juan Carlos Niebles, and Kris M. Kitani. 2023. Deformer: Dynamic fusion transformer for robust hand pose estimation. In ICCV."},{"key":"e_1_3_2_1_15_1","unstructured":"Daiheng Gao Xindi Zhang Xingyu Chen Andong Tan Bang Zhang Pan Pan and Ping Tan. 2022. CycleHand: Increasing 3D pose estimation ability on in-the-wild monocular image through cyclic flow. In ACM MM."},{"key":"e_1_3_2_1_16_1","unstructured":"Liuhao Ge Zhou Ren Yuncheng Li Zehao Xue Yingying Wang Jianfei Cai and Junsong Yuan. 2019. 3D hand shape and pose estimation from a single rgb image. In CVPR."},{"key":"e_1_3_2_1_17_1","volume-title":"Contactopt: Optimizing contact to improve grasps. In CVPR.","author":"Grady Patrick","year":"2021","unstructured":"Patrick Grady, Chengcheng Tang, Christopher D Twigg, Minh Vo, Samarth Brahmbhatt, and Charles C Kemp. 2021. Contactopt: Optimizing contact to improve grasps. In CVPR."},{"key":"e_1_3_2_1_18_1","unstructured":"Shaoxiang Guo Qing Cai Lin Qi and Junyu Dong. 2023. CLIP-Hand3D: Exploiting 3D hand pose estimation via context-aware prompting. In ACM MM."},{"key":"e_1_3_2_1_19_1","volume-title":"Honnotate: A method for 3D annotation of hand and object poses. In CVPR.","author":"Hampali Shreyas","year":"2020","unstructured":"Shreyas Hampali, Mahdi Rad, Markus Oberweger, and Vincent Lepetit. 2020. Honnotate: A method for 3D annotation of hand and object poses. In CVPR."},{"key":"e_1_3_2_1_20_1","volume-title":"Mahdi Rad, and Vincent Lepetit.","author":"Hampali Shreyas","year":"2022","unstructured":"Shreyas Hampali, Sayan Deb Sarkar, Mahdi Rad, and Vincent Lepetit. 2022. Keypoint transformer: Solving joint identification in challenging hands and object interactions for accurate 3D pose estimation. In CVPR."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Shangchen Han Beibei Liu Randi Cabezas Christopher D Twigg Peizhao Zhang Jeff Petkau Tsz-Ho Yu Chun-Jung Tai Muzaffer Akbay Zheng Wang et al. 2020. MEgATrack: Monochrome egocentric articulated hand-tracking for virtual reality. TOG (2020).","DOI":"10.1145\/3386569.3392452"},{"key":"e_1_3_2_1_22_1","volume-title":"Wei Yang, Jacky Liang, Yu-Wei Chao, Qian Wan, Stan Birchfield, Nathan Ratliff, and Dieter Fox.","author":"Handa Ankur","year":"2020","unstructured":"Ankur Handa, Karl Van Wyk, Wei Yang, Jacky Liang, Yu-Wei Chao, Qian Wan, Stan Birchfield, Nathan Ratliff, and Dieter Fox. 2020. Dexpilot: Vision-based teleoperation of dexterous robotic hand-arm system. In ICRA."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Yana Hasson Bugra Tekin Federica Bogo Ivan Laptev Marc Pollefeys and Cordelia Schmid. 2020. Leveraging photometric consistency over time for sparsely supervised hand-object reconstruction. In CVPR.","DOI":"10.1109\/CVPR42600.2020.00065"},{"key":"e_1_3_2_1_24_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_25_1","unstructured":"Kaiming He Georgia Gkioxari Piotr Doll\u00e1r and Ross Girshick. 2017. Mask r-cnn. In ICCV."},{"key":"e_1_3_2_1_26_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Stefan Hinterstoisser Vincent Lepetit Slobodan Ilic Stefan Holzer Gary Bradski Kurt Konolige and Nassir Navab. 2013. Model based training detection and pose estimation of texture-less 3D objects in heavily cluttered scenes. In ACCV.","DOI":"10.1007\/978-3-642-37331-2_42"},{"key":"e_1_3_2_1_28_1","volume-title":"ECCV Workshops.","author":"Hodavn Tom\u00e1vs","year":"2016","unstructured":"Tom\u00e1vs Hodavn, Jivr\u00ed Matas, and vStvep\u00e1n Obdrvz\u00e1lek. 2016. On evaluation of 6D object pose estimation. In ECCV Workshops."},{"key":"e_1_3_2_1_29_1","unstructured":"Junxing Hu Hongwen Zhang Zerui Chen Mengcheng Li Yunlong Wang Yebin Liu and Zhenan Sun. 2024. Learning explicit contact for implicit reconstruction of hand-held objects from monocular images. In AAAI."},{"key":"e_1_3_2_1_30_1","unstructured":"Yinlin Hu Joachim Hugonot Pascal Fua and Mathieu Salzmann. 2019. Segmentation-driven 6d object pose estimation. In CVPR."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Zihao Huang Min Shi Chengxin Liu Ke Xian and Zhiguo Cao. 2023. SimHMR: A simple query-based framework for parameterized human mesh reconstruction. In ACM MM.","DOI":"10.1145\/3581783.3611814"},{"key":"e_1_3_2_1_32_1","volume":"201","author":"Javier Romero Dimitrios Tzionas","unstructured":"Dimitrios Tzionas Javier Romero and Michael J Black. 2017. Embodied hands: Modeling and capturing hands and bodies together. TOG (2017).","journal-title":"Michael J Black."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Shijian Jiang Qi Ye Rengan Xie Yuchi Huo Xiang Li Yang Zhou and Jiming Chen. 2024. In-hand 3D object reconstruction from a monocular RGB video. In AAAI.","DOI":"10.1609\/aaai.v38i3.28029"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Korrawe Karunratanakul Jinlong Yang Yan Zhang Michael J Black Krikamol Muandet and Siyu Tang. 2020. Grasping field: Learning implicit representations for human grasps. In 3DV.","DOI":"10.1109\/3DV50981.2020.00043"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"Zhiying Leng Shun-Cheng Wu Mahdi Saleh Antonio Montanaro Hao Yu Yin Wang Nassir Navab Xiaohui Liang and Federico Tombari. 2023. Dynamic hyperbolic attention network for fine hand-object reconstruction. In ICCV.","DOI":"10.1109\/ICCV51070.2023.01368"},{"key":"e_1_3_2_1_36_1","volume-title":"EPnP: An accurate o(n) solution to the pnp Problem. IJCV","author":"Lepetit Vincent","year":"2009","unstructured":"Vincent Lepetit, Francesc Moreno-Noguer, and Pascal Fua. 2009. EPnP: An accurate o(n) solution to the pnp Problem. IJCV (2009)."},{"key":"e_1_3_2_1_37_1","unstructured":"Chengshu Li Ruohan Zhang Josiah Wong Cem Gokmen Sanjana Srivastava Roberto Mart\u00edn-Mart\u00edn Chen Wang Gabrael Levine Michael Lingelbach Jiankai Sun et al. 2023. Behavior-1k: A benchmark for embodied ai with 1 000 everyday activities and realistic simulation. In CoRL."},{"key":"e_1_3_2_1_38_1","unstructured":"Haoming Li Xinzhuo Lin Yang Zhou Xiang Li Yuchi Huo Jiming Chen and Qi Ye. 2023. Contact2grasp: 3D grasp synthesis via hand-object contact constraint. In IJCAI."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Ke Li Shijie Wang Xiang Zhang Yifan Xu Weijian Xu and Zhuowen Tu. 2021. Pose recognition with cascade transformers. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00198"},{"key":"e_1_3_2_1_40_1","unstructured":"Kailin Li Lixin Yang Xinyu Zhan Jun Lv Wenqiang Xu Jiefeng Li and Cewu Lu. 2022. ArtiBoost: Boosting articulated 3D hand-object pose estimation via online exploration and synthesis. In CVPR."},{"key":"e_1_3_2_1_41_1","volume-title":"Chord: Category-level hand-held object reconstruction via shape deformation. In ICCV.","author":"Li Kailin","year":"2023","unstructured":"Kailin Li, Lixin Yang, Haoyu Zhen, Zenan Lin, Xinyu Zhan, Licheng Zhong, Jian Xu, Kejian Wu, and Cewu Lu. 2023. Chord: Category-level hand-held object reconstruction via shape deformation. In ICCV."},{"key":"e_1_3_2_1_42_1","unstructured":"Mengcheng Li Liang An Hongwen Zhang Lianpeng Wu Feng Chen Tao Yu and Yebin Liu. 2022. Interacting attention graph for single image two-hand reconstruction. In CVPR."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Kevin Lin Lijuan Wang and Zicheng Liu. 2021. End-to-end human pose and mesh reconstruction with transformers. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"e_1_3_2_1_44_1","unstructured":"Tsung-Yi Lin Piotr Doll\u00e1r Ross Girshick Kaiming He Bharath Hariharan and Serge Belongie. 2017. Feature pyramid networks for object detection. In CVPR."},{"key":"e_1_3_2_1_45_1","unstructured":"Zhifeng Lin Changxing Ding Huan Yao Zengsheng Kuang and Shaoli Huang. 2023. Harmonious feature learning for interactive hand-object pose estimation. In CVPR."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Huan Liu Qiang Chen Zichang Tan Jiang-Jiang Liu Jian Wang Xiangbo Su Xiaolong Li Kun Yao Junyu Han Errui Ding et al. 2023. Group pose: A simple baseline for end-to-end multi-person pose estimation. In ICCV.","DOI":"10.1109\/ICCV51070.2023.01380"},{"key":"e_1_3_2_1_47_1","unstructured":"Shaowei Liu Hanwen Jiang Jiarui Xu Sifei Liu and Xiaolong Wang. 2021. Semi-supervised 3D hand-object poses estimation with interactions in time. In CVPR."},{"key":"e_1_3_2_1_48_1","unstructured":"Xueyi Liu and Li Yi. 2024. GeneOH diffusion: Towards generalizable hand-object interaction denoising via denoising diffusion. In ICLR."},{"key":"e_1_3_2_1_49_1","volume":"201","author":"Loper Matthew","unstructured":"Matthew Loper, Naureen Mahmood, Javier Romero, Gerard Pons-Moll, and Michael J Black. 2015. SMPL: A skinned multi-person linear model. TOG (2015).","journal-title":"Michael J Black."},{"key":"e_1_3_2_1_50_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. In ICLR."},{"key":"e_1_3_2_1_51_1","volume-title":"Poseur: Direct human pose regression with transformers. In ECCV.","author":"Mao Weian","year":"2022","unstructured":"Weian Mao, Yongtao Ge, Chunhua Shen, Zhi Tian, Xinlong Wang, Zhibin Wang, and Anton van den Hengel. 2022. Poseur: Direct human pose regression with transformers. In ECCV."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"crossref","unstructured":"Depu Meng Xiaokang Chen Zejia Fan Gang Zeng Houqiang Li Yuhui Yuan Lei Sun and Jingdong Wang. 2021. Conditional detr for fast training convergence. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"e_1_3_2_1_53_1","unstructured":"Gyeongsik Moon and Kyoung Mu Lee. 2020. I2l-meshnet: Image-to-lixel prediction network for accurate 3d human pose and mesh estimation from a single rgb image. In ECCV."},{"key":"e_1_3_2_1_54_1","unstructured":"Gyeongsik Moon Shoou-I Yu He Wen Takaaki Shiratori and Kyoung Mu Lee. 2020. Interhand2. 6m: A dataset and baseline for 3D interacting hand pose estimation from a single rgb image. In ECCV."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"crossref","unstructured":"JoonKyu Park Yeonguk Oh Gyeongsik Moon Hongsuk Choi and Kyoung Mu Lee. 2022. HandOccNet: Occlusion-robust 3D hand mesh estimation network. In CVPR.","DOI":"10.1109\/CVPR52688.2022.00155"},{"key":"e_1_3_2_1_56_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. In NIPS.","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. In NIPS."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"crossref","unstructured":"Gr\u00e9gory Rogez James S Supancic and Deva Ramanan. 2015. Understanding everyday hands in action from rgb-d images. In ICCV.","DOI":"10.1109\/ICCV.2015.443"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"crossref","unstructured":"Adrian Spurr Umar Iqbal Pavlo Molchanov Otmar Hilliges and Jan Kautz. 2020. Weakly supervised 3d hand pose estimation via biomechanical constraints. In ECCV.","DOI":"10.1007\/978-3-030-58520-4_13"},{"key":"e_1_3_2_1_59_1","volume-title":"Neural state machine for character-scene interactions. TOG","author":"Starke Sebastian","year":"2019","unstructured":"Sebastian Starke, He Zhang, Taku Komura, and Jun Saito. 2019. Neural state machine for character-scene interactions. TOG (2019)."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"crossref","unstructured":"Ke Sun Bin Xiao Dong Liu and Jingdong Wang. 2019. Deep high-resolution representation learning for human pose estimation. In CVPR.","DOI":"10.1109\/CVPR.2019.00584"},{"key":"e_1_3_2_1_61_1","volume-title":"EPMF: Efficient perception-Aware multi-sensor fusion for 3D semantic segmentation. TPAMI","author":"Tan Mingkui","year":"2024","unstructured":"Mingkui Tan, Zhuangwei Zhuang, Sitao Chen, Rong Li, Kui Jia, Qicheng Wang, and Yuanqing Li. 2024. EPMF: Efficient perception-Aware multi-sensor fusion for 3D semantic segmentation. TPAMI (2024)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"crossref","unstructured":"Xiao Tang Tianyu Wang and Chi-Wing Fu. 2021. Towards accurate alignment in real-time 3D hand-mesh reconstruction. In ICCV.","DOI":"10.1109\/ICCV48922.2021.01149"},{"key":"e_1_3_2_1_63_1","volume-title":"Ho: Unified egocentric recognition of 3D hand-object poses and interactions. In CVPR.","author":"Tekin Bugra","year":"2019","unstructured":"Bugra Tekin, Federica Bogo, and Marc Pollefeys. 2019. Ho: Unified egocentric recognition of 3D hand-object poses and interactions. In CVPR."},{"key":"e_1_3_2_1_64_1","volume-title":"Ales Leonardis, and Hyung Jin Chang.","author":"Elden Tse Tze Ho","year":"2022","unstructured":"Tze Ho Elden Tse, Kwang In Kim, Ales Leonardis, and Hyung Jin Chang. 2022. Collaborative learning for hand and object reconstruction with attention-guided graph convolution. In CVPR."},{"key":"e_1_3_2_1_65_1","volume-title":"Ales Leonardis, Feng Zheng, and Hyung Jin Chang.","author":"Elden Tse Tze Ho","year":"2022","unstructured":"Tze Ho Elden Tse, Zhongqun Zhang, Kwang In Kim, Ales Leonardis, Feng Zheng, and Hyung Jin Chang. 2022. S^2 Contact: Graph-based network for 3D hand-object contact estimation with semi-supervised learning. In ECCV."},{"key":"e_1_3_2_1_66_1","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan N Gomez \u0141ukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. In NIPS."},{"key":"e_1_3_2_1_67_1","volume-title":"Gdr-net: Geometry-guided direct regression network for monocular 6d object pose estimation. In CVPR.","author":"Wang Gu","year":"2021","unstructured":"Gu Wang, Fabian Manhardt, Federico Tombari, and Xiangyang Ji. 2021. Gdr-net: Geometry-guided direct regression network for monocular 6d object pose estimation. In CVPR."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"crossref","unstructured":"Haonan Wang Jie Liu Jie Tang and Gangshan Wu. 2023. Lightweight super-resolution head for human pose estimation. In ACM MM.","DOI":"10.1145\/3581783.3612236"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417852"},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"crossref","unstructured":"Rui Wang Sophokles Ktistakis Siwei Zhang Mirko Meboldt and Quentin Lohmeyer. 2023. POV-Surgery: A dataset for egocentric hand and tool pose estimation during surgical activities. In MICCAI.","DOI":"10.1007\/978-3-031-43996-4_42"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"crossref","unstructured":"Rong Wang Wei Mao and Hongdong Li. 2023. Interacting hand-object pose estimation via dense mutual attention. In WACV.","DOI":"10.1109\/WACV56688.2023.00569"},{"key":"e_1_3_2_1_72_1","volume-title":"Pheng Ann Heng, and Chi-Wing Fu","author":"Wang Yinqiao","year":"2024","unstructured":"Yinqiao Wang, Hao Xu, Pheng Ann Heng, and Chi-Wing Fu. 2024. SiMA-hand: Boosting 3D hand-mesh reconstruction by single-to-multi-view adaptation. In AAAI."},{"key":"e_1_3_2_1_73_1","volume-title":"Posecnn: A convolutional neural network for 6D object pose estimation in cluttered scenes. In RSS.","author":"Xiang Yu","year":"2018","unstructured":"Yu Xiang, Tanner Schmidt, Venkatraman Narayanan, and Dieter Fox. 2018. Posecnn: A convolutional neural network for 6D object pose estimation in cluttered scenes. In RSS."},{"key":"e_1_3_2_1_74_1","unstructured":"Zeqi Xiao Tai Wang Jingbo Wang Jinkun Cao Wenwei Zhang Bo Dai Dahua Lin and Jiangmiao Pang. 2024. Unified human-scene interaction via prompted chain-of-contacts. In ICLR."},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1920\/re.ifs.2023.0264"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"crossref","unstructured":"Hao Xu Tianyu Wang Xiao Tang and Chi-Wing Fu. 2023. H2onet: Hand-occlusion-and-orientation-aware network for real-time 3D hand mesh reconstruction. In CVPR.","DOI":"10.1109\/CVPR52729.2023.01635"},{"key":"e_1_3_2_1_77_1","unstructured":"Jie Yang Ailing Zeng Shilong Liu Feng Li Ruimao Zhang and Lei Zhang. 2023. Explicit box detection unifies end-to-end multi-person pose estimation. In ICLR."},{"key":"e_1_3_2_1_78_1","volume-title":"Cpf: Learning a contact potential field to model the hand-object interaction. In CVPR.","author":"Yang Lixin","year":"2021","unstructured":"Lixin Yang, Xinyu Zhan, Kailin Li, Wenqiang Xu, Jiefeng Li, and Cewu Lu. 2021. Cpf: Learning a contact potential field to model the hand-object interaction. In CVPR."},{"key":"e_1_3_2_1_79_1","unstructured":"Yufei Ye Abhinav Gupta and Shubham Tulsiani. 2022. What's in your hands? 3D reconstruction of generic objects in hands. In CVPR."},{"key":"e_1_3_2_1_80_1","unstructured":"Yufei Ye Poorvi Hebbar Abhinav Gupta and Shubham Tulsiani. 2023. Diffusion-guided reconstruction of everyday hand-object interaction clips. In ICCV."},{"key":"e_1_3_2_1_81_1","unstructured":"Zijie Ye Jia Jia and Junliang Xing. 2023. Semantics2Hands: Transferring hand motion semantics between avatars. In ACM MM."},{"key":"e_1_3_2_1_82_1","doi-asserted-by":"crossref","unstructured":"Yusuke Yoshiyasu. 2023. Deformable mesh transformer for 3D human mesh recovery. In CVPR.","DOI":"10.1109\/CVPR52729.2023.01631"},{"key":"e_1_3_2_1_83_1","volume-title":"ACR: Attention collaboration-based regressor for arbitrary two-hand reconstruction. In CVPR.","author":"Yu Zhengdi","year":"2023","unstructured":"Zhengdi Yu, Shaoli Huang, Chen Fang, Toby P Breckon, and Jue Wang. 2023. ACR: Attention collaboration-based regressor for arbitrary two-hand reconstruction. In CVPR."},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"crossref","unstructured":"Baowen Zhang Yangang Wang Xiaoming Deng Yinda Zhang Ping Tan Cuixia Ma and Hongan Wang. 2021. Interacting two-hand 3D pose and shape reconstruction from single color image. In ICCV.","DOI":"10.1109\/ICCV48922.2021.01116"},{"key":"e_1_3_2_1_85_1","unstructured":"Chenyangguang Zhang Yan Di Ruida Zhang Guangyao Zhai Fabian Manhardt Federico Tombari and Xiangyang Ji. 2024. DDF-HO: Hand-held object reconstruction via conditional directed distance field. In NIPS."},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"crossref","unstructured":"Lei Zhao Le Han Min Yao and Nenggan Zheng. 2023. Implicit decouple network for efficient pose estimation. In ACM MM.","DOI":"10.1145\/3581783.3611790"},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"crossref","unstructured":"Xiaozheng Zheng Chao Wen Zhou Xue Pengfei Ren and Jingyu Wang. 2023. HaMuCo: Hand pose estimation via multiview collaborative self-supervised learning. In ICCV.","DOI":"10.1109\/ICCV51070.2023.01898"},{"key":"e_1_3_2_1_88_1","unstructured":"Tianqiang Zhu Rina Wu Xiangbo Lin and Yi Sun. 2021. Toward human-like grasp: Dexterous grasping via semantic representation of object-hand. In ICCV."},{"key":"e_1_3_2_1_89_1","unstructured":"Xizhou Zhu Weijie Su Lewei Lu Bin Li Xiaogang Wang and Jifeng Dai. 2021. Deformable detr: Deformable transformers for end-to-end object detection. In ICLR."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681065","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681065","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:52Z","timestamp":1750294672000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681065"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":89,"alternative-id":["10.1145\/3664647.3681065","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681065","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"}}]}}