主要研究领域为计算机视觉、虚拟现实和人机交互。

在计算机视觉方面，着重研究人手/人体的三维姿态估计和外形重建、抓取合成、手势识别、场景重建与理解等。

在虚拟现实和人机交互方面，着重研究手势交互界面、多通道交互、机械手灵巧操作等。

   

081203-计算机应用技术

人机交互技术，计算机视觉

1. 研究生招生信息：

招收博士和硕士研究生，招生专业背景不限(包含并不限于计算机、软件工程、自动化、数学等专业)。希望你热爱科学研究，具有扎实的数学基础和编程能力(Python、C/C++等），以及良好的中英文表达能力和自律能力。

具有ACM-ICPC、NOI等程序设计竞赛、三维计算机视觉、图形学背景者将优先考虑。

2. 博士后招收信息：

2025年招收博士后1名，研究方向及主要研究内容：

人手与物体跟踪与交互合成方向：从事人手跟踪、抓取生成、强化学习的前沿算法和系统研究，具有人体或人手运动控制、机械手操作生成等研究经验者优先，与海内外著名实验室密切合作，完成高水平科研成果。

2004-09--2008-03 中国科学院自动化研究所模式识别国家重点实验室 工学博士学位
2001-09--2004-06 武汉大学 理学硕士学位
1997-09--2001-06 武汉大学 理学学士学位

2010-06-今，中国科学院软件研究所，人机交互北京市重点实验室，计算机应用技术，助理研究员，副研究员，研究员

2012-04-2013-06，新加坡国立大学, 电子与计算机工程系，计算机视觉与计算机图形学，Research Fellow

2008-02-2010-06，中国科学院计算技术研究所，虚拟现实技术实验室，虚拟现实，博士后

2024-08-18-今,中国计算机学会人机交互专业委员会, 委员
2020-10-16-今,中国图象图形学学会三维视觉专业委员会, 委员
2018-05-19-今,北京市人工智能学会, 理事
2013-10-22-今,中国计算机学会计算机视觉专业委员会, 委员

国际期刊：

[1] Jianping Jiang, Jiahe Li, Baowen Zhang, Xiaoming Deng, Boxin Shi, EvHandPose: Event-based 3D hand

 pose estimation with sparse supervision. IEEE Transactions on Pattern Analysis and Machine Intelligence,

 (2024) Video

[2] Xiaoming Deng,  Dexin Zuo,  Yinda Zhang, Zhaopeng Cui, Jian Cheng, Ping Tan, Liang Chang, Marc Pollefeys,

 Sean Fanello, Hongan Wang, Recurrent 3D hand pose estimation using cascaded pose-guided 3D alignments.

 IEEE Transactions on Pattern Analysis and Machine Intelligence, (2023) Video

[3] Fang Liu, Xiaoming Deng, Changqing Zou, Yu-Kun Lai, Keqi Chen, Ran Zuo, Cuixia Ma, Yong-Jin Liu,

Hongan Wang, SceneSketcher-v2: Fine-grained scene-level sketch-based image retrieval using adaptive

GCNs. IEEE Transactions on Image Processing, (2023) Video

[4] Ran Zuo, Xiaoming Deng, Keqi Chen, Zhengming Zhang, Yu-Kun Lai, Fang Liu, Cuixia Ma, Hao Wang,

Yong-Jin Liu, Hongan Wang, Fine-Grained Video Retrieval With Scene Sketches. IEEE Transactions on

Image Processing, (2023)

[5] Ze-Yuan Huang, Qiang He, Kevin T. Maher, Xiaoming Deng, Yu-Kun Lai, Cuixia Ma, Shengfeng Qin,

Yong-Jin Liu, Hongan Wang, SpeechMirror: A Multimodal Visual Analytics System for Personalized Reflection

 of Online Public Speaking Effectiveness. IEEE Transactions on Visualization and Computer Graphics, (2023)

 Video

[6] Xiaoming Deng, Yuying Zhu, Yinda Zhang, Zhaopeng Cui, Ping Tan, Wentian Qu, Cuixia Ma, Hongan Wang,

 Weakly-supervised  learning for single depth based hand shape recovery. IEEE Transactions on Image

 Processing, (2021) Video

[7] Xiaoming Deng, Yinda Zhang, Jian Shi, Yuying Zhu, Dachuan Cheng, Dexin Zuo, Zhaopeng Cui, Ping Tan,

 Liang Chang, Hongan Wang, Hand pose understanding with large-scale photo-realistic rendering dataset.

 IEEE Transactions on Image Processing, (2021) Video

[8] Kevin T. Maher, Ze-Yuan Huang, Jian-Cheng Song, Xiaoming Deng, Yu-Kun Lai, Cuixia Ma, Hao Wang,

 Yong-Jin Liu, Hongan Wang, E-ffective: A visual analytic system for exploring the emotion and effectiveness

 of inspirational speeches. IEEE Transactions on Visualization and Computer Graphics, (2021)

[9] Zihao Zhang, Lei Hu, Xiaoming Deng, Shihong Xia, Weakly supervised adversarial learning for 3D human

 pose estimation from point clouds. IEEE Transactions on Visualization and Computer Graphics, (2020) Video

[10] Xiaobing Du, Xiaoming Deng, Hangyu Qin, Yezhi Shu, Fang Liu, Guozhen Zhao, Yu-Kun Lai,  Cuixia Ma,

 Yong-Jin Liu, Hongan Wang, MMPosE: Movie-induced multi-label positive emotion classification through EEG

 signals, IEEE Transactions on Affective Computing, (2023)

[11] Xiaobing Du, Cuixia Ma, Guanhua Zhang, Jinyao Li, Yu-Kun Lai, Guozhen Zhao, Xiaoming Deng,  Yong-Jin

 Liu, Hongan Wang,  An efficient LSTM network for emotion recognition from multichannel EEG signals. IEEE

 Transactions on Affective Computing, (2020)

[12] Xiaoming Deng, Yinda Zhang, Shuo Yang, Ping Tan, Liang Chang, Ye Yuan, Hongan Wang, Joint hand detection

 and rotation estimation using CNN, IEEE Transactions on Image Processing,  (2018)

[13] Wei Zhang, Zeyi Lin, Jian Cheng, Cuixia Ma, Xiaoming Deng, Hongan Wang, STA-GCN: two-stream graph

 convolutional network with spatial–temporal attention for hand gesture recognition, The Visual Computer, (2020)

[14] Dachuan Cheng, Jian Shi, Yanyun Chen, Xiaoming Deng, Xiaopeng Zhang, Learning scene illumination by pairwise

 photos from rear and front mobile cameras, Computer Graphics Forum, (2018)

[15] Xiaoming Deng, Fuchao Wu, Yihong Wu, Fuqing Duan, Liang Chang, Hongan Wang, Self-calibration of hybrid

 central catadioptric and perspective cameras, Computer Vision and Image Understanding, (2012)  

[16] Fuqing Duan, Fuchao Wu, Mingquan Zhou, Xiaoming Deng, Yun Tian, Calibrating effective focal length for central

 catadioptric cameras using one space line, Pattern Recognition Letters,  (2012) 

[17] Hui Zeng, Xiaoming Deng, Zhanyi Hu, A new normalized method on line-based homography estimation, Pattern

 Recognition Letters, (2008)

国际会议：

[1] Yang Zou, Yanguang Wan, Yonghao Zhang,  Xiao Zhou, Jian Cheng, Cuixia  Ma, Chun Yu, Xiaoming Deng,

 Hongan Wang, Gesture Builder: Flexible Gesture Customization and Efficient Recognition on VR Devices.

 Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 2025  Video

[2] Zeyuan Huang, Cangjun Gao, Yaxian Shan, Haoxiang Hu, Qingkun Li, Xiaoming Deng, Cuixia Ma, Yu-Kun Lai,

Yong-Jin Liu, Feng Tian, Guozhong Dai, and Hongan Wang. SketchGPT: A Sketch-based Multimodal Interface

for Application-Agnostic LLM Interaction. UIST 2025 Video

[3] Wentian Qu, Jiahe Li, Jian Cheng, Jian Shi, Chenyu Meng, Cuixia Ma, Hongan Wang, Xiaoming Deng,

 Yinda Zhang, HOGSA: Bimanual Hand-Object Interaction Understanding with 3D Gaussian Splatting

Based Data Augmentation. AAAI 2025 Video

[4] Wentian Qu, Chenyu Meng, Heng Li,  Jian Cheng, Cuixia Ma, Hongan Wang,  Xiao Zhou, Xiaoming Deng,

 Ping Tan, Universal Features Guided Zero-Shot Category-Level Object Pose Estimation.  AAAI 2025 

[5] Yonghao Zhang, Qiang He, Yanguang Wan, Yinda Zhang, Xiaoming Deng, Cuixia Ma, Hongan Wang,

 DiffGrasp: Whole-Body Grasping Synthesis Guided by Object Motion Using a Diffusion Model.  AAAI 2025 Video

[6] Jianping Jiang, Xinyu Zhou, Bingxuan Wang, Xiaoming Deng, Chao Xu, Boxin Shi, Complementing event

  streams and RGB frames for hand mesh reconstruction. CVPR 2024. Video

[7] Ran Zuo, Haoxiang Hu, Xiaoming Deng, Cangjun Gao, Zhengming Zhang, Yu-Kun Lai, Cuixia Ma,

 Yong-Jin Liu, Hongan Wang, SceneDiff: Generative Scene-Level Image Retrieval with Text and Sketch Using

 Diffusion Models. IJCAI 2024.

[8] Zeyuan Huang, Cangjun Gao, Haiyan Wang, Xiaoming Deng, Yu-Kun Lai, Cuixia Ma, Shengfeng Qin,

 Yong-Jin Liu, Hongan Wang, SpeciFingers: Finger Identification and Error Correction on Capacitive

 Touchscreens. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 8(1) 2024.

[9] Haoxiang Hu, Cangjun Gao, Yaokun Li, Xiaoming Deng, Yu-Kun Lai, Cuixia Ma, Yong-Jin Liu,  Hongan Wang,

 SpaceGTN: A Time-Agnostic Graph Transformer Network for Handwritten Diagram Recognition and

 Segmentation. AAAI 2024.

[10] Baowen Zhang, Jiahe Li, Xiaoming Deng, Yinda Zhang, Cuixia Ma, Hongan Wang, Self-supervised

 learning of implicit shape representation with dense correspondence for deformable objects. ICCV 2023.

[11] Wentian Qu, Zhaopeng Cui, Yinda Zhang, Chenyu Meng, Cuixia Ma, Xiaoming  Deng, Hongan Wang,

 Novel-view synthesis and pose estimation for hand-object interaction from sparse views. ICCV 2023. Video

[12] Jian Cheng, Yanguang Wan, Dexin Zuo, Cuixia Ma, Jian Gu, Ping Tan, Hongan Wang, Xiaoming Deng,

 Yinda Zhang, Efficient virtual view selection for 3D hand pose estimation, AAAI 2022. 

[13] Baowen Zhang, Yangang Wang, Xiaoming Deng, Yinda Zhang, Ping Tan, Cuixia Ma, Hongan Wang,

 Interacting two-hand 3D pose and  shape reconstruction from single color image, ICCV 2021. Video

[14] Zihao Zhang, Lei Hu, Xiaoming Deng, Shihong Xia, Sequential 3D human pose estimation using

 adaptive point cloud sampling strategy, IJCAI 2021. Video

[15] Fang Liu, Changqing Zou, Xiaoming Deng, Ran Zuo, Yu-Kun Lai, Cuixia Ma, Yong-Jin Liu, Hongan Wang,

 SceneSketcher: Fine-grained image retrieval with scene sketches, ECCV 2020. Video

[16] Fang Liu, Xiaoming Deng, Yu-Kun Lai, Yong-Jin Liu, Cuixia Ma, Hongan Wang, SketchGAN: Joint sketch

 completion and recognition with generative adversarial network, CVPR 2019.

[17] Xiaoming Deng, Shihong Xia, Wenzhong Wang, Zhaoqi Wang, Liang Chang, Hongan Wang, Automatic gait

 motion capture with missing-marker fillings, ICPR 2014. 

[18] Zhenlong Zhou, Bo Shu, Shaojie. Zhuo, Xiaoming Deng, Ping Tan, Stephen Lin, Image-based clothes animation

 for virtual fitting, ACM SIGGRAPH Asia 2012, Technical briefs.

已指导学生

袁野        硕士研究生

杨硕        硕士研究生

朱玉影     硕士研究生

左德鑫     硕士研究生

林泽一     硕士研究生

程坚        硕士研究生

柯铭雨     硕士研究生

张宝文     硕士研究生

李家和     硕士研究生

万炎广     硕士研究生

曲文天     博士研究生

张永浩     硕士研究生

现指导学生

程坚        博士研究生

蒙宸宇     博士研究生

欧阳刘飞  博士研究生

贺强         博士研究生 (联合指导)

邹杨         硕士研究生

李浩生      硕士研究生

孙佳熙      硕士研究生