胡占义

胡占义，男，中国科学院自动化研究所研究员，国家自然科学基金信息学部咨询专家委员会委员，国家绕月探测科学应用专家委员会专家。^[1]

胡占义，研究员，1981年至1985年在北方工业大学自动化系攻读学士学位，1985年至1986年在四川外语学院学习法语。1986年12月至1993年2月在比利时列日大学深造并获得博士学位。自1993年2月起，胡占义在中国科学院自动化研究所工作，期间于1997年5月至1998年5月在香港中文大学交流。胡占义在学术界担任多项重要职务，包括《计算机辅助设计和图形学学报》副主编、《中国科学》编委、《科学通报》编委、Journal of Computer Science and Technology编委、《自动化学报》编委以及“十五-863”信息获取和处理主体专家。

- 机器人三维环境感知，2015-01--2020-12。

- 三维场景理解中的高阶能量优化理论与方法研究，2014-01--2018-12。

- 视觉腹部通道建模和表达一致性研究，2018-01--2022-12。

- P3P问题多解之间的伴随出现现象研究，2019-01--2022-12。

- SAR图像视觉三维认知理论与方法，2020-01--2024-12。

胡占义在学术期刊和国际会议上发表了多篇论文，涉及计算机视觉、图像处理、三维重建等多个领域。以下是部分论文列表：

- Two-View Line Segment Reconstruction Based on Structure Priors, SCIENCE CHINA Information Sciences, 2020, 第 3 作者。

- 3D Scanning of High Dynamic Scenes Using an RGB-D Sensor and an IMU on a Mobile Device, IEEE Access, 2019, 第 3 作者。

- Ground and aerial meta-data integration for localization and reconstruction: A review, Pattern Recognition Letters, 2019, 第 3 作者。

- Effective Piecewise Planar Modeling Based on Sparse 3D Points and Convolutional Neural Network, Neurocomputing, 2019, 第 3 作者。

- Complete Scene Reconstruction by Merging Images and Laser Scans, IEEE Transactions on Circuits and Systems for Video Technology, 2019, 第 6 作者。

- Zero-shot learning from Adversarial feature residual to compact visual feature, AAAI conference, 2019, 第 3 作者。

- Active Semantic Labeling of Street View Point Clouds, International Conference on Multimedia and Expo, ICME 2019, 2019, 第 3 作者。

- Visual-Inertial Odometry Tightly Coupled with Wheel Encoder Adopting Robust Initialization and Online Extrinsic Calibration, IROS, 2019, 2019, 第 3 作者。

- Learning Depth from Single Images with Deep Neural Network Embedding Focal Length, IEEE Transactions on Image Processing,Vol.27,No.29, pp.4676-4689, 2018, 通讯作者。

- Geometrically Stable Tracking for Depth Images Based 3D Reconstruction on Mobile Devices, ISPRS Journal of Photogrammetry and Remote Sensing, Vol.143, pp.222-232, 2018, 第 3 作者。

- Ancient Chinese Architecture 3D Preservation by Merging Ground and Aerial Point Clouds, ISPRS Journal of Photogrammetry and Remote Sensing, Vol.143, pp.72-84, 2018, 第 6 作者。

- Commentary: Using goal-driven deep learning models to understand sensory cortex, Frontiers in Computational Neuroscience, 19 January 2018, 通讯作者。

- Learning Stratified 3D Scene Reconstruction, Science China: Information Sciences, Vol.61, Feb., 2018, 通讯作者。

- Statistics of Visual Responses to Object Stimuli from Primate AIT Neurons to DNN Neurons, Neural Computation 30:447-476, 2018, 通讯作者。

- Large Scale Urban Scene Modeling from MVS Meshes, ECCV 2018, 2018, 第 4 作者。

- Fine-Level Semantic Labeling of Large-Scale 3D Model by Active Learning., 3DV2018, 2018, 第 3 作者。

- Dynamic Graph Cuts in Parallel, IEEE Transactions on Image Processing, Vol.26, No.8, pp. 3775-3788, 2017, 通讯作者。

- Comparison of IT Neural Response Statistics with Simulations, Frontiers in Computational Neuroscience,July 11, 2017, 通讯作者。

- Tracks Selection for Robust, Efficient and Scalable Large-Scale Structure from Motion, Pattern Recognition, Vol.72, pp. 341-354 2017, 第 3 作者。

- Accurate and efficient ground-to-aerial model alignment, Pattern Recognition, 76(4): 288-302, 2018, 第 5 作者。

- Two-Stream Deep Correlation Network for Frontal Face Recovery, IEEE Signal Processing Letters,Vol. 24, No.10，pp 1478 – 1482，2017, 第 4 作者。

- Semantic labeling of High Resolution Aerial Images Using an Ensemble of Fully Convolutional Networks, the Journal of Applied Remote Sensing, Dec. 2017://DOI: 10.1117/1.JRS.11.042617, 第 4 作者。

- High-Resolution Remote Sensing Data Classification over Urban Areas Using Random Forest Ensemble and Fully Connected Conditional Random Field, ISPRS International Journal of Geo-Information, 6(8), 245, 2017, 第 4 作者。

- Modern Physiognomy: An Investigation on the Prediction on the Personality Traits and the Intelligence from the Human Face, Science China: Information Sciences, Vol.61, May, 2017, 通讯作者。

- Physiognomy: Personality Traits Prediction by Learning,14(4):371-385,2017, International Journal of Automation and Computing, 第 4 作者。

- HSfM: Hybrid Structure-from-Motion, CVPR2017,July 21 – 26, Honolulu, Hawaii , USA，pp: 2393-2402， 2017, 第 3 作者。

- Accurate Mesh-based Alignment for Ground and Aerial Multi-view Stereo Models, IEEE International Conference on Image Processing, Sept.17-20 , Beijing, China, pp: 2627-2631. 2017, 第 4 作者。

- CSfM: Community-based Structure from Motion, IEEE International Conference on Image Processing, Sept.17-20 , Beijing, China, pp: 4517-4521, 2017, 第 4 作者。

- Batched Incremental Structure-from-Motion, International Conference on 3D vision( 3DV 2017), October 10-12 Qingdao, China, pp: 205-214, 2017, 第 4 作者。

- Variational Building Modeling from Urban MVS Meshes., International Conference on 3D vision (3DV 2017), October 10-12 Qingdao, China, pp: 318-326, 2017, 第 4 作者。