项目首席科学家 王亮
项目编号：2016YFB1001000
国家重点研发计划云计算和大数据重点专项
National Key Research and Development Program of China
面向大范围场景透彻感知的视觉大数据智能分析关键技术与验证系统
项目简介
国家重点研发计划云计算和大数据重点专项 “面向大范围场景透彻感知的视觉大数据智能分析关键技术与验证系统”项目（2016-2020）于2016年10月正式启动。
通过视觉大数据的深度理解全面掌控大范围复杂场景动态，实现视觉感知不留死角，进而提出了本项目的研究目标：面向大范围场景视觉大数据，突破当前场景范围小、个体识别近、群体刻画弱、事件预警难等“感知盲区”，从“个体-群体-场景”多层次实现大范围复杂场景视觉大数据的多粒度和多维度透彻感知。
最新消息
| 2021-03-20 | 项目课题绩效评价会顺利召开 |
|---|---|
| 2020-11-16 | 项目年度进展报告会顺利召开 |
| 2019-05-21 | 项目进展情况汇报与交流会顺利召开 |
| 2018-11-30 | 项目顺利通过中期检查 |
| 2018-09-27 | 项目中期进展报告会暨中期检查筹备会顺利召开 |
| 2018-04-13 | 课题四内部交流会顺利召开 |
| 2018-02-01 | 项目进展情况交流会顺利召开 |
| 2017-08-05 | 项目实施方案论证暨年度进展情况汇报会顺利召开 |
| 2017-07-13 | 商汤科技宣布完成4.1亿美元B轮融资 |
| 2017-06-20 | 中国电子学会《2017年VR/AR技术与产业研究报告》发布 |
| 2017-05-10 | 第一届视觉大数据高峰论坛成功在京举办 |
| 2017-03-30 | 林倞教授论文获得世界第一届10K最佳论文奖 - 钻石奖 |
| 2017-03-24 | 项目组黄凯奇研究员当选第十二届“中国科学院杰出青年” |
| 2017-03-22 | 2017年上半年度项目研讨会顺利召开 |
| 2017-03-09 | 中星微邓中翰两会建议：以自主芯片决胜AI时代 | 2016-12-27 | 佳都科技再度斩获“2015轨道交通创新力企业50强”及轨道交通创新产品奖 |
| 2016-12-16 | 项目组孙哲南研究员、周杰教授当选IAPR Fellow |
| 2016-12-13 | 项目组林倞教授、赫然研究员和冯建江副教授获得2016年国家优秀青年科学基金项目资助 |
| 2016-11-08 | 国家重点研发计划云计算和大数据重点专项“面向大范围场景透彻感知的视觉大数据智能分析关键技术与验证系统”项目启动会顺利召开 |
| 2016-09-21 | 国家重点研发计划云计算和大数据重点专项2016年度重点研究任务已经完成部署 |
课题设置
| 编号 | 名称 | |
| 课题一 | 01 | 大范围复杂场景视觉大数据的透彻感知理论与方法 |
| 课题二 | 02 | 个体视觉大数据的透彻感知关键技术 |
| 课题三 | 03 | 群体视觉大数据的透彻感知关键技术 |
| 课题四 | 04 | 场景视觉大数据的透彻感知关键技术 |
| 课题五 | 05 | 大范围场景透彻感知的验证系统和示范应用 |
论文推荐
- Junlin Hu, Jiwen Lu, Yap-Peng Tan, and Jie Zhou, “Deep transfer metric learning,” IEEE Trans. on Image Processing (TIP), vol.25, no. 12, pp. 5576-5588, 2016.
- Renliang Weng, Jiwen Lu, Yap-Peng Tan, and Jie Zhou, “Learning cascaded deep auto-encoder networks for face alignment, IEEE Trans. On Multimedia (TMM), vol.18, no. 10, pp. 2066-2078, 2016.
- Ran He, Xiang Wu, Zhenan Sun, and Tieniu Tan, “Learning invariant deep representation for NIR-VIS face recognition”, Proc.AAAI Conference on Artificial Intelligence, 2017, accepted.
- Yanbo Fan, Ran He, Jian Liang, and Baogang Hu, “Self-paced learning: an implicit regularization perspective”, Proc. AAAI Conference on Artificial Intelligence, 2017, accepted.
- Zifeng Wu, Yongzhen Huang, Liang Wang, Xiaogang Wang, and Tieniu Tan, A comprehensive study on cross-view gait based human identification with deep CNNs, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2016.
- JianFang Hu, Wei-Shi Zheng, Jianhuang Lai, and Jianguo Zhang, Jointly Learning Heterogeneous Features for RGB-D Activity Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2017 (DOI:10.1109/TPAMI.2016.2640292).
- Fang Zhao, Yongzhen Huang, Liang Wang, Tao Xiang, Tieniu Tan, Learning Relevance Restricted Boltzmann Machine for Un-structured Group Activity and Event Understanding, IJCV,119(3):329-345,2016.
- Yong Du, Yun Fu, Liang Wang, Representation Learning of Temporal Dynamics for Skeleton-Based Action Recognition. IEEE Trans. Image Processing 25(7): 3010-3022 (2016).
- Jiazhi He, Jianfang Hu, Xi Lu, Wei-Shi Zheng, Multi-Task Mid-Level Feature Learning for Micro-Expression Recognition. Pattern Recognition, 2017 (DOI: 10.1016/j.patcog.2016.11.029).
- J. Qin, Y. Wang, L. Liu, J. Chen and L. Shao, Beyond Semantic Attributes: Discrete Latent Attributes Learning for Zero-Shot Recognition, IEEE Signal Processing Letters (SPL), vol. 23, no. 11, pp. 1667-1671, Nov. 2016.
- Jie Gui, Zhenan Sun, Shuiwang Ji, Dacheng Tao, Tieniu Tan, Feature Selection Based on Structured Sparsity: A Comprehensive Study, IEEE Transactions on Neural Networks and Learning Systems, 2016, published online.
- Y. Sun, K. Nasrollahi, Z. Sun, T. Tan, "Complementary Cohort Strategy for Multimodal Face Pair Matching", IEEE Transactions on Information Forensics and Security, Vol.11, No.5, 2016, pp.937-950.
- Chao Ma, Yi Xu, Bingbing Ni, and Xiaokang Yang, "When Correlation Filters Meet Convolutional Neural Networks for Visual Tracking," IEEE Signal Processing Letters, 2016.
- Chao Ma, Chih-Yuan Yang, Xiaokang Yang, and Ming-Hsuan Yang, "Learninga No-reference Quality Metric for Single-Image Super-Resolution, "Computer Vision and Image Understanding, 2016, published online.
- Xiongkuo Min, Guangtao Zhai, Ke Gu, Yuming Fang, Xiaokang Yang,Xiaolin Wu, Jiantao Zhou, Xiaoming Liu. Blind Quality Assessment ofCompressed Images via Pseudo Structural Similarity ， InternationalConference on Media and Expo, 2016.(最佳论文奖)
- Zhe Ren, Junchi Yan, Bingbing Ni, Bin Liu, Xiaokang Yang and HongyuanZha. Unsupervised deep learning for optical flow estimation, TheThirty-First AAAI Conference on Artificial Intelligence, 2017.
- Yichao Yan, Bingbing Ni, Zhichao Song, Chao Ma, Yan Yan, and XiaokangYang, "Person Re-Identification via Recurrent Feature Aggregation," inEuropean Conference on Computer Vision, 2016.
- Le Wang, Gang Hua, Rahul Sukthankar, Jianru Xue, Zhenxing Niu, Nanning Zheng “Video Object and Co-Segmentation with Extremly Weak Supervision”, IEEE Transactions on Pattern Analysis and Machine Intelligence, in Press.
- Dongyu Zhang, Liang Lin*, Tianshui Chen, Xian Wu, Wenwei Tan, and Ebroul Izquierdo, "Content-Adaptive Sketch Portrait Generation by Decompositional Representation Learning", IEEE Transactions on Image Processing (T-IP), 26(1):328-339, 2017
- Chenglong Li, Liang Lin*, Wangmeng Zuo, and Jin Tang, "Learning Patch-based Dynamic Graph for Visual Tracking", Proc. of AAAI Conference on Artificial Intelligence (AAAI), February 2017, USA.