原春锋，研究员，博士生导师，北京市杰出青年基金获得者，科技部新一代人工智能重大项目项目负责人。分别于2012年、2015-2016年、2019-2020年在阿德莱德大学、微软亚洲研究院、美国西北大学进行访问学者研究工作。目前主要从事多媒体智能理解、视频图像内容理解、多模态行为识别、跨模态视频描述、目标检测、预训练大模型等方面的研究。已在IEEE T-PAMI、IJCV、IEEE T-IP等权威期刊和ICCV、CVPR、ECCV、IJCAI、AAAI等国际会议上发表论文80余篇。

多媒体内容理解与安全，模式识别与机器学习

主持国家信息安全专项1项、科技部新一代人工智能重大专项项目1 项、北京市杰出青年基金项目1 项、国家自然科学基金面上项目2 项、青年项目1 项、国家重点研发计划子课题2 项、北京市自然科学基金联合项目1 项、中科院先导子课题1项，以及腾讯、阿里、美图等项目共20余项。

[1] Chunfeng Yuan, Baoxin Wu, Xi Li, Weiming Hu, Stephen Maybank, and Fangshi Wang, “Fusing R Features and Local Features with Context-aware Kernels for Action Recognition,” International Journal of Computer Vision (IJCV), Vol. 118, pp.151-171,2016.
[2] Chunfeng Yuan, Xi Li, Weiming Hu, Haibin Ling, and Stephen Maybank, “Modeling Geometric-Temporal Context with Directional Pyramid Co-Occurrence for Action Recognition,” IEEE transactions on Image Processing (IEEE T-IP), Vol. 23, No. 2, pp. 658-672, February 2014.
[3] Chunfeng Yuan, Weiming Hu, GuodongTian, and Shuang Yang, “Multi-Task Sparse Learning with Beta Process Prior for Action Recognition,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.423-429, 2013. Portland, Oregon.
[4] Chunfeng Yuan, Xi Li, Weiming Hu, Haibin Lin, Stephen Maybank, and Haoran Wang, “3D R Transform on Spatio-Temporal Interest Points for Action Recognition,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.724-730, 2013. Portland, Oregon.
[5] Juan Wang, Chunfeng Yuan#, Bing Li, Ying Deng, Weiming Hu, Stephen Maybank, “Self-Prior Guided Pixel Adversarial Networks for Blind Image Inpainting”, IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2023.
[6] Ziqi Zhang, Zongyang Ma, Chunfeng Yuan, Yuxin Chen, Peijin Wang, Zhongang Qi, Chenglei Hao, Bing Li, Ying Shan, Weiming Hu, Stephen Maybank, “Chinese Title Generation for Short Videos: Dataset, Metric and Algorithm”, IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), 2024.
[7] Li Yang, Chunfeng Yuan#*, Ziqi Zhang, Zhongang Qi, Yan Xu, Wei Liu, Ying Shan, Bing Li, Weiping Yang, Peng Li, Yan Wang, Weiming Hu, “Exploiting Contextual Objects and Relations for 3D Visual Grounding”, Thirty-seventh Conference on Neural Information Processing Systems (NIPS), 2023.
[8] Yuxin Chen, Ziqi Zhang, Chunfeng Yuan*, Bing Li, Ying Deng, Weiming Hu, “Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition,” Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021.

2022年获中国自动化学会技术发明奖一等奖。

授权国家发明专利20余项