李乔哲，博士，中国科学院自动化研究所副研究员，主要研究方向为模式识别、智能博弈对抗和对手建模，在IEEE TCSVT、AAAI、IJCAI等多个国际学术期刊和会议上发表多篇学术论文。主持和参与中科院先导、国家专项领域等多项项目。
模式识别、智能博弈对抗、对手建模
多方博弈理论与方法，主持，中科院先导科技专项子课题，2020.07-2025.06
复杂环境下智能目标感知与分析，主持，中科院创新重点部署子课题，2021.05-2023.04
异构群体多域智能协同系统，参与，中科院联合基金重点专项， 2019.01-2021.05
国产智能芯片的图像智能测试集，参与，国家专项领域，2018.06-2020.12
面向芯片的无人系统智能测试集，参与，国家专项领域，2021.07-2023.12
博弈开放生态与对手意图建模，参与，中科院战略先导专项 ，2021.07-2023.06
[1] Qiaozhe Li, Xin Zhao, Ran He, Kaiqi Huang. Recurrent Prediction with Spatio-temporal Attention for Crowd Attribute Recognition. IEEE Transactions on Circuits and Systems for Video Technology, 2019. (CCF-B)
[2] Fei He, Qiaozhe Li, Xin Zhao, Kaiqi Huang. Temporal-adaptive Sparse Feature Aggregation for Video Object Detection. Pattern Recognition, 2022. (CCF-B)
[3] Qiaozhe Li, Xin Zhao, Ran He, Kaiqi Huang. Visual-semantic Graph Reasoning for Pedestrian Attribute Recognition. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2019. (CCF-A, acceptance rate: 16.7%)
[4] Qiaozhe Li, Xin Zhao, Ran He, Kaiqi Huang. Pedestrian Attribute Recognition by Joint Visual-semantic Reasoning and Knowledge Distillation. International Joint Conference on Artificial Intelligence (IJCAI), 2019. (CCF-A, acceptance rate:17.8%)
[5] Qiaozhe Li, Jiahui Zhang, Xin Zhao, Kaiqi Huang. Can DNN Detectors Compete Against Human Vision in Object Detection Task? Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 2021.
[6] Qiaozhe Li, Xin Zhao, Kaiqi Huang. Learning Temporally Correlated Representations using LSTMs for Visual Tracking. IEEE International Conference on Image Processing (ICIP), 2016.
Fei He, Naiyu Gao, Qiaozhe Li, Senyao Du, Xin Zhao, Kaiqi Huang. Temporal Context Enhanced Feature Aggregation for Video Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2021. (CCF-A)
[7] Yifei chen, Junge Zhang, Qiaozhe Li, Kaiqi Huang. FGA-NAS: Fast Resource-Constrained Neural Architecture Search by Greedy-ADMM Algorithm, International Joint Conference on Neural Networks (IJCNN), 2022.
基于视频的群体属性识别方法和装置，CN：CN108537128B
