颜力琦

颜力琦.jpg

   

高级工程师

复旦大学博士生

 

 现博士就读于复旦大学,主要研究计算机视觉(CV)、自然语言处理(NLP)和机器人等相关技术领域。本科毕业于北京邮电大学,曾担任校学生会科技部副部长。本科期间曾负责国家级大学生创新创业项目一项,后获得研究生推荐免试资格,保研至复旦大学·西湖大学联培直博项目。博士期间曾担任西湖大学ACM学生分会副主席、主席。2019-2020连续两年获得之江杯全球人工智能大赛二等奖,并获西湖大学苏武奖学金。参与完成杭州市重大科技创新项目1项。申请专利2项。共发表论文9篇,其中第一作者7篇。在SCI 一区期刊(TCSVT)、中国计算机协会推荐A类顶级会议(AAAI、ICCV和IJCAI)和其它国际顶级会议(IROS和ICASSP)上均有发表论文。担任2023年国际人工智能顶级会议AAAI的程序委员会委员(PC-member)、审稿人。详见个人主页: https://ylqi.github.io/

 

 

代表性论文

[1] Liqi Yan*, Qifan Wang, Siqi Ma, Jingang Wang, Changbin Yu (2022). Solve the Puzzle of Instance Segmentation in Videos: A Weakly Supervised Framework with Spatio-Temporal Collaboration. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT).

[2] Liqi Yan*, Qifan Wang, Yiming Cui, Fuli Feng, Xiaojun Quan, Xiangyu Zhang, Dongfang Liu (2022). GL-RG: Global-Local Representation Granularity for Video Captioning. International Joint Conference on Artificial Intelligence (IJCAI). (pp. 2769-2775).

[3] Yiming Cui*, Liqi Yan*, Zhiwen Cao, Dongfang Liu (2021). Tf-blender: Temporal feature blender for video object detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (pp. 8138-8147).

[4] Liqi Yan*, Yiming Cui, Yingjie Chen, Dongfang Liu* (2021). Hierarchical attention fusion for geo-localization. In 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 2220-2224). IEEE.

[5] Dongfang Liu, Yiming Cui, Liqi Yan*, Christos Mousas, Baijian Yang, Yingjie Chen (2021). Densernet: Weakly supervised visual localization using multi-scale feature aggregation. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 35, No. 7, pp. 6101-6109).

[6] Liqi Yan*, Dongfang Liu, Yaoxian Song, Changbin Yu (2020). Multimodal Aggregation approach for memory vision-voice indoor navigation with meta-learning. 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

 

参与项目

杭州市科学技术局, 重大科技创新项目, 20182014B07, 高动态环境下工业车辆无人驾驶技术及集群控制, 2019-01至2021-12, 200万元

 

 

发明专利

[1] 一种基于群体识别的多个体间距检测系统和方法。专利公开号:CN111739651A

[2] 基于图像物体检测技术的利用摄像头的视频实物计数方法。专利公开号:CN110472552A