刘梦源 博士生导师
研究方向：深度学习、计算机视觉、视频分析与理解
教育背景：
| 2012-2017 | 北京大学 | 博士 | |
| 2017-2018 | 新加坡南洋理工大学 | 博士后 | |
| 2018-2020 | 腾讯科技 | 高级研究员 | |
| 2020-2023 | 中山大学(深圳) | 副教授 | |
| 2023-至今 | 北京大学 | 博士生导师 |
发表论文
| # | 作者 | 会议|期刊 | 论文名称 |
| 1 | Wei Shi, Hong Liu, Mengyuan Liu | Pattern Recognition | Image-to-video person re-identification using three-dimensional semantic appearance alignment and cross-modal interactive learning |
| 2 | Mengyuan Liu, Youneng Bao, Yongsheng Liang, Fanyang Meng | IEEE Signal Processing Letters | Spatial-Temporal Asynchronous Normalization for Unsupervised 3D Action Representation Learning |
| 3 | Wenhao Li, Hong Liu, Runwei Ding, Mengyuan Liu, Pichao Wang, Wenming Yang | IEEE Transactions on Multimedia | Exploiting temporal contexts with strided transformer for 3d human pose estimation |
| 4 | Xuan Wang, Minghong Zhong, Hoiyuen Cheng, Junjie Xie, Yingchu Zhou, Jun Ren, Mengyuan Liu | CAAI Transactions on Intelligence Technology | SpikeGoogle: Spiking Neural Networks with GoogLeNet-like inception module |
| 5 | Wei Shi, Hong Liu, Mengyuan Liu | Image and Vision Computing | IRANet: Identity-relevance aware representation for cloth-changing person re-identification |
| 6 | Yi Zhang, Youjun Zhao, Yuhang Wen, Zixuan Tang, Xinhua Xu, Mengyuan Liu | Proceedings of the 29th ACM International Conference on Multimedia | Facial Prior Based First Order Motion Model for Micro-expression Generation |
| 7 | Yang Liu, Huaqiu Wang, Fanyang Meng, Mengyuan Liu, Hong Liu | 2021 IEEE International Conference on Image Processing (ICIP) | Attend, Correct And Focus: A Bidirectional Correct Attention Network For Image-Text Matching |
| 8 | Wei Shi, Hong Liu, Mengyuan Liu | Neurocomputing | Identity-sensitive loss guided and instance feature boosted deep embedding for person search |
| 9 | Hong Liu, Bin Ren, Mengyuan Liu, Runwei Ding | IEEE International Conference on Image Processing (ICIP) | Grouped Temporal Enhancement Module for Human Action Recognition |
| 10 | Hong Liu, Linlin Zhang, Lisi Guan, Mengyuan Liu | IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | GFNET: A Lightweight Group Frame Network for Efficient Human Action Recognition |
| 11 | Liu M, Liu H, Chen C | Pattern Recognition | Enhanced skeleton visualization for view invariant human action recognition[ |
| 12 | Liu M, Liu H, Chen C | IEEE Transactions on Circuits & Systems for Video Technology | 3D Action Recognition Using Multi-scale Energy-based Global Ternary Image |
| 13 | Liu M, Liu H | Neurocomputing | Depth Context: a new descriptor for human activity recognition by using sole depth sequences |
| 14 | Sun Q, Liu H, Liu M | Neurocomputing | Human activity prediction by mapping grouplets to recurrent Self-Organizing Map |
| 15 | Liu M, Chen C, Liu H | IEEE International Conference on Multimedia and Expo | LEARNING INFORMATIVE PAIRWISE JOINTS WITH ENERGY-BASED TEMPORAL PYRAMID FOR 3D ACTION RECOGNITION |
| 16 | Liu M, Chen C, Liu H | IEEE International Conference on Multimedia and Expo | 3D ACTION RECOGNITION USING DATA VISUALIZATION AND CONVOLUTIONAL NEURAL NETWORKS |
| 17 | Liu M, Liu H, Sun Q | IEEE International Conference on Multimedia and Expo | Action classification by exploring directional co-occurrence of weighted stips |
| 18 | Liu M, Liu H, Chen C | International Conference on 3d Vision. IEEE | Energy-Based Global Ternary Image for Action Recognition Using Sole Depth Sequences |
| 19 | Liu M, Chen C, Meng F | 3D ACTION RECOGNITION USING MULTI-TEMPORAL SKELETON VISUALIZATION | |
| 20 | Liu M, Liu H, Sun Q | Caai Transactions on Intelligence Technology | Salient pairwise spatio-temporal interest points for real-time activity recognition |
| 21 | Chen C, Liu M, Zhang B | International Joint Conference on Artificial Intelligence. AAAI Press | 3D action recognition using multi-temporal depth motion maps and fisher vector |
| 22 | Liu H, Liu M, Sun Q | Learning directional co-occurrence for human action classification | |
| 23 | Liu M, Liu H, Chen C | IEEE Transactions on Multimedia (T-MM) | Robust 3D Action Recognition through Sampling Local Appearances and Global Distributions |