刘梦源
Work Unit：南洋理工大学research fellow
Current place of residence：新加坡
Dissertation：基于深度序列时空结构的人体行为识别方法
Email：nkliuyifang@gmail.com
Published Papers
| # | Authors | Journal|Conference | Title |
| 1 | Liu M, Liu H, Chen C | Pattern Recognition | Enhanced skeleton visualization for view invariant human action recognition[ |
| 2 | 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 |
| 3 | Liu M, Liu H | Neurocomputing | Depth Context: a new descriptor for human activity recognition by using sole depth sequences |
| 4 | Sun Q, Liu H, Liu M | Neurocomputing | Human activity prediction by mapping grouplets to recurrent Self-Organizing Map |
| 5 | 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 |
| 6 | Liu M, Chen C, Liu H | IEEE International Conference on Multimedia and Expo | 3D ACTION RECOGNITION USING DATA VISUALIZATION AND CONVOLUTIONAL NEURAL NETWORKS |
| 7 | Liu M, Liu H, Sun Q | IEEE International Conference on Multimedia and Expo | Action classification by exploring directional co-occurrence of weighted stips |
| 8 | Liu M, Liu H, Chen C | International Conference on 3d Vision. IEEE | Energy-Based Global Ternary Image for Action Recognition Using Sole Depth Sequences |
| 9 | Liu M, Chen C, Meng F | 3D ACTION RECOGNITION USING MULTI-TEMPORAL SKELETON VISUALIZATION | |
| 10 | Liu M, Liu H, Sun Q | Caai Transactions on Intelligence Technology | Salient pairwise spatio-temporal interest points for real-time activity recognition |
| 11 | 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 |
| 12 | Liu H, Liu M, Sun Q | Learning directional co-occurrence for human action classification | |
| 13 | Liu M, Liu H, Chen C | IEEE Transactions on Multimedia (T-MM) | Robust 3D Action Recognition through Sampling Local Appearances and Global Distributions |