2017 Fiscal Year Annual Research Report
Fast, effective and robust person re-identification for large-scale real applications
| Project/Area Number |
15K16024
|
|---|
| Research Institution | Nara Institute of Science and Technology |
|---|
Principal Investigator |
伍 洋 奈良先端科学技術大学院大学, 研究推進機構, 特任助教 (30750559)
|
|---|
| Project Period (FY) |
2015-04-01 – 2018-03-31
|
| Keywords | Person Re-identification / Pattern Recognition / Computer Vision / Machine Learning / Deep Learning / Transfer Learning / Active Learning / Object Tracking |
|---|
| Outline of Annual Research Achievements |
In this year, we have already got 1 journal paper and 7 conference papers published, and gave 4 invited talks at 4 top-level universities from 2 countries (China and United Kingdom). Besides, there are 8 other papers (2 international journal papers and 6 international conference papers) still under review.
These papers covers the following aspects. 1. New metric learning model. 2. Further enhancing the effectiveness of our person re-identification model via exploring better temporal representation and image generation based data augmentation. 3. Adaptation to changing environments via transfer learning and active learning. 4. Pose estimation and tracking.
Within them, 1 and 3 are mostly about planned work, while there are also some exploratory works in 2-4, good for future research.
|
-
-
-
-
-
-
-
-
-
[Presentation] 3D Hand Pose Estimation: From Current Achievements to Future Goals2018
Author(s)
Shanxin Yuan, Guillermo Garcia-Hernando, Bjorn Stenger, Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee, Pavlo Molchanov, Jan Kautz, Sina Honari, Liuhao Ge, Junsong Yuan, Xinghao Chen, Guijin Wang, Fan Yang, Kai Akiyama, Yang Wu, et. al.
Organizer
IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)
Int'l Joint Research
-
-
-
-
-
