PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data.
Zheng TangMilind NaphadeStan BirchfieldJonathan TremblayWilliam HodgeRatnesh KumarShuo WangXiaodong YangPublished in: CoRR (2020)
Keyphrases
- synthetic data
- multi task learning
- multi task
- learning tasks
- multitask learning
- multiple tasks
- gaussian processes
- learning problems
- real world
- real image data
- high order
- pose estimation
- data sets
- learning models
- transfer learning
- theoretical analysis
- multi label image annotation
- learning algorithm
- supervised learning
- feature selection
- machine learning
- data mining