Back to Search
Start Over
Learning Feature Aggregation in Temporal Domain for Re-Identification
- Publication Year :
- 2019
-
Abstract
- Person re-identification is a standard and established problem in the computer vision community. In recent years, vehicle re-identification is also getting more attention. In this paper, we focus on both these tasks and propose a method for aggregation of features in temporal domain as it is common to have multiple observations of the same object. The aggregation is based on weighting different elements of the feature vectors by different weights and it is trained in an end-to-end manner by a Siamese network. The experimental results show that our method outperforms other existing methods for feature aggregation in temporal domain on both vehicle and person re-identification tasks. Furthermore, to push research in vehicle re-identification further, we introduce a novel dataset CarsReId74k. The dataset is not limited to frontal/rear viewpoints. It contains 17,681 unique vehicles, 73,976 observed tracks, and 277,236 positive pairs. The dataset was captured by 66 cameras from various angles.<br />Under consideration at Computer Vision and Image Understanding
- Subjects :
- FOS: Computer and information sciences
Thesaurus (information retrieval)
Feature aggregation
Computer science
business.industry
Feature vector
Computer Vision and Pattern Recognition (cs.CV)
Computer Science - Computer Vision and Pattern Recognition
020207 software engineering
Pattern recognition
02 engineering and technology
Viewpoints
Object (computer science)
Weighting
Domain (software engineering)
Signal Processing
0202 electrical engineering, electronic engineering, information engineering
020201 artificial intelligence & image processing
Computer Vision and Pattern Recognition
Artificial intelligence
Focus (optics)
business
Software
Subjects
Details
- Language :
- English
- Database :
- OpenAIRE
- Accession number :
- edsair.doi.dedup.....ed0fd56405a9e1e7c8d3bc1d6dcddd9d