Abstract | ||
---|---|---|
Person re-identification is one of the widely studied research topic in the fields of computer vision and pattern recognition. In this paper, we present a deep multi-instance learning approach for person re-identification. Since most publicly available databases for pedestrian re-identification are not enough big, over-fitting problems occur in deep learning architectures. To tackle this problem, person re-identification is expressed as a deep multi-instance learning issue. Therefore, a multiscale feature learning process is introduced which is driven by optimizing a novel cost function. We report on experiments and comparisons to other state-of-the-art algorithms using publicly available databases such as VIPeR and ETHZ. |
Year | Venue | Field |
---|---|---|
2017 | European Signal Processing Conference | Robot learning,Pedestrian,Instance-based learning,Active learning (machine learning),Computer science,Feature extraction,Artificial intelligence,Deep learning,Feature learning,Machine learning |
DocType | ISSN | Citations |
Conference | 2076-1465 | 0 |
PageRank | References | Authors |
0.34 | 14 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Domonkos Varga | 1 | 13 | 4.29 |
Tamás Szirányi | 2 | 152 | 26.92 |