Abstract | ||
---|---|---|
Person re-identification concerns about the problem of recognizing people across space (captured by different cameras) and/or over time gaps. Though recently the literature on it grows rapidly, all the proposed solutions have treated it as a normal classification or ranking problem. In this paper, however, we argue that it is in fact a natural transfer learning problem, thus it's valuable and also necessary to investigate how the progress on transfer learning could benefit the research on it. We present so far the first study on justifying the effectiveness of a representative transfer learning methodology: feature-based inductive transfer learning, for person re-identification. Extensive experiments on standard datasets with typical methods result in several important findings. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/ICIP.2013.6738579 | ICIP |
Keywords | Field | DocType |
feature mapping,representative transfer learning methodology,feature-based inductive transfer learning,learning (artificial intelligence),ranking problem,transfer learning,normal classification problem,feature extraction,natural transfer learning problem,person re-identification,object recognition,inductive transfer learning,people recognition problem,person reidentification,learning artificial intelligence | Algorithmic learning theory,Semi-supervised learning,Instance-based learning,Multi-task learning,Pattern recognition,Inductive transfer,Active learning (machine learning),Computer science,Transfer of learning,Artificial intelligence,Machine learning,Feature learning | Conference |
ISSN | Citations | PageRank |
1522-4880 | 6 | 0.44 |
References | Authors | |
12 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yang Wu | 1 | 6 | 0.44 |
Wei Li | 2 | 59 | 5.16 |
Michihiko Minoh | 3 | 349 | 58.69 |
Masayuki Mukunoki | 4 | 199 | 21.86 |