Abstract | ||
---|---|---|
Automatic person re-identification in is a crucial capability underpinning many applications in public space video surveillance. It is challenging due to intra-class variation in person appearance when observed in different views, together with limited inter-class variability. Various recent approaches have made great progress in re-identification performance using discriminative learning techniques. However, these approaches are fundamentally limited by the requirement of extensive annotated training data for every pair of views. For practical re-identification, this is an unreasonable assumption, as annotating extensive volumes of data for every pair of cameras to be re-identified may be impossible or prohibitively expensive. In this paper we move toward relaxing this strong assumption by investigating flexible multi-source transfer of re-identification models across camera pairs. Specifically, we show how to leverage prior re-identification models learned for a set of source view pairs (domains), and flexibly combine these to obtain good re-identification performance in a target view pair (domain) with greatly reduced training data requirements in the target domain. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1145/2510650.2510658 | ARTEMIS@ACM Multimedia |
Keywords | Field | DocType |
re-identification model,target view pair,domain transfer,source view pair,automatic person re-identification,re-identification performance,camera pair,extensive annotated training data,training data requirement,good re-identification performance,practical re-identification,transfer learning,support vector machines | Training set,Public space,Leverage (finance),Computer science,Support vector machine,Transfer of learning,Artificial intelligence,Machine learning,Underpinning,Discriminative learning | Conference |
Citations | PageRank | References |
12 | 0.57 | 25 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ryan Layne | 1 | 160 | 5.69 |
Timothy M. Hospedales | 2 | 1282 | 73.06 |
Shaogang Gong | 3 | 7941 | 498.04 |