Abstract
Face re-identification is largely thought of as a solved problem in the research community, with State-of-the-art systems attaining human-level performance on unconstrained image datasets. However, these results do not seem to translate to the real world. In systems matching people in surveillance-like footage to high-quality images, reported performance is much lower than what the literature would suggest. In this work, we contribute a multi-modal dataset for evaluating real-world performance of facial re-identification systems. We then perform a verification and re-identification evaluation for state-of-art systems on both this dataset and the popular benchmarking dataset Labelled Faces in the Wild (LFW).
Original language | English |
---|---|
Title of host publication | Proceedings of the 20th Irish Machine Vision and Image Processing Conference, IMVIP 2018 |
Editors | Bryan W. Scotney |
Publisher | Irish Pattern Recognition & Classification Society |
Pages | 137-144 |
ISBN (Electronic) | 9780993420733 |
Publication status | Published - 31 Aug 2018 |
Event | 20th Irish Machine Vision and Image Processing Conference - Ulster University, Belfast, United Kingdom Duration: 29 Aug 2018 → 31 Aug 2018 |
Conference
Conference | 20th Irish Machine Vision and Image Processing Conference |
---|---|
Abbreviated title | IMVIP |
Country/Territory | United Kingdom |
City | Belfast |
Period | 29/08/2018 → 31/08/2018 |