Spectral Attribute Learning for Visual Regression
Tutkimustuotos › › vertaisarvioitu
Yksityiskohdat
| Alkuperäiskieli | Englanti |
|---|---|
| Sivut | 74-81 |
| Julkaisu | Pattern Recognition |
| Vuosikerta | 66 |
| Varhainen verkossa julkaisun päivämäärä | 13 tammikuuta 2017 |
| DOI - pysyväislinkit | |
| Tila | Julkaistu - 2017 |
| OKM-julkaisutyyppi | A1 Alkuperäisartikkeli |
Tiivistelmä
A number of computer vision problems such as facial age estimation, crowd counting and pose estimation can be solved by learning regression mapping on low-level imagery features. We show that visual regression can be substantially improved by two-stage regression where imagery features are first mapped to an attribute space which explicitly models latent correlations across continuously-changing output. We propose an approach to automatically discover “spectral attributes” which avoids manual work required for defining hand-crafted attribute representations. Visual attribute regression outperforms direct visual regression and our spectral attribute visual regression achieves state-of-the-art accuracy in multiple applications.