Knowing who to listen to: Prioritizing experts from a diverse ensemble for attribute personalization
Learning attribute models for applications like Zero-Shot Learning (ZSL) and image search is challenging because they require attribute classifiers to generalize to test data that may be very different from the training data. A typical scenario is when the notion of an attribute may differ from one...
| Հիմնական հեղինակներ: | , , , , |
|---|---|
| Ձևաչափ: | Conference item |
| Հրապարակվել է: |
IEEE
2016
|