Learning Deep Representations of Fine-grained Visual Descriptions

CVPR 2016 Scott ReedZeynep AkataBernt SchieleHonglak Lee

State-of-the-art methods for zero-shot visual recognition formulate learning as a joint embedding problem of images and side information. In these formulations the current best complement to visual features are attributes: manually encoded vectors describing shared characteristics among categories... (read more)

PDF Abstract

Evaluation results from the paper

  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.