Context-aware Captions from Context-agnostic Supervision

Vedantam, R; Bengio, S; Murphy, K; Parikh, D; Chechik, G

Vedantam, R (reprint author), Virginia Tech, Blacksburg, VA 24061 USA.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017; ( ): 1070

Abstract

We introduce an inference technique to produce discriminative context-aware image captions (captions that describe differences between images or visua......

Full Text Link