Sergey Tulyakov
Panos Achlioptas
Description: Affection, Affection-dataset, Emotions, Deep Learning, neural-speakers
Real-world images often convey emotional intent, i.e., the photographer tries to capture and promote an emotionally interesting story. In this work, we explore the emotional reactions that real-world images tend to induce by using natural language as the medium to express the rationale behind an affective response to a given visual stimulus. To embark on this journey, we introduce and share with the research community a large-scale dataset that contains emotional reactions and free-form textual explanations
We curate and share Affection a large-scale dataset with emotional reactions to real-world images and explanations behind them in free-form language. We introduce the task of E motional E xplanation C aptioning ( EAC ) and develop correspondingly neural speakers that can create plausible utterances to explain emotions grounded in real-world images. Our best neural speaker passes an emotional Turing test with a 65% chance. I.e., its generations are this likely to be thought of as if other humans made them, a
The Affection dataset is provided under specific terms of use .
Sergey Tulyakov
Panos Achlioptas