A5069390185- Emotion and Mood Recognition
- Visual Attention and Saliency Detection
- Digital Marketing and Social Media
- Consumer Behavior in Brand Consumption and Identification
National Research University Higher School of Economics
2019-2020
Lomonosov Moscow State University
2020
In the recent years facial emotion recognition algorithms have evolved and in some cases top commercial detect emotions like happiness better than humans do. To evaluate performance of these algorithms, common practice is to compare them with human-labeled ground truth. This article covers monitoring advancements automatic solutions, here we suggest an additional criteria for their evaluation, that agreement between algorithms’ predictions. this work, four algorithms: Affectiva Affdex,...
Ad recall is a commonly used measure of advertising effectiveness. Automatic prediction effectiveness will help to improve video and optimize the process ad creation. We present novel multimodal approach for based on viewer’s features features. In our experiment twenty people watched ads (n=100 in total). Ads have ground truth that was previously obtained field study. While were watching ads, we recorded them with camera, collected contact photolpletysmography eye-tracking data, also asked...