September 26-27, 2016
New York, NY

Building and applying emotion recognition

Anna Roth (Microsoft), Cristian Canton (Microsoft Technology and Research)
11:50am–12:30pm Monday, 09/26/2016
Implementing AI
Location: 3D09 Level: Intermediate
Average rating: **...
(2.00, 1 rating)

Prerequisite knowledge

  • A high-level knowledge of machine learning
  • What you'll learn

  • Understand the importance of emotion recognition and the challenges of acquiring a good ground truth
  • Description

    Anna Roth and Cristian Canton walk you through building a system to recognize emotions by inferring them from facial expressions. Cristian and Anna explain how they trained their emotion recognition CNN from noisy data and how to approach labeling subjective data like emotion with crowdsourcing before showing a demo of this work in action, as it is exposed in Microsoft’s Emotion API.

    Photo of Anna Roth

    Anna Roth


    Anna S. Roth a PM for the computer vision cloud team at Microsoft. Previously she worked at Microsoft Technology & Research, on the team which launched Microsoft Cognitive Services. Say hello on Twitter at @AnnaSRoth.

    Photo of Cristian Canton

    Cristian Canton

    Microsoft Technology and Research

    Cristian Canton is a senior SDE and researcher at Microsoft Technology and Research, where he is primarily focused on bridging the gap between bleeding-edge state-of-the-art computer vision and machine-learning research and impactful products. Cristian’s topics of interest revolve around computer vision and machine learning applied to scene understanding. He holds a BSc and a PhD in telecommunications engineering from the Technical University of Catalonia (UPC) and an MSc from the Swiss Federal Institute of Technology of Lausanne (EPFL).