Abstract | ||
---|---|---|
Dissimilarity measures are often used as a proxy or a handle to reason about data. This can be problematic, as the data representation is often a consequence of the capturing process or how the data is visualized, rather than a reflection of the semantics that we want to extract. Facial expressions are a subtle and essential part of human communication but they are challenging to extract from current representations. In this paper we present a method that is capable of learning semantic representations of faces in a data driven manner. Our approach uses sparse human supervision which our method grounds in the data. We provide experimental justification of our approach showing that our representation improves the performance for emotion classification. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/FG.2018.00035 | 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018) |
Keywords | Field | DocType |
facial expressions,representation learning,variational auto encoder | Data-driven,External Data Representation,Computer science,Emotion classification,Facial expression,Natural language processing,Artificial intelligence,Human communication,Perception,Feature learning,Semantics | Conference |
ISSN | ISBN | Citations |
2326-5396 | 978-1-5386-2336-7 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Olga Mikheeva | 1 | 0 | 0.34 |
carl henrik ek | 2 | 327 | 30.76 |
hedvig kjellstrom | 3 | 491 | 42.24 |