The ICML 2013 Workshop on Challenges in Representation Learning focused on three challenges: the black box learning challenge, the facial expression recognition challenge, and the multimodal learning challenge. We describe the datasets created for these challenges and summarize the results of the competitions. We provide suggestions for organizers of future challenges and some comments on what kind of knowledge can be gained from machine learning competitions.

PDF Abstract

Datasets


Introduced in the Paper:

FER2013

Used in the Paper:

SVHN

Results from the Paper


 Ranked #1 on Facial Expression Recognition on FER2013 (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Facial Expression Recognition FER2013 Residual Masking Network Accuracy 74.14 # 4
Facial Expression Recognition FER2013 Ensemble ResMaskingNet with 6 other CNNs Accuracy 76.82 # 1
Facial Expression Recognition FER2013 Local Learning BOW Accuracy 67.48 # 13

Methods


No methods listed for this paper. Add relevant methods here