lisa_emotiw
lisa_emotiw copied to clipboard
nouiz
Challenge de reco d'émotions sur les visages.
Pierre-Luc et Vincent The tasks included in this ticket are : -Add keypoint data to SFEW's wrapper class -Wrap the Flickr dataset -Wrap the multiPIE dataset -Wrap the BioID dataset...
For Atousa Please create an account Atousa will apply the activity recognition pipeline of Wang et al (state-of-the-art on Hollywood 2) to the problem of emotion recognition. There was a...
Choose a format and associated object class to hold the different speech features (some may be global to the sequence). Coordinate with +Pascal Vincent on this (project-wide data organization).
Roland will work with his student on his approach to activity recognition, to compare with Atousa's implementation of emotion recognition.
Select and code up advanced feature extraction algorithms that may be relevant to the task of emotion classification (look at what the previous papers on the subject have reported).
Setup and train deep convolutional network for speech-to-emotion with input window over the features extracted by +Nicolas and max-pooling on the output sequence. Train it first on the challenge data,...
Setup and train deep MLP for speech-to-emotion with input window over the features extracted by +Nicolas and max-pooling on the output sequence. Train it first on the challenge data, then...
Code and train a bidirectional recurrent net for speech-to-emotion mapping the feature sequence to a single probabilistic output through a final max-pooling (or other) aggregation. Try pooling the top hidden...
Get other relevant datasets which could help training an emotion classifier from speech, including music+mood data, unlabeled speech with emotional content, and most importantly, emotion+speech data such as in http://emotion-research.net/databases...
(I put the label "Data Organization" as "Performance Evaluation" is not there, not sure if it is on purpose).
