End2You -- The Imperial Toolkit for Multimodal Profiling by End-to-End Learning

TL;DR

End2You is an open-source Python toolkit enabling end-to-end deep learning for multimodal profiling, supporting raw data inputs and providing comparable results to state-of-the-art methods without manual feature extraction.

Contribution

It introduces the first generic toolkit for end-to-end multimodal profiling, simplifying the process by learning directly from raw data across multiple modalities.

Findings

Achieves comparable results to state-of-the-art methods

Supports raw audio, visual, physiological data

Facilitates end-to-end learning without manual feature engineering

Abstract

We introduce End2You -- the Imperial College London toolkit for multimodal profiling by end-to-end deep learning. End2You is an open-source toolkit implemented in Python and is based on Tensorflow. It provides capabilities to train and evaluate models in an end-to-end manner, i.e., using raw input. It supports input from raw audio, visual, physiological or other types of information or combination of those, and the output can be of an arbitrary representation, for either classification or regression tasks. To our knowledge, this is the first toolkit that provides generic end-to-end learning for profiling capabilities in either unimodal or multimodal cases. To test our toolkit, we utilise the RECOLA database as was used in the AVEC 2016 challenge. Experimental results indicate that End2You can provide comparable results to state-of-the-art methods despite no need of expert-alike feature representations, but self-learning these from the data "end to end".