Proceedings of the 2018 on Audio/Visual Emotion Challenge and Workshop

摘要

It is our great pleasure to welcome you to the 8th Audio-Visual Emotion Challenge - AVEC'18, held in conjunction with the ACM Multimedia 2018 in Seoul, Korea. This year's challenge and associated workshop continues to push the boundaries of audio-visual emotion and health recognition towards real-life applications of affective computing. Looking back in the history of AVEC, the first challenge posed the problem of detecting discrete emotion classes on a large set of natural behaviour data. The second AVEC extended this problem to the prediction of continuous valued dimensional affect, which was enlarged further for the third edition to include the prediction of self-reported severity of depression, and enriched annotations for the fourth edition. Physiological signals were then introduced for the prediction of dimensional affect in the fifth AVEC. In the sixth edition, the focus was on depression analysis from human-agent interactions, and on emotion recognition from human behaviours captured 'in-the-wild' for the seventh AVEC. Finally, for this year edition, we proposed cross-cultural affect prediction 'in-the-wild', classification of bipolar disorder, and generation of dimensional labels for continuous emotion recognition. The mission of the AVEC series is to provide a common benchmark test set for multimodal information processing and compare the merits of the approaches under well-defined and strictly comparable conditions. The main underlying motivation is the need to advance emotion and health estimation for multimedia retrieval to a level where behaviours can be reliably sensed in real-life conditions, as this is exactly the type of data that the new generation of affect-oriented multimedia and human-machine/human-robot communication interfaces have to face in the real world. The call for participation attracted 23 submissions from Asia, Europe, Oceania and North America. The programme committee accepted 11 papers in addition to the baseline paper for oral presentation. We hope that these proceedings will serve as a valuable reference for researchers and developers in the area of audio-visual emotion and health sensing.