Programe

Monday 22 October 2018, Sapphire Ballroom 1, Lotte Hotel Seoul

Session 0 - Keynote Talk

09:00 - 10:00 Interpersonal Behavior Modeling for Personality, Affect, and Mental States Recognition and Analysis

Chi Chun (Jeremy) Lee (National Tsing-Hua University)

Session 1 - AVEC'18 Challenge Introduction

10:00 - 10:30 AVEC 2018 Workshop and Challenge: Bipolar Disorder and Cross-Cultural Affect Recognition

Fabien Ringeval (Grenoble Alps University), Björn Schuller (University of Augsburg/Imperial College London), Michel Valstar (University of Nottingham), Roddy Cowie (Queen’s University Belfast), Heysem Kaya (Namık Kemal University), Maximilian Schmitt (University of Augsburg), Shahin Amiriparian (University of Augsburg), Nicholas Cummins (University of Augsburg), Denis Lalanne (University of Fribourg), Adrien Michaud (Grenoble Alps University), Elvan Çiftçi (University of Health Sciences - Istanbul), Hüseyin Güleç (University of Health Sciences - Istanbul), Albert Ali Salah (Boğaziçi University/Nagoya University) and Maja Pantic (Imperial College London/University of Twente)

10:30 - 11:00 Coffee break

Session 2 - Bipolar Disorder Sub-challenge

11:00 - 11:20 Bipolar Disorder Recognition with Histogram Features of Arousal and Body Gestures

Le Yang (Northwestern Polytechnical University), Yan Li (Northwestern Polytechnical University), Haifeng Chen (Northwestern Polytechnical University), Dongmei Jiang (Northwestern Polytechnical University), Meshia Cédric Oveneke (Vrije Universiteit Brussel) and Hichem Sahli (Vrije Universiteit Brussel)

11:20 - 11:40 Bipolar Disorder Recognition via Multi-scale Discriminative Audio Temporal Representation

Zhengyin Du (Beihang University), Weixin Li (Beihang University), Di Huang (Beihang University) and Yunhong Wang (Beihang University)

11:40 - 12:00 Multi-modality Hierarchical Recall based on GBDTs for Bipolar Disorder Classification

Xiaofen Xing (South China University of Technology), Bolun Cai (South China University of Technology), Yinhu Zhao (South China University of Technology), Shuzhen Li (South China University of Technology), Zhiwei He (South China University of Technology) and Weiquan Fan (South China University of Technology)

12:00 - 12:20 Automated Screening for Bipolar Disorder from Audio/Visual Modalities

Zafi Sherhan Syed (Cardiff University), Kirill Sidorov (Cardiff University) and David Marshall (Cardiff University)

12:20 - 14:00 Lunch break

Session 3 - Cross-cultural Emotion Sub-challenge

14:00 - 14:20 Speech-based Continuous Emotion Prediction by Learning Perception Responses related to Salient Events: A Study based on Vocal Affect Bursts and Cross-Cultural Affect in AVEC 2018

Kalani Wataraka Gamage (The University of New South Wales), Ting Dange (The University of New South Wales), Vidhyasaharan Sethu (The University of New South Wales), Julien Epps (The University of New South Wales) and Eliathamby Ambikairajah (The University of New South Wales)

14:20 - 14:40 Multimodal Continuous Emotion Recognition with Data Augmentation Using Recurrent Neural Networks

Jian Huang (National Laboratory of Pattern Recognition), Ya Li (National Laboratory of Pattern Recognition), Jianhua Tao (National Laboratory of Pattern Recognition), Zheng Lian (National Laboratory of Pattern Recognition), Zhengqi Wen (National Laboratory of Pattern Recognition) and Minghao Yang (National Laboratory of Pattern Recognition)

14:40 - 15:00 Multi-modal Multi-cultural Dimensional Continues Emotion Recognition in Dyadic Interactions

Jinming Zhao (Renmin University of China), Ruichen Li (Renmin University of China), Shizhe Chen (Renmin University of China) and Qin Jin (Renmin University of China)

Session 4 - Gold-standard Emotion Sub-challenge

15:00 - 15:20 Towards a Better Gold Standard: Denoising and Modelling Continuous Emotion Annotations Based on Feature Agglomeration and Outlier Regularisation

Chen Wang (University of Geneva), Phil Lopes (University of Geneva), Thierry Pun (University of Geneva) and Guillaume Chanel (University of Geneva)

15:20 - 15:40 Fusing Annotations with Majority Vote Triplet Embeddings

Brandon Booth (University of Southern California), Karel Mundnich (University of Southern California) and Shrikanth Narayanan (University of Southern California)

15:40 - 16:00 Coffee break

Session 5 - Deep Learning for Affective Computing

16:00 - 16:20 Deep Learning for Continuous Multiple Time Series Annotations

16:20 - 16:40 Learning an Arousal-Valence Speech Front-End Network using Media Data In-the-Wild for Emotion Recognition

Chih-Chuan Lu (National Tsing-Hua University), Jeng-Lin Li (National Tsing-Hua University) and Chi-Chun Lee (National Tsing-Hua University)

Session 6 - Challenge Results

16:40 - 17:00 AVEC'18 Challenge results