Continuous affect prediction in the wild is a very interesting problem and is challenging as continuous prediction involves heavy computation. This paper presents the methodologies and techniques used in our contribution to predict continuous emotion dimensions i.e., valence and arousal in ABAW competition on Aff-Wild2 database. Aff-Wild2 database consists of videos in the wild labelled for valence and arousal at frame level. Our proposed methodology uses fusion of both audio and video features (multi-modal) extracted using state-of-the-art methods. These audio-video features are used to train a sequence-to-sequence model that is based on Gated Recurrent Units (GRU). We show promising results on validation data with simple architecture. The overall valence and arousal of the proposed approach is 0.22 and 0.34, which is better than the competition baseline of 0.14 and 0.24 respectively.
$M^3$T: Multi-Modal Continuous Valence-Arousal Estimation in the Wild
Key Lab of Intelligent Information Processing, Chinese Academy of Sciences (CAS) Institute of Computing Technology, CAS（中国科学院计算技术研究所智能信息处理重点实验室）；School of Computer Science and Technology University of Chinese Academy of Sciences（中国科学院大学计算机科学与技术学院）
Symbolic music generation conditioned on continuous-valued emotions
Institute for Systems and Computer Engineering, Technology and Science (INESC TEC)（系统与计算机工程、技术与科学研究所（INESC TEC））；University of Coimbra（科英布拉大学）；Polytechnic of Porto（波尔图理工学院）
Exploiting Diverse Feature for Multimodal Sentiment Analysis
Hefei University of Technology（合肥工业大学）；Anhui University（安徽大学）；Hefei University of Technology Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥工业大学人工智能研究所、合肥综合性国家科学中心）
