57 citations · 70 across the 10 of their papers we have counts for
3 papers · 1 filter
Efficient Labelling of Affective Video Datasets via Few-Shot & Multi-Task Contrastive Learning
Ravikiran Parameshwara, Ibrahim Radwan, Akshay Asthana +3
Whilst deep learning techniques have achieved excellent emotion prediction, they still require large amounts of labelled training data, which are (a) onerous and tedious to compile…
A Weakly Supervised Approach to Emotion-change Prediction and Improved Mood Inference
Soujanya Narayana, Ibrahim Radwan, Ravikiran Parameshwara +4
Whilst a majority of affective computing research focuses on inferring emotions, examining mood or understanding the \textit{mood-emotion interplay} has received significantly less…
Focus on Change: Mood Prediction by Learning Emotion Changes via Spatio-Temporal Attention
Soujanya Narayana, Ramanathan Subramanian, Ibrahim Radwan +1
While emotion and mood interchangeably used, they differ in terms of duration, intensity and attributes. Even as multiple psychology studies examine the mood-emotion relationship,…