# A Weakly Supervised Approach to Emotion-change Prediction and Improved Mood Inference

arXiv: https://arxiv.org/abs/2306.06979 · HTML: https://mlsanity.com/paper/2306.06979/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 46 references that are in the map.
- First posted on arXiv 12 Jun 2023.

## Builds on (most cited first, 8 of 8)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild](https://mlsanity.com/paper/1708.03985/) (2017)
- [Expression, Affect, Action Unit Recognition: Aff-Wild2, Multi-Task Learning and ArcFace](https://mlsanity.com/paper/1910.04855/) (2019)
- [Exploring Emotion Features and Fusion Strategies for Audio-Video Emotion Recognition](https://mlsanity.com/paper/2012.13912/) (2020)
- [Speech Emotion Recognition via Contrastive Loss under Siamese Networks](https://mlsanity.com/paper/1910.11174/) (2019)
- [Affect Recognition in Ads with Application to Computational Advertising](https://mlsanity.com/paper/1709.01683/) (2017)
- [Gender and Emotion Recognition with Implicit User Signals](https://mlsanity.com/paper/1708.08735/) (2017)
- [To Improve Is to Change: Towards Improving Mood Prediction by Learning Changes in Emotion](https://mlsanity.com/paper/2210.00719/) (2022)

## Built on by (most cited first, 1 of 1)

- [Efficient Labelling of Affective Video Datasets via Few-Shot & Multi-Task Contrastive Learning](https://mlsanity.com/paper/2308.02173/) (2023)

## Abstract (arXiv)

Whilst a majority of affective computing research focuses on inferring emotions, examining mood or understanding the textitmood-emotion interplay has received significantly less attention. Building on prior work, we (a) deduce and incorporate emotion-change (Delta) information for inferring mood, without resorting to annotated labels, and (b) attempt mood prediction for long duration video clips, in alignment with the characterisation of mood. We generate the emotion-change (Delta) labels via metric learning from a pre-trained Siamese Network, and use these in addition to mood labels for mood classification. Experiments evaluating textitunimodal (training only using mood labels) vs textitmultimodal (training using mood plus Delta labels) models show that mood prediction benefits from the incorporation of emotion-change information, emphasising the importance of modelling the mood-emotion interplay for effective mood inference.