Multimodal Emotion Recognition with Modality-Pairwise Unsupervised Contrastive Loss

by   Riccardo Franceschini, et al.
Università di Trento

Emotion recognition is involved in several real-world applications. With an increase in available modalities, automatic understanding of emotions is being performed more accurately. The success in Multimodal Emotion Recognition (MER), primarily relies on the supervised learning paradigm. However, data annotation is expensive, time-consuming, and as emotion expression and perception depends on several factors (e.g., age, gender, culture) obtaining labels with a high reliability is hard. Motivated by these, we focus on unsupervised feature learning for MER. We consider discrete emotions, and as modalities text, audio and vision are used. Our method, as being based on contrastive loss between pairwise modalities, is the first attempt in MER literature. Our end-to-end feature learning approach has several differences (and advantages) compared to existing MER methods: i) it is unsupervised, so the learning is lack of data labelling cost; ii) it does not require data spatial augmentation, modality alignment, large number of batch size or epochs; iii) it applies data fusion only at inference; and iv) it does not require backbones pre-trained on emotion recognition task. The experiments on benchmark datasets show that our method outperforms several baseline approaches and unsupervised learning methods applied in MER. Particularly, it even surpasses a few supervised MER state-of-the-art.


An Empirical Study and Improvement for Speech Emotion Recognition

Multimodal speech emotion recognition aims to detect speakers' emotions ...

Temporal aggregation of audio-visual modalities for emotion recognition

Emotion recognition has a pivotal role in affective computing and in hum...

UniMSE: Towards Unified Multimodal Sentiment Analysis and Emotion Recognition

Multimodal sentiment analysis (MSA) and emotion recognition in conversat...

MEmoBERT: Pre-training Model with Prompt-based Learning for Multimodal Emotion Recognition

Multimodal emotion recognition study is hindered by the lack of labelled...

Deep Residual Local Feature Learning for Speech Emotion Recognition

Speech Emotion Recognition (SER) is becoming a key role in global busine...

Unsupervised Extractive Summarization of Emotion Triggers

Understanding what leads to emotions during large-scale crises is import...

Supervised Prototypical Contrastive Learning for Emotion Recognition in Conversation

Capturing emotions within a conversation plays an essential role in mode...

Please sign up or login with your details

Forgot password? Click here to reset