DeepAI AI Chat
Log In Sign Up

Improving Multimodal Accuracy Through Modality Pre-training and Attention

by   Aya Abdelsalam Ismail, et al.

Training a multimodal network is challenging and it requires complex architectures to achieve reasonable performance. We show that one reason for this phenomena is the difference between the convergence rate of various modalities. We address this by pre-training modality-specific sub-networks in multimodal architectures independently before end-to-end training of the entire network. Furthermore, we show that the addition of an attention mechanism between sub-networks after pre-training helps identify the most important modality during ambiguous scenarios boosting the performance. We demonstrate that by performing these two tricks a simple network can achieve similar performance to a complicated architecture that is significantly more expensive to train on multiple tasks including sentiment analysis, emotion recognition, and speaker trait recognition.


page 1

page 2

page 3

page 4


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

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

Vision-Language Pre-Training for Multimodal Aspect-Based Sentiment Analysis

As an important task in sentiment analysis, Multimodal Aspect-Based Sent...

Modality-based Factorization for Multimodal Fusion

We propose a multimodal data fusion method by obtaining a M+1 dimensiona...

Attentive Modality Hopping Mechanism for Speech Emotion Recognition

In this work, we explore the impact of visual modality in addition to sp...

Multi-attention Recurrent Network for Human Communication Comprehension

Human face-to-face communication is a complex multimodal signal. We use ...

Training Transitive and Commutative Multimodal Transformers with LoReTTa

Collecting a multimodal dataset with two paired modalities A and B or B ...

Rethinking Vision Transformer and Masked Autoencoder in Multimodal Face Anti-Spoofing

Recently, vision transformer (ViT) based multimodal learning methods hav...