GCNet: Graph completion network for incomplete multimodal learning in conversation

Z Lian, L Chen, L Sun, B Liu… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Conversations have become a critical data format on social media platforms. Understanding
conversation from emotion, content and other aspects also attracts increasing attention from …

Understanding multimodal contrastive learning and incorporating unpaired data

R Nakada, HI Gulluk, Z Deng, W Ji… - International …, 2023 - proceedings.mlr.press
Abstract Language-supervised vision models have recently attracted great attention in
computer vision. A common approach to build such models is to use contrastive learning on …

Data augmentation for audio-visual emotion recognition with an efficient multimodal conditional GAN

F Ma, Y Li, S Ni, SL Huang, L Zhang - Applied Sciences, 2022 - mdpi.com
Audio-visual emotion recognition is the research of identifying human emotional states by
combining the audio modality and the visual modality simultaneously, which plays an …

Robust audiovisual emotion recognition: Aligning modalities, capturing temporal information, and handling missing features

L Goncalves, C Busso - IEEE Transactions on Affective …, 2022 - ieeexplore.ieee.org
Emotion recognition using audiovisual features is a challenging task for human-machine
interaction systems. Under ideal conditions (perfect illumination, clean speech signals, and …

SDR-GNN: Spectral Domain Reconstruction Graph Neural Network for incomplete multimodal learning in conversational emotion recognition

F Fu, W Ai, F Yang, Y Shou, T Meng, K Li - Knowledge-Based Systems, 2025 - Elsevier
Abstract Multimodal Emotion Recognition in Conversations (MERC) aims to classify
utterance emotions using textual, auditory, and visual modal features. Most existing MERC …

A novel transformer autoencoder for multi-modal emotion recognition with incomplete data

C Cheng, W Liu, Z Fan, L Feng, Z Jia - Neural Networks, 2024 - Elsevier
Multi-modal signals have become essential data for emotion recognition since they can
represent emotions more comprehensively. However, in real-world environments, it is often …

Multiplex graph aggregation and feature refinement for unsupervised incomplete multimodal emotion recognition

Y Deng, J Bian, S Wu, J Lai, X **e - Information Fusion, 2025 - Elsevier
Abstract Multimodal Emotion Recognition (MER) involves integrating information of various
modalities, including audio, visual, text and physiological signals, to comprehensively grasp …

Alignment-enhanced interactive fusion model for complete and incomplete multimodal hand gesture recognition

S Duan, L Wu, A Liu, X Chen - IEEE Transactions on Neural …, 2023 - ieeexplore.ieee.org
Hand gesture recognition (HGR) based on surface electromyogram (sEMG) and
Accelerometer (ACC) signals is increasingly attractive where fusion strategies are crucial for …

Deep multimodal learning with missing modality: A survey

R Wu, H Wang, HT Chen, G Carneiro - arxiv preprint arxiv:2409.07825, 2024 - arxiv.org
During multimodal model training and testing, certain data modalities may be absent due to
sensor limitations, cost constraints, privacy concerns, or data loss, negatively affecting …

Leveraging Knowledge of Modality Experts for Incomplete Multimodal Learning

W Xu, H Jiang, X Liang - Proceedings of the 32nd ACM International …, 2024 - dl.acm.org
Multimodal Emotion Recognition (MER) may encounter incomplete multimodal scenarios
caused by sensor damage or privacy protection in practical applications. Existing incomplete …