• Home
  • Search
  • A novel adaptive lightweight multimodal efficient feature inference network ALME-FIN for EEG emotion recognition.
  • Cite Icon2
  • https://doi.org/10.1007/s11571-024-10186-xCopy DOI Icon

A novel adaptive lightweight multimodal efficient feature inference network ALME-FIN for EEG emotion recognition.

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Enhancing the accuracy of emotion recognition models through multimodal learning is a common approach. However, challenges such as insufficient modal feature learning in multimodal inference and scarcity of sample data continue to pose obstacles that need to be overcome. Therefore, we propose a novel adaptive lightweight multimodal efficient feature inference network (ALME-FIN). We introduce a time-domain lightweight adaptive network (TDLAN) and a two-dimensional dynamic focusing network (TDDFN) for multimodal feature learning. The TDLAN incorporates the denoising process as an integral part of network training, achieving adaptive denoising for each sample through the continuous optimization of the trainable filtering threshold. Simultaneously, it incorporates an interactive convolutional sampling module, enabling lightweight multi-scale feature extraction in the time domain. TDDFN effectively extracts core image features while filtering out redundancies. During the training process, the Multi-network dynamic gradient adjustment framework (MDGAF) dynamically monitors the feature learning efficacy across different modalities. It timely adjusts the training gradients of networks to allocate additional optimization time for under-optimized modalities, thereby maximizing the utilization of multimodal feature information. Moreover, the introduction of a Multi-class relationship interaction module prior to the classifier aids the model in clearly understanding the relationships among different category samples. This approach enables the model to achieve relatively accurate emotion recognition even in scenarios of limited sample availability. Compared to existing multimodal learning techniques, ALME-FIN exhibits a more efficient multimodal feature inference method that can achieve satisfactory emotional recognition performance even with a limited number of samples.

Similar Papers
  • Research Article

Multimodal emotion recognition via adaptive high-order transforme network.

  • Oct 27, 2025
  • PloS one
  • Yuanyuan Lu +1
  • Research Article

Multimodal emotion recognition via adaptive high-order transforme network

  • Oct 27, 2025
  • PLOS One
  • Yuanyuan Lu +4
  • PDF
  • Research Article
  • Citations8

Hierarchical Attention-Based Multimodal Fusion Network for Video Emotion Recognition.

  • Jan 01, 2021
  • Computational Intelligence and Neuroscience
  • Xiaodong Liu +2
  • Conference Article
  • Citations5

ER-MRL: Emotion Recognition based on Multimodal Representation Learning

  • Oct 14, 2022
  • Xiaoding Guo +6
  • Research Article

Research on Short Video Data Analysis Based on Multimodal Features

  • Jun 20, 2025
  • Scientific Journal of Technology
  • Yue Xie
  • Research Article

AMB-DSGDN: Adaptive modality-balanced dynamic semantic graph differential network for multimodal emotion recognition

  • Jul 01, 2026
  • Expert Systems with Applications
  • Yunsheng Wang +5
  • Research Article
  • Citations57

Adaptive fusion network for RGB-D salient object detection

  • Dec 15, 2022
  • Neurocomputing
  • Tianyou Chen +4
  • Research Article

KA-MIN: Knowledge-Aware Multimodal Interaction Network for Emotion Recognition in Conversation

  • Aug 01, 2025
  • IEEE Transactions on Circuits and Systems for Video Technology
  • Minjie Ren +5
  • Research Article
  • Citations198

Multimodal Representation Learning for Recommendation in Internet of Things

  • Dec 01, 2019
  • IEEE Internet of Things Journal
  • Zhenhua Huang +4
  • Research Article
  • Citations6

Image annotation in social networks using graph and multimodal deep learning features

  • Jan 08, 2021
  • Multimedia Tools and Applications
  • Mohamed Yassine Landolsi +2
  • Research Article

Research on Emotion Recognition Algorithm of Piano Music Based on Multimodal Learning

  • Dec 06, 2024
  • Advances in Computer and Engineering Technology Research
  • Qiaolin Yu +1
  • Research Article
  • Citations1

Novel Approach for Decoding Olfactory Receptors Interactions With Molecules Based on Multimodal Feature and Deep Learning Network.

  • Jan 01, 2025
  • IEEE transactions on neural networks and learning systems
  • Fei Wang +6
  • Research Article
  • Citations3

MM-HiFuse: multi-modal multi-task hierarchical feature fusion for esophagus cancer staging and differentiation classification

  • Jan 01, 2025
  • Complex & Intelligent Systems
  • Xiangzuo Huo +6
  • Research Article
  • Citations79

SMIN: Semi-Supervised Multi-Modal Interaction Network for Conversational Emotion Recognition

  • Jul 01, 2023
  • IEEE Transactions on Affective Computing
  • Zheng Lian +2
  • Research Article
  • Citations64

Self-Distillation Feature Learning Network for Optical and SAR Image Registration

  • Jan 01, 2022
  • IEEE Transactions on Geoscience and Remote Sensing
  • Dou Quan +7
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.