activity
20242026
collaborators
Showing cs.CLShow all

11 papers · 1 filter

cs.CL2026

Relational graph-driven differential denoising and diffusion attention fusion for multimodal conversation emotion recognition

Ying Liu, Yuntao Shou, Wei Ai +2

In real-world scenarios, audio and video signals are often subject to environmental noise and limited acquisition conditions, resulting in extracted features containing excessive n…

cs.CL2025

Multimodal Large Language Models Meet Multimodal Emotion Recognition and Reasoning: A Survey

Yuntao Shou, Tao Meng, Wei Ai +1

In recent years, large language models (LLMs) have driven major advances in language understanding, marking a significant step toward artificial general intelligence (AGI). With in…

cs.CL2025

SE-GNN: Seed Expanded-Aware Graph Neural Network with Iterative Optimization for Semi-supervised Entity Alignment

Tao Meng, Shuo Shan, Hongen Shao +3

Entity alignment aims to use pre-aligned seed pairs to find other equivalent entities from different knowledge graphs (KGs) and is widely used in graph fusion-related fields. Howev…

cs.CL2025

Dynamic Graph Neural ODE Network for Multi-modal Emotion Recognition in Conversation

Yuntao Shou, Tao Meng, Wei Ai +1

Multimodal emotion recognition in conversation (MERC) refers to identifying and classifying human emotional states by combining data from multiple different modalities (e.g., audio…

cs.CL2024

SE-GCL: An Event-Based Simple and Effective Graph Contrastive Learning for Text Representation

Tao Meng, Wei Ai, Jianbin Li +3

Text representation learning is significant as the cornerstone of natural language processing. In recent years, graph contrastive learning (GCL) has been widely used in text repres…

cs.CL2024

SDR-GNN: Spectral Domain Reconstruction Graph Neural Network for Incomplete Multimodal Learning in Conversational Emotion Recognition

Fangze Fu, Wei Ai, Fan Yang +3

Multimodal Emotion Recognition in Conversations (MERC) aims to classify utterance emotions using textual, auditory, and visual modal features. Most existing MERC methods assume eac…