DDSE: A Decoupled Dual-Stream Enhanced Framework for Multimodal Sentiment Analysis with Text-Centric SSM

Official code implementation of LLM-Guided Semantic Relational Reasoning for Multimodal Intent Recognition (EMNLP 2025).

Implementation of tensor decompositions in Scala

[Findings of ACL 2024]Optimal Transport Guided Correlation Assignment for Multimodal Entity Linking

[CVPR'25] EMOE: Modality-Specific Enhanced Dynamic Emotion Experts

[CVPR 2025] This is the official implementation of "Seek Common Ground While Reserving Differences: Semi-supervised Image-Text Sentiment Recognition".

Neurips 2024

[AAAI'25] DLF: Disentangled-Language-Focused Multimodal Sentiment Analysis

[ICLR2025] Enhancing Cognition and Explainability of Multimodal Foundation Models with Self-Synthesized Data

H-MBA: Hierarchical MamBa Adaptation for Multi-Modal Video Understanding in Autonomous Driving

[ICCV 2023] The official implementation of "Multimodal Optimal Transport-based Co-Attention Transformer with Global Structure Consistency for Survival Prediction".

[ICASSP 2025] Official PyTorch code for training and inference pipeline for DepMamba: Progressive Fusion Mamba for Multimodal Depression Detection

[ACL 2024 Main] Official PyTorch implementation of the paper "Multimodal Prompt Learning with Missing Modalities for Sentiment Analysis and Emotion Recognition"

Codebase for EMNLP 2024 Findings Paper "Knowledge-Guided Dynamic Modality Attention Fusion Framework for Multimodal Sentiment Analysis"

[Information Fusion 2024] HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion Recognition

Towards Robust Multimodal Sentiment Analysis with Incomplete Data

Efficient Multimodal Transformer with Dual-Level Feature Restoration for Robust Multimodal Sentiment Analysis (TAC 2023)

UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery, ISPRS. Also, including other vision transformers and CNNs for satellite, aerial image …

[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

A simple and efficient Mamba implementation in pure PyTorch and MLX.

Source code of BI-Mamba for cardiovascular disease detection from two-view chest X-rays

Source code for the paper "Modality-collaborative Transformer with Hybrid Feature Reconstruction for Robust Emotion Recognition".

Official Code of Diff-IF: Multi-modality image fusion via diffusion model with fusion knowledge prior (Information Fusion 2024)

A collection of datasets for the purpose of emotion recognition/detection in speech.

The code for the paper "ECR-Chain: Advancing Generative Language Models to Better Emotion Cause Reasoners through Reasoning Chains" (IJCAI-2024).