Publications

# denotes equal contribution, * denotes correspondence. Jump to [Preprint], [Survey], [Benchmark], [Conference], [Journal], [Others].

Conference

•   CyIN: Cyclic Informative Latent Space for Bridging Complete and Incomplete Multimodal Learning
     Ronghao Lin, Qiaolin He, Sijie Mai, Ying Zeng, Aolin Xiong, Li Huang, Yap-Peng Tan, Haifeng Hu
     NeurIPS    2025    [paper] [code] 

•   E3RG: Building Explicit Emotion-driven Empathetic Response Generation System with Multimodal Large Language Model
     Ronghao Lin, Shuai Shen, Weipeng Hu, Qiaolin He, Aolin Xiong, Li Huang, Haifeng Hu, Yap-Peng Tan
     ACM MM (Grand Challenge)    2025    [paper] [code] 

•   Multi-source Multimodal Progressive Domain Adaption for Audio-Visual Deception Detection
     Ronghao Lin, Sijie Mai, Ying Zeng, Qiaolin He, Aolin Xiong, Haifeng Hu
     ACM MM (SVC Workshop)    2025    Oral    [paper] [code] 

•   Multimodal Contrastive Learning via Uni-Modal Coding and Cross-Modal Prediction for Multimodal Sentiment Analysis
     Ronghao Lin, Haifeng Hu
     EMNLP (Findings)    2022    [paper]  

•   Diff-LMM: Diffusion Teacher-Guided Spatio-Temporal Perception for Video Large Multimodal Models
     Jisheng Dang, Ligen Chen, Jingze Wu, Ronghao Lin, Bimei Wang, Yun Wang, Liting Wang, Nannan Zhu, Teng Wang
     IJCAI    2025    [paper]  

Journal

•   Adapt and Explore: Multimodal Mixup for Representation Learning
     Ronghao Lin, Haifeng Hu
     ELSEVIER Information Fusion (INFFUS)    2024   [paper] [code] 

•   MissModal: Increasing Robustness to Missing Modality in Multimodal Sentiment Analysis
     Ronghao Lin, Haifeng Hu
     MIT Transactions of the Association for Computational Linguistics (TACL)    2024   [paper] [code] [Presented at EMNLP 2023]

•   Multi-Task Momentum Distillation for Multimodal Sentiment Analysis
     Ronghao Lin, Haifeng Hu
     IEEE Transactions on Affective Computing (TAFFC)    2023   [paper] [code] 

•   Dynamically Shifting Multimodal Representations via Hybrid-Modal Attention for Multimodal Sentiment Analysis
     Ronghao Lin, Haifeng Hu
     IEEE Transactions on Multimedia (TMM)    2023   [paper] [code] 

•   Prompt-guided Transformer and MLLM Interactive Learning for Text-Based Pedestrian Search
     Zefeng Lu, Ronghao Lin, Tan Yap-Peng, Haifeng Hu
     IEEE Transactions on Information Forensics and Security (TIFS)    2025   [paper]  

•   Mind the Inconsistent Semantics in Positive Pairs: Semantic Aligning and Multimodal Contrastive Learning for Text-based Pedestrian Search
     Zefeng Lu, Ronghao Lin, Haifeng Hu
     IEEE Transactions on Intelligent Transportation Systems (TITS)    2024   [paper]  

•   Disentangling Modality and Posture Factors: Memory-Attention and Orthogonal Decomposition for Visible-Infrared Re-Identification
     Zefeng Lu, Ronghao Lin, Haifeng Hu
     IEEE Transactions on Neural Networks and Learning Systems (TNNLS)    2024   [paper]  

•   Tri-Level Modality-Information Disentanglement for Visible-Infrared Person Re-Identification
     Zefeng Lu, Ronghao Lin, Haifeng Hu
     IEEE Transactions on Multimedia (TMM)    2024   [paper]  

•   Mask-Aware Pseudo Label Denoising for Unsupervised Vehicle Re-Identification
     Zefeng Lu, Ronghao Lin, Haifeng Hu
     IEEE Transactions on Intelligent Transportation Systems (TITS)    2023   [paper]  

•   MART: Mask-Aware Reasoning Transformer for Vehicle Re-identification
     Zefeng Lu, Ronghao Lin, Haifeng Hu
     IEEE Transactions on Intelligent Transportation Systems (TITS)    2023   [paper]  

•   Identity-Unrelated Information Decoupling Model for Vehicle Re-Identification
     Zefeng Lu, Ronghao Lin, Haifeng Hu
     IEEE Transactions on Intelligent Transportation Systems (TITS)    2022   [paper]