 VEGAS: Towards Visually Explainable and Grounded Artificial Social IntelligenceAAAI Conference on Artificial Intelligence (AAAI), 2025 |
 MuRAR: A Simple and Effective Multimodal Retrieval and Answer Refinement Framework for Multimodal Question AnsweringInternational Conference on Computational Linguistics (COLING), 2024 |
 FedMEKT: Distillation-based Embedding Knowledge Transfer for Multimodal
Federated LearningNeural Networks (Neural Netw.), 2023 |
 Extending Compositional Attention Networks for Social Reasoning in
VideosInterspeech (Interspeech), 2022 |
 Face-to-Face Contrastive Learning for Social Intelligence
Question-AnsweringIEEE International Conference on Automatic Face & Gesture Recognition (FG), 2022 |
 Multimodal Co-learning: Challenges, Applications with Datasets, Recent
Advances and Future DirectionsInformation Fusion (Inf. Fusion), 2021 |
