4 papers
PGE-SAM: Prompt-Guided Feature Enhancement for Interactive Segmentation under Degradation
Tuan-Duc Nguyen, Anh-Tuan Mai, Duc-Trong Le
Segment Anything Model (SAM) has revolutionized promptable image segmentation with strong zero-shot generalization. However, its performance degrades substantially under real-world…
Divide and Refine: Enhancing Multimodal Representation and Explainability for Emotion Recognition in Conversation
Anh-Tuan Mai, Cam-Van Thi Nguyen, Duc-Trong Le
Multimodal emotion recognition in conversation (MERC) requires representations that effectively integrate signals from multiple modalities. These signals include modality-specific…
Ada2I: Enhancing Modality Balance for Multimodal Conversational Emotion Recognition
Cam-Van Thi Nguyen, The-Son Le, Anh-Tuan Mai +1
Multimodal Emotion Recognition in Conversations (ERC) is a typical multimodal learning task in exploiting various data modalities concurrently. Prior studies on effective multimoda…
Conversation Understanding using Relational Temporal Graph Neural Networks with Auxiliary Cross-Modality Interaction
Cam-Van Thi Nguyen, Anh-Tuan Mai, The-Son Le +2
Emotion recognition is a crucial task for human conversation understanding. It becomes more challenging with the notion of multimodal data, e.g., language, voice, and facial expres…