3 papers
cs.CV2026
EmoTrans: A Benchmark for Understanding, Reasoning, and Predicting Emotion Transitions in Multimodal LLMs
He Hu, Tengjin Weng, Zebang Cheng +5
Recent multimodal large language models (MLLMs) have shown strong capabilities in perception, reasoning, and generation, and are increasingly used in applications such as social ro…
cs.SD2025
Heterogeneous bimodal attention fusion for speech emotion recognition
Jiachen Luo, Huy Phan, Lin Wang +1
Multi-modal emotion recognition in conversations is a challenging problem due to the complex and complementary interactions between different modalities. Audio and textual cues are…
cs.SD2025
Bimodal Connection Attention Fusion for Speech Emotion Recognition
Jiachen Luo, Huy Phan, Lin Wang +1
Multi-modal emotion recognition is challenging due to the difficulty of extracting features that capture subtle emotional differences. Understanding multi-modal interactions and co…