Author

Qunli Tang

h-index 2 View on Semantic Scholar

We have 1 of 4 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access Jul 2026

Emotion-BIND for multimodal emotion recognition and reasoning.

Empir-BIND is presented, a multimodal framework that integrates ImageBind-based representations with a differentiated positional encoding strategy, termed m-ROPE, and applies 2D RoPE to image representations and 3D RoPE to video representations, supporting multimodal spatial and temporal modeling.

Qunli Tang, Qi Wang, Shouhao Zhang et al. · Scientific Reports · 0 citations