Xiatian Zhu

Latest

• Unsupervised Audio-Visual Segmentation with Modality Alignment
• AV-GS: Learning Material and Geometry aware Priors for Novel View Acoustic Synthesis
• DiffSED: Sound Event Detection with Denoising Diffusion
• Sarcasm in Sight and Sound: Benchmarking and Expansion to Improve Multimodal Sarcasm Detection
• Leveraging Foundation Models for Unsupervised Audio-Visual Segmentation