self-supervised models

4 papers

• $\texttt{AVROBUSTBENCH}$: Benchmarking the Robustness of Audio-Visual Recognition Models at Test-Time
• Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations
• RESPIN-S1.0: A read speech corpus of 10000+ hours in dialects of nine Indian Languages
• Training-free Detection of AI-generated images via Cropping Robustness