2 papers
eess.AS2026
From Signals to Patterns: Non-Invasive Tuberculosis Detection from Cough Audio using Bandit Weighted Hyperbolic Prototypes
Mohd Mujtaba Akhtar, Girish, Sanjam Wadhwa +2
In this study, we focus on cough-based tuberculosis screening (CBTS) and hypothesize that fusing speech/audio foundation representations with spectral descriptors will yield strong…
cs.CV2024
SurgPETL: Parameter-Efficient Image-to-Surgical-Video Transfer Learning for Surgical Phase Recognition
Shu Yang, Zhiyuan Cai, Luyang Luo +3
Capitalizing on image-level pre-trained models for various downstream tasks has recently emerged with promising performance. However, the paradigm of "image pre-training followed b…