Low-Voltage Energy Efficient Neural Inference by Leveraging Fault Detection Techniques
Operating at reduced voltages offers substantial energy efficiency improvement but at the expense of increasing the probability of computational errors due to […]
Cross-modal Self-Supervised Learning for Lip Reading
The goal of this work is to learn discriminative visual representations for lip reading without access to manual text annotation. Recent advances […]
Self-supervised pain intensity estimation from facial videos via statistical spatiotemporal distillation
Recently, automatic pain assessment technology, in particular automatically detecting pain from facial expressions, has been developed to improve the quality of pain […]
Leveraging Unlabeled Whole-Slide-Images for Mitosis Detection
Mitosis count is an important biomarker for prognosis of various cancers. At present, pathologists typically perform manual counting on a few selected […]