Abstract: Generalized zero-shot learning (GZSL) requires that models are able to recognize classes they were trained on, and new classes they haven't seen before. Feature-generation approaches are ...

Demonstrating robust continual depth completion: performance over the course of training in the challenging mixed setting of adapting from indoor to outdoor environments. Existing depth completion ...

Abstract: Multimodal survival methods combining gigapixel histology whole-slide images (WSIs) and transcriptomic profiles are particularly promising for patient prognostication and stratification.

Abstract: Autonomous driving vehicles (ADVs) are the next significant evolution in transportation systems. Using machine learning techniques supported by strong processing units and sensors, the ...