In-Memory Hardware-Software Co-design for Image Processing

Dynamic Voltage Scaling of Image Sensors towards Low-Power loT Vision

Neural Volumetric Reconstruction for Coherent Synthetic Aperture Sonar

Road Traffic Scene Reconstruction from Aerial Video

Improving Shape Awareness and Interpretability in Deep Networks

Polynomial Implicit Neural Representations for Large Diverse Datasets

Implementing Improved Diversity Using Adversarially Learned Transformations for Domain Generalization

Self-Supervised Technique for Training Vision Transformers

Regularization Technique for Training Vision Transformers

Hand-Directed System for Identifying Activities