6 accepted papers
Vision Transformers (ViTs) have achieved remarkable success across various vision tasks, yet their deployment is often hindered by prohibitive computational costs. While structured weight pruning and token compression have emerged as promising solutions, they suffer from prolonged retraining times a…
"Pre-trained on extensive and diverse multi-modal datasets, 2D foundation models excel at addressing 2D tasks with little or no downstream supervision, owing to their robust representations. The emergence of 2D-to-3D distillation frameworks has extended these capabilities to 3D models. However, dist…
Modern robotic systems are required to operate in dense dynamic environments, requiring highly accurate real-time track identification and estimation. For 3D multi-object tracking, recent approaches process a single measurement frame recursively with greedy association and are prone to errors in amb…
Estimating the uncertainty in deep neural network predictions is crucial for many real-world applications. A common approach to model uncertainty is to choose a parametric distribution and fit the data to it using maximum likelihood estimation. The chosen parametric form can be a poor fit to the dat…
We develop a multi-step motion prediction modeling method for dynamic systems over long horizons using deep learning. Building on previous work, we propose a novel hybrid network architecture, by combining deep recurrent neural networks with a quadrotor motion model created using classic system iden…
Dynamic camera cluster (DCC) calibration determines a time-varying set of extrinsic calibration transformations between cameras in a multi-camera cluster, where one or more cameras are mounted on actuated mechanisms. In this paper, we present a novel active vision approach for DCC calibration, which…