• Publications
  • Influence
Parallel Separable 3D Convolution for Video and Volumetric Data Understanding
TLDR
In this paper, we propose a novel convolution block, Parallel Separable 3D Convolution (PmSCn), which applies m parallel streams of n 2D and one 1D convolution layers along different dimensions. Expand
  • 9
  • 2
  • PDF
ICON: An interactive approach to train deep neural networks for segmentation of neuronal structures
TLDR
We present an interactive approach to train a deep neural network pixel classifier for the segmentation of neuronal structures. Expand
  • 5
  • 1
  • PDF
Scalable Interactive Visualization for Connectomics
TLDR
We present BUTTERFLY middleware, a scalable platform that can handle massive data for interactive visualization in connectomics. Expand
  • 15
  • PDF
SPARTA : Fast global planning of collision-avoiding robot trajectories
We present an algorithm for obtaining collision-avoiding robot trajectories we call SPARTA (SPline-based ADMM for Robot Trajectory Avoidance). We break the problem of solving for collision-avoidingExpand
  • 2
  • PDF
An Interactive Deep Learning Toolkit for Automatic Segmentation of Images
Image Segmentation, Neuron Segmentation, Interactive Segmentation, Deep Neural Networks, Multilayer Perceptron, Deep Learning
Consistent Recurrent Neural Networks for 3D Neuron Segmentation
TLDR
We present a recurrent network for 3D reconstruction of neurons that sequentially generates binary masks for every object in an image with spatio-temporal consistency. Expand