Computer vision publications
-
Efficient Fine-Grained Classification and Part Localization Using One Compact Network
We propose a novel multi-task deep network architecture that jointly optimizes both localization of parts and fine-grained class labels by learning from training data.
-
Utilizing Semantic Visual Landmarks for Precise Vehicle Navigation
This paper presents a new approach for integrating semantic information for vision-based vehicle navigation.
-
Automated Image Analysis and Classification Tool Based on Computer Vision Deep Learning Technologies
We present a rapid underwater video and automated image analysis tool using computer vision deep learning technologies.
-
Advances in Automated Stock Assessment Based on Computer Vision Deep Learning Technologies
We present a rapid fish assessment method leveraging computer vision deep learning technologies to provide both (1) rapid fish annotation and (2) fish classification with fish counting.
-
BitNet: Bit-Regularized Deep Neural Networks
We present a novel optimization strategy for training neural networks which we call "BitNet". Our key idea is to limit the expressive power of the network by dynamically controlling the…
-
GPU Performance Prediction using Representation Learning
We propose a representation learning approach to address the high level of contention among thousands of parallel threads in GPU activity prediction models.
-
Low Precision Neural Networks using Subband Decomposition
In this paper, we present a unique approach using lower precision weights for more efficient and faster training phase.
-
Sub-Meter Vehicle Navigation Using Efficient Pre-Mapped Visual Landmarks
This paper presents a vehicle navigation system that is capable of achieving sub-meter GPS-denied navigation accuracy in large-scale urban environments, using pre-mapped visual landmarks.
-
Analyzing hyperspectral images into multiple subspaces using Guassian mixture models
I argue that the spectra in a hyperspectral datacube will usually lie in several low dimensional subspaces, and that these subspaces are more easily estimated from the data than the…
-
Extending Semantically Enabled Virtual Environments for Training Assessment
This paper reports the lessons learned from several recent research and development projects, and offers some directions for new studies that build on this work.
-
Pattern of life analysis for diverse data types
SRI has developed a system to automatically analyze the Pattern of Life of ports, routes and vessels from a large collection of AIS data. The PoL of these entities are…
-
Analyzing hyperspectral images into multiple subspaces using Gaussian mixture models
I argue that the spectra in a hyperspectral datacube will usually lie in several low-dimensional subspaces, and that these subspaces are more easily estimated from the data than the endmembers.