-
Chapter and Conference Paper
Benchmarking Object Detection Models with Mummy Nuts Datasets
Agriculture presents challenges in automation, especially so in vision systems. Varying lighting conditions, sporadic diversity, and large amounts of noise create difficulty in detecting target objects. Our Mu...
-
Chapter and Conference Paper
DistPro: Searching a Fast Knowledge Distillation Process via Meta Optimization
Recent Knowledge distillation (KD) studies show that different manually designed schemes impact the learned results significantly. Yet, in KD, automatically searching an optimal distillation scheme has not yet...
-
Chapter and Conference Paper
Gated Transfer Network for Transfer Learning
Deep neural networks have led to a series of breakthroughs in computer vision given sufficient annotated training datasets. For novel tasks with limited labeled data, the prevalent approach is to transfer the ...
-
Chapter and Conference Paper
Random Temporal Skip** for Multirate Video Analysis
Current state-of-the-art approaches to video understanding adopt temporal jittering to simulate analyzing the video at varying frame rates. However, this does not work well for multirate videos, in which actio...
-
Chapter and Conference Paper
Hidden Two-Stream Convolutional Networks for Action Recognition
Analyzing videos of human actions involves understanding the temporal relationships among video frames
-
Chapter
Georeferenced Social Multimedia as Volunteered Geographic Information
We argue that georeferenced social multimedia is really a form of volunteered geographic information. For example, community-contributed images and videos available at websites such as Flickr often indicate th...
-
Chapter and Conference Paper
Depth2Action: Exploring Embedded Depth for Large-Scale Action Recognition
This paper performs the first investigation into depth for large-scale human action recognition in video where the depth cues are estimated from the videos themselves. We develop a new framework called depth2acti...
-
Article
Land cover classification using geo-referenced photos
We investigate publicly available geo-referenced photo collections for land cover classification. Map** land cover is a fundamental task in the geographic sciences and is typically done using remote sensing ...
-
Article
Open AccessValidating clustering of molecular dynamics simulations using polymer models
Molecular dynamics (MD) simulation is a powerful technique for sampling the meta-stable and transitional conformations of proteins and other biomolecules. Computational data clustering has emerged as a useful,...
-
Chapter and Conference Paper
Estimating Atmospheric Visibility Using General-Purpose Cameras
There is a growing interest in using general-purpose cameras to monitor a variety of physical phenomenon. In particular, a number of visibility camera networks have recently been deployed to complement traditi...
-
Chapter and Conference Paper
Geographic Image Retrieval Using Interest Point Descriptors
We investigate image retrieval using interest point descriptors. New geographic information systems such as Google Earth and Microsoft Virtual Earth are providing increased access to remote sensed imagery. Con...
