High frame rate video capture and image processing is an important capability for applications in defense and homeland security where incoming missiles must be detected in very sh...
In this paper, we propose a framework for predicting the performance of a vision algorithm given the input image or video so as to maximize the algorithm's ability to provide...
We present a method to detect the regions of interests in moving camera views of dynamic scenes with multiple moving objects. We start by extracting a global motion tendency that ...
In this paper, we present a systematic framework for recognizing realistic actions from videos “in the wild.” Such unconstrained videos are abundant in personal collections as...
In deformable model segmentation, the geometric training process plays a crucial role in providing shape statistical priors and appearance statistics that are used as likelihoods. ...
Qiong Han, Derek Merck, Josh Levy, Christina Villa...