Many human action recognition tasks involve data that can be factorized into multiple views such as body postures and hand shapes. These views often interact with each other over ...
We introduce two novel methods to improve the performance of wide area video surveillance applications by using scene features. First, we evaluate the drift in intrinsic and extri...
Top-down visual saliency facilities object localization by providing a discriminative representation of target objects and a probability map for reducing the search space. In this...
We propose a nonparametric framework based on the beta process for discovering temporal patterns within a heterogenous video collection. Starting from quantized local motion descr...
This paper investigates the role that nonlinear camera response functions (CRFs) have on image deblurring. In particular, we show how nonlinear CRFs can cause a spatially invarian...
Sunyeong Kim, Yu-Wing Tai, Seon Joo Kim, Michael S...