1 code implementation • 1 Aug 2016 • Varun K. Nagaraja, Vlad I. Morariu, Larry S. Davis
Our approach uses an LSTM to learn the probability of a referring expression, with input features from a region and a context region.
no code implementations • 24 Nov 2015 • Varun K. Nagaraja, Vlad I. Morariu, Larry S. Davis
However, we can use structure in the scene to search for objects without processing the entire image.