Learn More
Referring expressions usually describe an object using properties of the object and relationships of the object with other objects. We propose a technique that integrates context between objects to understand referring expressions. Our approach uses an LSTM to learn the probability of a referring expression, with input features from a region and a context(More)
To identify the location of objects of a particular class, a passive computer vision system generally processes all the regions in an image to finally output few regions. However , we can use structure in the scene to search for objects without processing the entire image. We propose a search technique that sequentially processes image regions such that the(More)
We propose a supervised feature selection technique called the Optimal Loadings, that is based on applying the theory of Optimal Experiment Design (OED) to Partial Least Squares (PLS) regression. We apply the OED criterions to PLS with the goal of selecting an optimal feature subset that minimizes the variance of the regression model and hence minimize its(More)
Discovering music is a process that can be facilitated by many different approaches, depending on the music style and even personal preferences of the listener/researcher of music. The common ground for all approaches is to explore an artist’s work as discographies and to detect collaborations between musicians. In this paper, we present MusicDigger as a(More)
Before deriving the score functions, we first formulate the MAP inference problem in binary Markov networks as an Integer Linear Program (ILP) following the work of Globerson and Jaakkola [1]. The integer variables in the ILP are then relaxed to continuous values giving us a relaxed linear program. We then obtain the dual of this relaxed linear program and(More)
High level semantic analysis typically involves constructing a Markov network over detections from low level detectors to encode context and model relationships between them. In complex higher order networks (e.g. Markov Logic Networks), each detection can be part of many factors and the network size grows rapidly as a function of the number of detections.(More)
  • 1