Jacob Walker

Learn More
In this paper we present a conceptually simple but surprisingly powerful method for visual prediction which combines the effectiveness of mid-level visual elements with temporal modeling. Our framework can be learned in a completely unsupervised manner from a large collection of videos. However, more importantly, because our approach models the prediction(More)
In a given scene, humans can often easily predict a set of immediate future events that might happen. However, generalized pixellevel anticipation in computer vision systems is difficult because machine learning struggles with the ambiguity inherent in predicting the future. In this paper, we focus on predicting the dense trajectory of pixels in a scene —(More)
Given a scene, what is going to move, and in what direction will it move? Such a question could be considered a non-semantic form of action prediction. In this work, we present a convolutional neural network (CNN) based approach for motion prediction. Given a static image, this CNN predicts the future motion of each and every pixel in the image in terms of(More)
In human robot dialogue, identifying intended referents from human partners’ spatial language is challenging. This is partly due to automated inference of potentially ambiguous underlying reference system (i.e., frame of reference). To improve spatial language understanding, we conducted an empirical study to investigate the prevalence of ambiguities of(More)
We describe an attractor network of binary perceptrons receiving inputs from a retinotopic visual feature layer. Each class is represented by a random subpopulation of the attractor layer, which is turned on in a supervised manner during learning of the feed forward connections. These are discrete three state synapses and are updated based on a simple field(More)
Current approaches in video forecasting attempt to generate videos directly in pixel space using Generative Adversarial Networks (GANs) or Variational Autoencoders (VAEs). However, since these approaches try to model all the structure and scene dynamics at once, in unconstrained settings they often generate uninterpretable results. Our insight is to model(More)
In human robot dialogue, identifying intended referents from human partners’ spatial language is challenging. This is partly due to automated inference of potentially ambiguous underlying reference system (i.e., frame of reference). To improve spatial language understanding, we conducted an empirical study to investigate the prevalence of ambiguities of(More)
OBJECTIVES To describe latent tuberculosis infection (LTBI) testing practices in long-term care facilities (LTCFs). DESIGN Retrospective cohort study. SETTING Three Boston-area LTCFs. PARTICIPANTS Residents admitted between January 1 and December 31, 2011. MEASUREMENTS Resident demographic characteristics, comorbidities, LTCF stay, and LTBI testing(More)
  • 1