Learning where to Attend with Deep Architectures for Image Tracking

Details Learning where to Attend with Deep Architectures for Image Tracking Learning where to Attend with Deep Architectures for Image Tracking

2011-09-16

arxiv.org/abs/1109.3737v1

Computer Science

Artificial Intelligence

Scientific paper

We discuss an attentional model for simultaneous object tracking and recognition that is driven by gaze data. Motivated by theories of perception, the model consists of two interacting pathways: identity and control, intended to mirror the what and where pathways in neuroscience models. The identity pathway models object appearance and performs classification using deep (factored)-Restricted Boltzmann Machines. At each point in time the observations consist of foveated images, with decaying resolution toward the periphery of the gaze. The control pathway models the location, orientation, scale and speed of the attended object. The posterior distribution of these states is estimated with particle filtering. Deeper in the control pathway, we encounter an attentional mechanism that learns to select gazes so as to minimize tracking uncertainty. Unlike in our previous work, we introduce gaze selection strategies which operate in the presence of partial information and on a continuous action space. We show that a straightforward extension of the existing approach to the partial information setting results in poor performance, and we propose an alternative method based on modeling the reward surface as a Gaussian Process. This approach gives good performance in the presence of partial information and allows us to expand the action space from a small, discrete set of fixation points to a continuous domain.

Affiliated with

Also associated with

No associations

Rating

Learning where to Attend with Deep Architectures for Image Tracking does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Learning where to Attend with Deep Architectures for Image Tracking, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Learning where to Attend with Deep Architectures for Image Tracking will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-142186