We propose a deep convolutional neural network for 3D human pose and camera estimation from monocular images that learns from 2D joint annotations. The proposed network follows the typical architecture, but contains an additional output layer which projects predicted 3D joints onto 2D, and enforces constraints on body part lengths in 3D. We further enforce pose constraints using an independently trained network that learns a prior distribution over 3D poses. We evaluate our approach on several benchmark datasets and compare against state-of-the-art approaches for 3D human pose estimation, achieving comparable performance. Additionally, we show that our approach significantly outperforms other methods in cases where 3D ground truth data is unavailable, and that our network exhibits good generalization properties.

We present a Bayesian framework for estimating 3D human pose and camera from a single RGB image. We develop a generative model where a 3D pose is rendered onto an image (via the camera), which then generates a detection probability map for each body part. We represent a human pose with a set of 3D cylinders in space, one for each body part, and we place kinematic and self-intersection priors on the model. Importantly, we use a graphics engine (e.g., OpenGL) to render the pose, and use its built-in capabilities for color blending to efficiently compute the likelihood of the model given the observed probability maps, which are obtained by running a convolutional neural network classifier on a test image. We explore the space of 3D poses and camera configurations via the Hybrid Monte Carlo algorithm, with sampling moves designed specifically for this problem. We train the parameters of our prior and likelihood distributions using annotated poses from the CMU mocap database, and test our algorithm on two benchmark datasets, where we compare performance against state-of-the-art methods. Additionally, we demonstrate the flexibility of our framework by incorporating a likelihood function for depth images and showing the associated performance gains.

We consider linear dynamical systems, particularly coupled linear oscillators, where the parameters represent meaningful values in a domain theory and thus learning what affects them contributes to explanation. Rather than allow perturbations of latent states, we assume that temporal variation beyond noise is explained by parameter drift, and variation across coupled systems is a function of moderating variables. This change of focus reduces opportunities for efficient inference, and we propose sampling procedures to learn and fit the models. We test our approach on a real dataset of physiological measures of heterosexual couples engaged in a conversation about a potentially emotional topic, with body mass index (BMI) being considered as a moderator. We evaluate several models on their ability to predict future conversation dynamics (the last 20% of the data for each test couple), with shared parameters being learned using held out data. As proof of concept, we validate the hypothesis that BMI affects the conversation dynamic in the experimentally chosen topic.

We develop a Bayesian modeling approach for tracking people in 3D from monocular video with unknown cameras. Modeling in 3D provides natural explanations for occlusions and smoothness discontinuities that result from projection, and allows priors on velocity and smoothness to be grounded in physical quantities: meters and seconds vs. pixels and frames. We pose the problem in the context of data association, in which observations are assigned to tracks. A correct application of Bayesian inference to multi-target tracking must address the fact that the model's dimension changes as tracks are added or removed, and thus, posterior densities of different hypotheses are not comparable. We address this by marginalizing out the trajectory parameters so the resulting posterior over data associations has constant dimension. This is made tractable by using (a) Gaussian process priors for smooth trajectories and (b) approximately Gaussian likelihood functions. Our approach provides a principled method for incorporating multiple sources of evidence, we present results using both optical flow and object detector outputs. Results are comparable to recent work on 3D tracking and, unlike others, our method requires no pre-calibrated cameras.

We present a general model for tracking smooth trajectories of multiple targets in complex data sets, where tracks potentially cross each other many times. As the number of overlapping trajectories grows, exploiting smoothness becomes increasingly important to disambiguate the association of successive points. However, in many important problems an effective parametric model for the trajectories does not exist. Hence we propose modeling trajectories as independent realizations of Gaussian processes with kernel functions which allow for arbitrary smooth motion. Our generative statistical model accounts for the data as coming from an unknown number of such processes, together with expectations for noise points and the probability that points are missing. For inference we compare two methods: A modified version of the Markov chain Monte Carlo data association (MCMCDA) method, and a Gibbs sampling method which is much simpler and faster, and gives better results by being able to search the solution space more efficiently. In both cases, we compare our results against the smoothing provided by linear dynamical systems (LDS). We test our approach on videos of birds and fish, and on 82 image sequences of pollen tubes growing in a petri dish, each with up to 60 tubes with multiple crossings. We achieve 93% accuracy on image sequences with up to ten trajectories (35 sequences) and 88% accuracy when there are more than ten (42 sequences). This performance surpasses that of using an LDS motion model, and far exceeds a simple heuristic tracker.

We propose a top down approach for understanding indoor scenes such as bedrooms and living rooms. These environments typically have the Manhattan world property that many surfaces are parallel to three principle ones. Further, the 3D geometry of the room and objects within it can largely be approximated by non overlapping simple structures such as single blocks (e.g. the room boundary), thin blocks (e.g. picture frames), and objects that are well modeled by single blocks (e.g. simple beds). We separately model the 3D geometry, the imaging process (camera parameters), and edge likelihood, to provide a generative statistical model for image data. We fit this model using data driven MCMC sampling. We combine reversible jump Metropolis Hastings samples for discrete changes in the model such as the number of blocks, and stochastic dynamics to estimate continuous parameter values in a particular parameter space that includes block positions, block sizes, and camera parameters. We tested our approach on two datasets using room box pixel orientation. Despite using only bounding box geometry and, in particular, not training on appearance, our method achieves results approaching those of others. We also introduce a new evaluation method for this domain based on ground truth camera parameters, which we found to be more sensitive to the task of understanding scene geometry.

Restoring data operations after a disaster is a daunting task: how should recovery be performed to minimize data loss and application downtime? Administrators are under considerable pressure to recover quickly, so they lack time to make good scheduling decisions. They schedule recovery based on rules of thumb, or on pre-determined orders that might not be best for the failure occurrence. With multiple workloads and recovery techniques, the number of possibilities is large, so the decision process is not trivial.This paper makes several contributions to the area of data recovery scheduling. First, we formalize the description of potential recovery processes by defining recovery graphs. Recovery graphs explicitly capture alternative approaches for recovering workloads, including their recovery tasks, operational states, timing information and precedence relationships. Second, we formulate the data recovery scheduling problem as an optimization problem, where the goal is to find the schedule that minimizes the financial penalties due to downtime, data loss and vulnerability to subsequent failures. Third, we present several methods for finding optimal or near-optimal solutions, including priority-based, randomized and genetic algorithm-guided ad hoc heuristics. We quantitatively evaluate these methods using realistic storage system designs and workloads, and compare the quality of the algorithms' solutions to optimal solutions provided by a math programming formulation and to the solutions from a simple heuristic that emulates the choices made by human administrators. We find that our heuristics' solutions improve on the administrator heuristic's solutions, often approaching or achieving optimality.