Query-Sensitive Embeddings

A common problem in many types of databases is retrieving the most similar matches to a query object. Finding those matches in a large database can be too slow to be practical, especially in domains where objects are compared using computationally expensive similarity (or distance) measures. This paper proposes a novel method for approximate nearest neighbor retrieval in such spaces. Our method is embedding-based, meaning that it constructs a function that maps objects into a real vector space. The mapping preserves a large amount of the proximity structure of the original space, and it can be used to rapidly obtain a short list of likely matches to the query. The main novelty of our method is that it constructs, together with the embedding, a query-sensitive distance measure that should be used when measuring distances in the vector space. The term "query-sensitive" means that the distance measure changes depending on the current query object. We report experiments with an image database of handwritten digits, and a time-series database. In both cases, the proposed method outperforms existing state-of-the-art embedding methods, meaning that it provides significantly better trade-offs between efficiency and retrieval accuracy.

A Two-Tiered On-Line Server-Side Bandwidth Reservation Framework for the Real-Time Delivery of Multiple Video Streams

The advent of virtualization and cloud computing technologies necessitates the development of effective mechanisms for the estimation and reservation of resources needed by content providers to deliver large numbers of video-on-demand (VOD) streams through the cloud. Unfortunately, capacity planning for the QoS-constrained delivery of a large number of VOD streams is inherently difficult as VBR encoding schemes exhibit significant bandwidth variability. In this paper, we present a novel resource management scheme to make such allocation decisions using a mixture of per-stream reservations and an aggregate reservation, shared across all streams to accommodate peak demands. The shared reservation provides capacity slack that enables statistical multiplexing of peak rates, while assuring analytically bounded frame-drop probabilities, which can be adjusted by trading off buffer space (and consequently delay) and bandwidth. Our two-tiered bandwidth allocation scheme enables the delivery of any set of streams with less bandwidth (or equivalently with higher link utilization) than state-of-the-art deterministic smoothing approaches. The algorithm underlying our proposed frame-work uses three per-stream parameters and is linear in the number of servers, making it particularly well suited for use in an on-line setting. We present results from extensive trace-driven simulations, which confirm the efficiency of our scheme especially for small buffer sizes and delay bounds, and which underscore the significant realizable bandwidth savings, typically yielding losses that are an order of magnitude or more below our analytically derived bounds.

Search Space Reduction in QoS Routing

To provide real-time service or engineer constrained-based paths, networks require the underlying routing algorithm to be able to find low-cost paths that satisfy given Quality-of-Service (QoS) constraints. However, the problem of constrained shortest (least-cost) path routing is known to be NP-hard, and some heuristics have been proposed to find a near-optimal solution. However, these heuristics either impose relationships among the link metrics to reduce the complexity of the problem which may limit the general applicability of the heuristic, or are too costly in terms of execution time to be applicable to large networks. In this paper, we focus on solving the delay-constrained minimum-cost path problem, and present a fast algorithm to find a near-optimal solution. This algorithm, called DCCR (for Delay-Cost-Constrained Routing), is a variant of the k-shortest path algorithm. DCCR uses a new adaptive path weight function together with an additional constraint imposed on the path cost, to restrict the search space. Thus, DCCR can return a near-optimal solution in a very short time. Furthermore, we use the method proposed by Blokh and Gutin to further reduce the search space by using a tighter bound on path cost. This makes our algorithm more accurate and even faster. We call this improved algorithm SSR+DCCR (for Search Space Reduction+DCCR). Through extensive simulations, we confirm that SSR+DCCR performs very well compared to the optimal but very expensive solution.

Articulated Pose Estimation in a Learned Smooth Space of Feasible Solutions

A learning based framework is proposed for estimating human body pose from a single image. Given a differentiable function that maps from pose space to image feature space, the goal is to invert the process: estimate the pose given only image features. The inversion is an ill-posed problem as the inverse mapping is a one to many process. Hence multiple solutions exist, and it is desirable to restrict the solution space to a smaller subset of feasible solutions. For example, not all human body poses are feasible due to anthropometric constraints. Since the space of feasible solutions may not admit a closed form description, the proposed framework seeks to exploit machine learning techniques to learn an approximation that is smoothly parameterized over such a space. One such technique is Gaussian Process Latent Variable Modelling. Scaled conjugate gradient is then used find the best matching pose in the space of feasible solutions when given an input image. The formulation allows easy incorporation of various constraints, e.g. temporal consistency and anthropometric constraints. The performance of the proposed approach is evaluated in the task of upper-body pose estimation from silhouettes and compared with the Specialized Mapping Architecture. The estimation accuracy of the Specialized Mapping Architecture is at least one standard deviation worse than the proposed approach in the experiments with synthetic data. In experiments with real video of humans performing gestures, the proposed approach produces qualitatively better estimation results.

Tracking Human Body Pose on a Learned Smooth Space

Particle filtering is a popular method used in systems for tracking human body pose in video. One key difficulty in using particle filtering is caused by the curse of dimensionality: generally a very large number of particles is required to adequately approximate the underlying pose distribution in a high-dimensional state space. Although the number of degrees of freedom in the human body is quite large, in reality, the subset of allowable configurations in state space is generally restricted by human biomechanics, and the trajectories in this allowable subspace tend to be smooth. Therefore, a framework is proposed to learn a low-dimensional representation of the high-dimensional human poses state space. This mapping can be learned using a Gaussian Process Latent Variable Model (GPLVM) framework. One important advantage of the GPLVM framework is that both the mapping to, and mapping from the embedded space are smooth; this facilitates sampling in the low-dimensional space, and samples generated in the low-dimensional embedded space are easily mapped back into the original highdimensional space. Moreover, human body poses that are similar in the original space tend to be mapped close to each other in the embedded space; this property can be exploited when sampling in the embedded space. The proposed framework is tested in tracking 2D human body pose using a Scaled Prismatic Model. Experiments on real life video sequences demonstrate the strength of the approach. In comparison with the Multiple Hypothesis Tracking and the standard Condensation algorithm, the proposed algorithm is able to maintain tracking reliably throughout the long test sequences. It also handles singularity and self occlusion robustly.

Real-Time Spatio-Temporal Query Processing in Mobile Ad-Hoc Sensor Networks

Personal communication devices are increasingly equipped with sensors that are able to collect and locally store information from their environs. The mobility of users carrying such devices, and hence the mobility of sensor readings in space and time, opens new horizons for interesting applications. In particular, we envision a system in which the collective sensing, storage and communication resources, and mobility of these devices could be leveraged to query the state of (possibly remote) neighborhoods. Such queries would have spatio-temporal constraints which must be met for the query answers to be useful. Using a simplified mobility model, we analytically quantify the benefits from cooperation (in terms of the system's ability to satisfy spatio-temporal constraints), which we show to go beyond simple space-time tradeoffs. In managing the limited storage resources of such cooperative systems, the goal should be to minimize the number of unsatisfiable spatio-temporal constraints. We show that Data Centric Storage (DCS), or "directed placement", is a viable approach for achieving this goal, but only when the underlying network is well connected. Alternatively, we propose, "amorphous placement", in which sensory samples are cached locally, and shuffling of cached samples is used to diffuse the sensory data throughout the whole network. We evaluate conditions under which directed versus amorphous placement strategies would be more efficient. These results lead us to propose a hybrid placement strategy, in which the spatio-temporal constraints associated with a sensory data type determine the most appropriate placement strategy for that data type. We perform an extensive simulation study to evaluate the performance of directed, amorphous, and hybrid placement protocols when applied to queries that are subject to timing constraints. Our results show that, directed placement is better for queries with moderately tight deadlines, whereas amorphous placement is better for queries with looser deadlines, and that under most operational conditions, the hybrid technique gives the best compromise.