Abstract

String sorting or variable-length key sorting has lagged in performance on the GPU even as the fixed-length key sorting has improved dramatically. Radix sorting is the fastest on the GPUs. In this paper, we present a fast and efficient string sort on the GPU that is built on the available radix sort. Our method sorts strings from left to right in steps, moving only indexes and small prefixes for efficiency. We reduce the number of sort steps by adaptively consuming maximum string bytes based on the number of segments in each step. Performance is improved by using Thrust primitives for most steps and by removing singleton segments from consideration. Over 70% of the string sort time is spent on Thrust primitives. This provides high performance along with high adaptability to future GPUs. We achieve speed of up to 10 over current GPU methods, especially on large datasets. We also scale to much larger input sizes. We present results on easy and difficult strings defined using their after-sort tie lengths.

Abstract

We present an approach to simulate both Newtonian and generalized Newtonian fluids using Lattice Boltzmann Method. The focus has been on accurately modelling nonNewtonian fluids at the micro channel level from biological fluids in the past. Our method can model macroscopic behaviour of such fluids by simulating the variation of properties such as viscosity through the bulk of the fluid. The method works regardless of the magnitude of flow, be it through a thin tube or a large quantity of liquid splashing in a container. We simulate the change in viscosity of a generalized Newtonian fluid and its free surface interactions with obstacles and boundaries. We harness the inherent parallelism of Lattice Boltzmann Method to give a fast GPU implementation for the same.

Abstract

We present an approach for fast registration of a Global Articulated 3D Model to RGBD data from Kinect. Our approach uses geometry based matching of rigid parts of the articulated objects in depth images. The registration is performed in a parametric space of transformations independently for each segment. The time for registering each frame with the global model is reduced greatly using this method. We experimented the algorithm with different articulated object datasets and obtained significantly low execution time as compared to ICP algorithm when applied on each rigid part of the articulated object.

Abstract

In this work we specify various parameters like 1) local quantumness 2) entangling capability 3) classical randomness and give a canonical rep- representation of two qubit mixed quantum states based on them. Here we investigate the correlating capability of a non local Hamiltonian acting on general two qubit states in context of these parameters. In particular we address the questions like: 1.What is the rate of change of the standard measures of correlation like Entanglement (E) and Discord (D). 2.How these measures get affected by the change of the parameters. 3.For what choice of initial parameters, these rates of change of correlation like dE/dt ; dD/dt are maximum. 4.We study its application on bistable and open systems. Our study and analysis are completely based on the mixed quantum states quite unlike to the previous investigations based on pure quantum states.

Abstract

In this paper, we present a novel stable hybrid vision-based robot control algorithm. This method utilizes probabilistic integration of image-based and position-based visual servo con-trollers to produce an improved vision-based robot control. A probabilistic framework is employed to derive the integration scheme. Appropriate probabilistic importance functionsare de ned for the basic two algorithms to characterize their suitability in the task. The integrated algorithm has superior performance both in image and Cartesian spaces. Exper-iments validate this claim.

Abstract

Understanding the nature of data is the key to build-ing good representations. In domains such as natural im-ages, the data comes from very complex distributions which are hard to capture. Feature learning intends to discover or best approximate these underlying distributions and use their knowledge to weed out irrelevant information, pre-serving most of the relevant information. Feature learning can thus be seen as a form of dimensionality reduction. In this paper, we describe a feature learning scheme for nat-ural images. We hypothesize that image patches do not all come from the same distribution, they lie in multiple non-linear subspaces. We propose a framework that uses KRestricted Boltzmann Machines (K-RBMS) to learn mul-tiple non-linear subspaces in the raw image space. Pro-jections of the image patches into these subspaces gives us features, which we use to build image representations.Our algorithm solves the coupled problem of finding the right non-linear subspaces in the input space and associ-ating image patches with those subspaces in an iterative EM like algorithm to minimize the overall reconstruction error. Extensive empirical results over several popular im-age classification datasets show that representations based on our framework outperform the traditional feature repre-sentations such as the SIFT based Bag-of-Words (BoW) and convolutional deep belief networks.

Abstract

The automatic discovery of distinctive parts for an ob-ject or scene class is challenging since it requires simulta-neously to learn the part appearance and also to identify the part occurrences in images. In this paper, we propose a simple, efficient, and effective method to do so. We ad-dress this problem by learning parts incrementally, starting from a single part occurrence with an Exemplar SVM. In this manner, additional part instances are discovered and aligned reliably before being considered as training exam-ples. We also propose entropy-rank curves as a means of evaluating the distinctiveness of parts shareable between categories and use them to select useful parts out of a set of candidates.We apply the new representation to the task of scene cat-egorisation on the MIT Scene 67 benchmark. We show that our method can learn parts which are significantly more in-formative and for a fraction of the cost, compared to previ-ous part-learning methods such as Singhet al. [28]. We also show that a well constructed bag of words or Fisher vector model can substantially outperform the previous state-of-the-art classification performance on this data.

Abstract

Automatically generating meaningful descriptions for images has recently emerged as an important area of re-search. In this direction, a nearest-neighbour based gener-ative phrase prediction model (PPM) proposed by (Guptaet al. 2012) was shown to achieve state-of-the-art results on PASCAL sentence dataset, thanks to the simultaneous use of three different sources of information (i.e. visual clues,corpus statistics and available descriptions). However, they do not utilize semantic similarities among the phrases that might be helpful in relating semantically similar phrases during phrase relevance prediction. In this paper, we ex-tend their model by considering inter-phrase semantic sim-ilarities. To compute similarity between two phrases, we consider similarities among their constituent words deter-mined using Word Net. We also re-formulate their objective function for parameter learning by penalizing each pair of phrases unevenly, in a manner similar to that in structured predictions. Various automatic and human evaluations are performed to demonstrate the advantage of our “semantic phrase prediction model” (SPPM) over PPM.

Abstract

We focus on the problem of mining object categories from large datasets like Google Street View images. Mining ob-ject categories in these unannotated datasets is an impor-tant and useful step to extract meaningful information. Of-ten the location and spatial extent of an object in an im-age is unknown. Mining objects in such a setting is hard.Recent methods model this problem as learning a separate classifier for each category. This is computationally expen-sive since a large number of classifiers are required to be trained and evaluated, before one can mine a concise set of meaningful objects. On the other hand, fast and efficient solutions have been proposed for the retrieval of instances(same object) from large databases. We borrow, from in-stance retrieval pipeline, its strengths and adapt it to speedup category mining. For this, we explore objects which are“near-instances”.We mine several near-instance object categories from images. Using an instance retrieval based solution, we are able to mine certain categories of near-instance objects much faster than an Exemplar SVM based solution.

Abstract

We aim to decompose a global histogram representation of an image into histograms of its associated objects and re-gions. This task is formulated as an optimization problem,given a set of linear classifiers, which can effectively dis-criminate the object categories present in the image. Our decomposition bypasses harder problems associated with accurately localizing and segmenting objects. We evaluate our method on a wide variety of composite histograms, and also compare it with MRF-based solutions. In addition to merely mea suring the accuracy of decomposition, we also show the utility of the estimated object and background his-tograms for the task of image classification on thePASCALVOC2007dataset.