Abstract

The Simultaneous Localization and Mapping problem (SLAM) in robotics is typically modeled as a dyadic graph of relative pose measurements taken by the robot. The graph nodes store the values representing the absolute pose of the robot at a given point of time. An edge connecting two nodes represents robot movement and it stores the measurements taken by the robot sensor while moving between two nodes. The objective of the SLAM problem is to find the optimal global measurements best satisfying the noisy relative measurements [12]. This problem of optimal estimation on a graph given relative measurements is a well-studied problem within the control community, for which several results and algorithms are known [3, 4]. SLAM is generally solved as a least squares problem. Robust kernels which are less sensitive to outliers are used to deal with noise and outlier measurements. However, robust kernels tend to be dependent on initialization and can fail as the number of outliers increase. Therefore, it's important to identify and prune the outlier (noisy) measurements represented by incorrect loop closure edges for an accurate pose estimate. In this paper we propose a multi-scale Heat-Kernel analysis based loop closure edge pruning algorithm for the SLAM graph. We show that compared to other pruning algorithms, our algorithm has a substantially higher precision and recall when compared and is able to handle a large amount of outlier measurements.We have corroborated results on several publicly available datasets and several types of noise. Our algorithm is not restricted to SLAM graphs only, but has a much wider applicability to other types of geometric graphs.

Abstract

Face frontalization is the process of synthesizing a frontal view of a face, given its non-frontal view. Frontalization is used in intelligent photo editing tools and also aids in improving the accuracy of face recognition systems. For example, in the case of photo editing, faces of persons in a group photo can be corrected to look into the camera, if they are looking elsewhere. Similarly, even though recent methods in face recognition claim accuracy which surpasses that of humans in some cases, perfor- mance of recognition systems degrade when profile view of faces are given as input. One way to address this issue is to synthesize frontal views of faces before recognition. We propose a simple and efficient method to address the face frontalization problem. Our method leverages the fact that faces in general have a definite structure and can be represented in a low dimensional subspace. We employ an exemplar based approach to find the transformation that relates the profile view to the frontal view, and use it to generate realistic frontalizations. Our method does not involve estimating 3 D model of the face, which is a common approach in previous work in this area. This leads to an efficient solution, since we avoid the complexity of adding one more dimension to the problem. Our method also retains the structural information of the individual as compared to that of a recent method [4], which assumes a generic 3 D model for synthesis. We show impressive qualitative and quantitative results in comparison to the state-of-the-art in this field.

Abstract

DNA molecules tagged to metal nanoparticles, especially gold nanoparticles (AuNPs), have been shown to exhibit potential applications in designing and fabrication of novel electronic nano-devices, but the binding mechanism between gold nanoparticles and DNA bases and its implications are not completely understood. In this work, a comprehensive study to examine the effect of structural perturbations offered to DNA base pairs in terms of size expansion and adsorption on a gold cluster (Au3) has been done using density functional theory. Geometric and electronic features of these complexes provide evidences for distortion of certain base pairs depending on the binding site of the cluster. This is further substantiated via normal mode, natural bond orbital (NBO) and atoms in molecules (AIM) analyses. The natural population analysis (NPA) and NBO analysis indicate that complexation greatly affects the charge distribution on the base pairs due to charge transfer between base pair and gold cluster. This charge redistribution may offer a possibility of higher order interactions. Upon complexation, a marked decrease in the HOMO-LUMO gap is observed, which is more profound in cases where size expanded bases are involved due to the extended π-conjugation of the fused benzine rings. This study demonstrates the possibility of combining structural modifications to DNA base pairs and subsequent binding to gold nano particles to modulate and achieve molecular systems with desired optico-electronic properties.

Abstract

Recent reports have demonstrated that nanoclusters of silver and gold can act as substrates for Raman signal enhancements. This article presents a density functional theory (DFT)-based study to explore how the variations in the nature of the cluster-binding heteroatom in the ligand molecule and the relative orientation of the alkyl group attached to the heteroatom affect the Raman signal enhancement in the ligand molecules. Our calculations involved nitrogen and phosphorus heteroatoms in two simple model molecules, methylphosphine and methylamine, as ligands and four small gold clusters, Aun (n = 6–9). In order to understand the interactions in the cluster-molecule systems, we have calculated various geometrical parameters such as Au–X (X = P, N) distances, ffC–X–Au angles and different bond lengths of free and cluster-bound molecules as well as various interaction energies. We have performed natural bond order (NBO) analysis and have calculated second order stabilization energies for the molecules bound to the gold clusters from the NBO analysis. In addition, we have performed detailed calculations pertaining to the change in polarisability, quantity of molecule to cluster charge transfer as well as molecular orientations relative to the clusters and have studied how these factors influence the Raman scattering cross-sections and vibrational frequency shifts. The quantity of charge transfer and the orientation effect have been found to be important contributors in the chemical Raman enhancement mechanism of the ligand molecules.

Abstract

Modern feature extraction pipelines, especially the on esusing deep networks, involve an increasing variety of elements. With layered approaches heaping abstraction upon abstraction, it becomes difficult to understand what it is that these features are capturing. One appealing way of solving this puzzle is feature visualization, where features are mapped back to the image domain. Our work improves the generic approach of performing gradient descent (GD) in the image space to match a given set of features to achieve a visualization. Specifically, we note that coarse features of an image like blobs, outlines etc. are useful by them-selves for classification purposes. We develop an inversion scheme based on this idea by recovering coarse features of the image before finer details. This is done by modeling the image as the composition of a Laplacian Pyramid. We show that by performing GD on the pyramid in a level-wise manner, we can recover meaningful images. Results are presented for inverting a shallow network: the densely calculated SIFT as well as a deep network: Krizehvsky et al.’sImagenet CNN (Alexnet).

Abstract

Most of the traditional sketch-based image retrieval systems compare sketches and images using morphological features. Since these features belong to two different modalities, they are compared either by reducing the image to a sparse sketch like form or by transforming the sketches to a denser image like representation. However, this cross-modal transformation leads to information loss or adds undesirable noise to the system. We propose a method, in which, instead of comparing the two modalities directly, across-modal correspondence is established between the images and sketches. Using an extended version of Canonical Correlation Analysis (CCA), the samples are projected onto a lower dimensional subspace, where the images and sketches of the same class are maximally correlated. We test the efficiency of our method on images from Caltech, PAS-CAL and sketches from TU-BERLIN dataset. Our resultsshow significant improvement in retrieval performance with the cross-modal correspondence.

Abstract

Understanding the precise 3D structure of an environ-ment is one of the fundamental goals of computer vision and is challenging due to a variety of factors such as appearance variation, illumination, pose, noise, occlusion and scene clutter. A generic solution to the problem is ill-posed due to the loss of depth information during imaging. In this paper, we consider a specific but common situation, where the scene contains known objects. Given 3D models of a set of known objects and a cluttered scene image, we try to detect these objects in the image, and align 3D models to their images to find their exact pose. We develop an approach that poses this as a 3D-to-2D alignment problem.We also deal with pose estimation of 3D articulated objects in images. We evaluate our proposed method on Big Bird dataset and our own tabletop dataset, and present experimental comparisons with state-of-the-art methods.

Abstract

Automating the process of indexing journal abstracts has been a topic of research for several years. Biomedical Semantic Indexing aims to assign correct MeSH terms to the PubMed documents. In this paper we report our participation in the Task 3a of BioASQ challenge 2015. The participating teams were provided with PubMed articles and asked to return relevant MeSH terms. We tried three different approaches: Nearest Neighbours, IDF-Ratio based indexing and multi-label classification. The official challenge results demonstrate that we consistently performed better than the baseline approaches for Task 3a.

Abstract

In this paper, we describe our participation in the 2015 BioASQ challenge on Bio-Medical Question Answering. For Question Answering task (Task 3b), teams were provided with natural language questions and asked to retrieve responses from PubMed corpus in the form of documents, snippets, concepts and RDF triplets (Phase A) and direct answers (Phase B). For Phase A, we took the support of PubMed search engine and our snippet extraction technique. In our QA system, apart from the standard techniques discussed in literature, we tried the following novel techniques to - a) leverage web search results for improving question processing and b) identify domain words and define a new answer ranking function based on number of common domain words. We scored an F-measure of 0.193 for document extraction and F-measure of 0.0717 in snippet generation

Abstract

The memory and core requirements of a virtual machine depend on the performance requirements of the applications hosted on it. In this paper, we propose algorithms for dynamic memory and core scaling using a combination of machine learning and feedback control techniques. These algorithms work for sequential and parallel applications such as scientific computations where speedup is the primary performance metric. Then we use these algorithms to address the simultaneous memory and core allocation problem, which is more complex due to possible correlation between these resource requirements. All these algorithms can be applied in a black box fashion without instrumenting the source code of applications.