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.

Abstract

Real-time multimedia applications which demand very low decoding delays are increasing day-by-day. To address this challenge, in error-resilient applications, many approximate computing architectures for delay critical units have been proposed. In this paper, we propose an architecture for an approximate multiplier, accuracy of which can be configured during the run-time. According to the requirement of the application, the multiplier can be configured to operate in an exact mode or in any of the approximate modes, reducing its decoding delay and the dynamic power consumed. The architecture for the proposed approximate multiplier has been synthesized and simulated using Cadence design tools. Using 16-bit multiplication, it has been demonstrated that, the pass-rate and the propagation delay of the proposed multiplier is comparable or better than most of the published inaccurate multipliers. The proposed approximate multiplier is successfully used in a JPEG conversion application and performances of different accuracy modes are compared.

Abstract

The telecare medicine information system (TMIS) helps the patients to gain the health monitoring facility at home and access medical services over the Internet of mobile networks. Recently, Amin and Biswas presented a smart card based user authentication and key agreement security protocol usable for TMIS system using the cryptographic one-way hash function and biohashing function, and claimed that their scheme is secure against all possible attacks. Though their scheme is efficient due to usage of one-way hash function, we show that their scheme has several security pitfalls and design flaws, such as (1) it fails to protect privileged-insider attack, (2) it fails to protect strong replay attack, (3) it fails to protect strong man-in-the-middle attack, (4) it has design flaw in user registration phase, (5) it has design flaw in login phase, (6) it has design flaw in password change phase, (7) it lacks of supporting biometric update phase, and (8) it has flaws in formal security analysis. In order to withstand these security pitfalls and design flaws, we aim to propose a secure and robust user authenticated key agreement scheme for the hierarchical multi-server environment suitable in TMIS using the cryptographic one-way hash function and fuzzy extractor. Through the rigorous security analysis including the formal security analysis using the widely-accepted Burrows-Abadi-Needham (BAN) logic, the formal security analysis under the random oracle model and the informal security analysis, we show that our scheme is secure against possible known attacks. Furthermore, we simulate our scheme using the most-widely accepted and used Automated Validation of Internet Security Protocols and Applications (AVISPA) tool. The simulation results show that our scheme is also secure. Our scheme is more efficient in computation and communication as compared to Amin-Biswas’s scheme and other related schemes. In addition, our scheme supports extra functionality features as compared to other related schemes. As a result, our scheme is very appropriate for practical applications in TMIS.

Abstract

Recent advanced technology enables the telecare medicine information system (TMIS) for the patients to gain the health monitoring facility at home and also to access medical services over the Internet of mobile networks. Several remote user authentication schemes have been proposed in the literature for TMIS. However, most of them are either insecure against various known attacks or they are inefficient. Recently, Tan proposed an efficient user anonymity preserving three-factor authentication scheme for TMIS. In this paper, we show that though Tan’s scheme is efficient, it has several security drawbacks such as (1) it fails to provide proper authentication during the login phase, (2) it fails to provide correct updation of password and biometric of a user during the password and biometric update phase, and (3) it fails to protect against replay attack. In addition, Tan’s scheme lacks the formal security analysis and verification. Later, Arshad and Nikooghadam also pointed out some security flaws in Tan’s scheme and then presented an improvement on Tan’s s scheme. However, we show that Arshad and Nikooghadam’s scheme is still insecure against the privileged-insider attack through the stolen smart-card attack, and it also lacks the formal security analysis and verification. In order to withstand those security loopholes found in both Tan’s scheme, and Arshad and Nikooghadam’s scheme, we aim to propose an effective and more secure three-factor remote user authentication scheme for TMIS. Our scheme provides the user anonymity property. Through the rigorous informal and formal security analysis using random oracle models and the widely-accepted AVISPA (Automated Validation of Internet Security Protocols and Applications) tool, we show that our scheme is secure against various known attacks, including the replay and man-in-the-middle attacks. Furthermore, our scheme is also efficient as compared to other related schemes.Recent advanced technology enables the telecare medicine information system (TMIS) for the patients to gain the health monitoring facility at home and also to access medical services over the Internet of mobile networks. Several remote user authentication schemes have been proposed in the literature for TMIS. However, most of them are either insecure against various known attacks or they are inefficient. Recently, Tan proposed an efficient user anonymity preserving three-factor authentication scheme for TMIS. In this paper, we show that though Tan’s scheme is efficient, it has several security drawbacks such as (1) it fails to provide proper authentication during the login phase, (2) it fails to provide correct updation of password and biometric of a user during the password and biometric update phase, and (3) it fails to protect against replay attack. In addition, Tan’s scheme lacks the formal security analysis and verification. Later, Arshad and Nikooghadam also pointed out some security flaws in Tan’s scheme and then presented an improvement on Tan’s s scheme. However, we show that Arshad and Nikooghadam’s scheme is still insecure against the privileged-insider attack through the stolen smart-card attack, and it also lacks the formal security analysis and verification. In order to withstand those security loopholes found in both Tan’s scheme, and Arshad and Nikooghadam’s scheme, we aim to propose an effective and more secure three-factor remote user authentication scheme for TMIS. Our scheme provides the user anonymity property. Through the rigorous informal and formal security analysis using random oracle models and the widely-accepted AVISPA (Automated Validation of Internet Security Protocols and Applications) tool, we show that our scheme is secure against various known attacks, including the replay and man-in-the-middle attacks. Furthermore, our scheme is also efficient as compared to other related schemes.

Abstract

SURROGATE CITY FINDER - WEATHER DATA TOOLVishal Garg, T.V.S Nikhil, Hema Rallapalli,Aviruch Bhatia, Jegibabu Subhash, Chetan Kasireddy International Institute of Information Technology, Hyderabad, India. ABSTRACTWeather data is the one of the important inputs for the building energy simulation and is available for almost all major cities of the world. However, there are still some cities, for which weather data is not readily available in the format suitable for energy simulation. To address this problem, we have developed a web-based tool called Surrogate City Finder (SCF). For a given location, for which there is no weather file available, the tool shortlists the best-matched weather files based on parameters such as the latitude, altitude, and temperature range of the given location. The SCF tool has been tested by analysing the annual energy consumption of 16-reference building models simulated for eight locations from different international climate zones and their surrogate cities. In most cases, the deviation in annual energy consumption was within two percent.