Gaurav Sharma

Bio: Gaurav Sharma is an academic researcher from Shenzhen University. The author has contributed to research in topics: Medicine & Photocatalysis. The author has an hindex of 82, co-authored 1244 publications receiving 31482 citations. Previous affiliations of Gaurav Sharma include Northeastern University & D. E. Shaw & Co..

Coordinated Joint Multimodal Embeddings for Generalized Audio-Visual Zeroshot Classification and Retrieval of Videos.

Abstract: We present an audio-visual multimodal approach for the task of zeroshot learning (ZSL) for classification and retrieval of videos. ZSL has been studied extensively in the recent past but has primarily been limited to visual modality and to images. We demonstrate that both audio and visual modalities are important for ZSL for videos. Since a dataset to study the task is currently not available, we also construct an appropriate multimodal dataset with 33 classes containing 156,416 videos, from an existing large scale audio event dataset. We empirically show that the performance improves by adding audio modality for both tasks of zeroshot classification and retrieval, when using multimodal extensions of embedding learning methods. We also propose a novel method to predict the `dominant' modality using a jointly learned modality attention network. We learn the attention in a semi-supervised setting and thus do not require any additional explicit labelling for the modalities. We provide qualitative validation of the modality specific attention, which also successfully generalizes to unseen test classes.

Retinal Vessel Detection in Wide-Field Fluorescein Angiography with Deep Neural Networks: A Novel Training Data Generation Approach

Abstract: Retinal blood vessel detection is a crucial step in automatic retinal image analysis. Recently, deep neural networks have significantly advanced the state of the art for retinal blood vessel detection in color fundus (CF) images. Thus far, similar gains have not been seen in fluorescein angiography (FA) because the FA modality is entirely different from CF and annotated training data has not been available for FA imagery. We address retinal vessel detection in wide-field FA images with generative adversarial networks (GAN) via a novel approach for generating training data. Using a publicly available dataset that contains concurrently acquired pairs of CF and fundus FA images, vessel maps are detected in CF images via a pre-trained neural network and registered with fundus FA images via parametric chamfer matching to a preliminary FA vessel detection map. The co-aligned pairs of vessel maps (detected from CF images) and fundus FA images are used as ground truth labeled data for de novo training of a deep neural network for FA vessel detection. Specifically, we utilize adversarial learning to train a GAN where the generator learns to map FA images to binary vessel maps and the discriminator attempts to distinguish generated vs. ground-truth vessel maps. We highlight several important considerations for the proposed data generation methodology. The proposed method is validated on VAMpIRE dataset that contains high-resolution wide-field FA images and manual annotation of vessel segments. Experimental results demonstrate that the proposed method achieves an estimated ROC AUC of 0.9758.

A Study of Transmigrated Canine in an Indian Population

Abstract: Aim. The purpose of this study was to investigate the prevalence of transmigrated canines in a north Indian population and association with gender, side, associated pathologies, and dental anomalies. Subjects and methods. The prospective study consisted of panoramic radiographs of 3000 patients from two dental colleges in north India. The panoramic radiographs were screened for radiographically identified position of the transmigrated tooth, retained canine, and other coexisting dental anomalies. Results. The overall prevalence of transmigrated canines (15 mandibular and 5 maxillary) was 0.66%. The prevalence of mandibular transmigrated canine was 0.5% and maxillary transmigrated canine was 0.16%. All the transmigrated canines were unilateral. The age range was 15–53 years (average age 24.1 years) and there were 12 males (60%) and 8 females (40%). Type 1 mandibular canine transmigration was the commonest type found in our study (10 cases), followed by types 2 and 4 (2 cases each) and 1 case of type 5 transmigration. Conclusion. The prevalence of transmigrated canines in the north Indian population was 0.66% and no gender predilection was evident. The transmigrated canines have a low complication rate (10.0%) and no correlation with other dental anomalies was found. Type 3 canine is the rarest form of mandibular canine transmigration.

On the Security of Certificateless Signature Schemes

Abstract: Wireless Sensor Network (WSN) has proved its presence in various real time applications and hence the security of such embedded devices is a vital issue. Certificateless cryptography is one of the recent paradigms to provide security. Certificateless public key cryptography (CL-PKC) deals effectively with the twin issues of certificate management in traditional public key cryptography and key escrow problem in identity-based cryptography. CL-PKC has attracted special attention in the field of information security as it has opened new avenues for improvement in the present security architecture. Recently, Tsai et al. proposed an improved certificateless signature scheme without pairing and claimed that their new construction is secure against different kinds of attacks. In this paper, we present a security analysis of their scheme and our results show that scheme does not have resistance against malicious-KGC attack. In addition, we have found some security flaws in the certificateless signature scheme of Fan et al. and proved the scheme vulnerable to Strong Type I attack.

I and i

Abstract: There is, I think, something ethereal about i —the square root of minus one. I remember first hearing about it at school. It seemed an odd beast at that time—an intruder hovering on the edge of reality. Usually familiarity dulls this sense of the bizarre, but in the case of i it was the reverse: over the years the sense of its surreal nature intensified. It seemed that it was impossible to write mathematics that described the real world in …

SPAdes, a new genome assembly algorithm and its applications to single-cell sequencing ( 7th Annual SFAF Meeting, 2012)

Abstract: The lion's share of bacteria in various environments cannot be cloned in the laboratory and thus cannot be sequenced using existing technologies. A major goal of single-cell genomics is to complement gene-centric metagenomic data with whole-genome assemblies of uncultivated organisms. Assembly of single-cell data is challenging because of highly non-uniform read coverage as well as elevated levels of sequencing errors and chimeric reads. We describe SPAdes, a new assembler for both single-cell and standard (multicell) assembly, and demonstrate that it improves on the recently released E+V-SC assembler (specialized for single-cell data) and on popular assemblers Velvet and SoapDeNovo (for multicell data). SPAdes generates single-cell assemblies, providing information about genomes of uncultivatable bacteria that vastly exceeds what may be obtained via traditional metagenomics studies. SPAdes is available online ( http://bioinf.spbau.ru/spades ). It is distributed as open source software.