International Institute of Information Technology, Hyderabad

About: International Institute of Information Technology, Hyderabad is a education organization based out in Hyderabad, India. It is known for research contribution in the topics: Computer science & Authentication. The organization has 2048 authors who have published 3677 publications receiving 45319 citations. The organization is also known as: IIIT Hyderabad & International Institute of Information Technology (IIIT).

A secure and robust temporal credential-based three-factor user authentication scheme for wireless sensor networks

Abstract: User authentication is one of the most important security services required for the resource-constrained wireless sensor networks (WSNs). In user authentication, for critical applications of WSNs, a legitimate user is allowed to query and collect the real-time data at any time from a sensor node of the network as and when he/she demands for it. In order to get the real-time information from the nodes, the user needs to be first authenticated by the nodes as well as the gateway node (GWN) of WSN so that illegal access to nodes do not happen in the network. Recently, Jiang et al. proposed an efficient two-factor user authentication scheme with unlinkability property in WSNs Jiang (2014). In this paper, we analyze Jiang et al.’s scheme. Unfortunately, we point out that Jiang et al.’s scheme has still several drawbacks such as (1) it fails to protect privileged insider attack, (2) inefficient registration phase for the sensor nodes, (3) it fails to provide proper authentication in login and authentication phase, (4) it fails to update properly the new changed password of a user in the password update phase, (5) it lacks of supporting dynamic sensor node addition after initial deployment of nodes in the network, and (6) it lacks the formal security verification. In order to withstand these pitfalls found in Jiang et al.’s scheme, we aim to propose a three-factor user authentication scheme for WSNs. Our scheme preserves the original merits of Jiang et al.’s scheme. Our scheme is efficient as compared to Jiang et al.’s scheme and other schemes. Furthermore, our scheme provides better security features and higher security level than other schemes. In addition, we simulate our scheme for the formal security analysis using the widely-accepted AVISPA (Automated Validation of Internet Security Protocols and Applications) tool. The simulation results clearly demonstrate that our scheme is also secure.

ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction

Abstract: The ICDAR 2019 Challenge on "Scanned receipts OCR and key information extraction" (SROIE) covers important aspects related to the automated analysis of scanned receipts. The SROIE tasks play a key role in many document analysis systems and hold significant commercial potential. Although a lot of work has been published over the years on administrative document analysis, the community has advanced relatively slowly, as most datasets have been kept private. One of the key contributions of SROIE to the document analysis community is to offer a first, standardized dataset of 1000 whole scanned receipt images and annotations, as well as an evaluation procedure for such tasks. The Challenge is structured around three tasks, namely Scanned Receipt Text Localization (Task 1), Scanned Receipt OCR (Task 2) and Key Information Extraction from Scanned Receipts (Task 3). The competition opened on 10th February, 2019 and closed on 5th May, 2019. We received 29, 24 and 18 valid submissions received for the three competition tasks, respectively. This report presents the competition datasets, define the tasks and the evaluation protocols, offer detailed submission statistics, as well as an analysis of the submitted performance. While the tasks of text localization and recognition seem to be relatively easy to tackle, it is interesting to observe the variety of ideas and approaches proposed for the information extraction task. According to the submissions' performance we believe there is still margin for improving information extraction performance, although the current dataset would have to grow substantially in following editions. Given the success of the SROIE competition evidenced by the wide interest generated and the healthy number of submissions from academic, research institutes and industry over different countries, we consider that the SROIE competition can evolve into a useful resource for the community, drawing further attention and promoting research and development efforts in this field.

Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles

Abstract: Many practical perception systems exist within larger processes which often include interactions with users or additional components that are capable of evaluating the quality of predicted solutions. In these contexts, it is beneficial to provide these oracle mechanisms with multiple highly likely hypotheses rather than a single prediction. In this work, we pose the task of producing multiple outputs as a learning problem over an ensemble of deep networks -- introducing a novel stochastic gradient descent based approach to minimize the loss with respect to an oracle. Our method is simple to implement, agnostic to both architecture and loss function, and parameter-free. Our approach achieves lower oracle error compared to existing methods on a wide range of tasks and deep architectures. We also show qualitatively that solutions produced from our approach often provide interpretable representations of task ambiguity.

Improving CNN-RNN Hybrid Networks for Handwriting Recognition

Abstract: The success of deep learning based models have centered around recent architectures and the availability of large scale annotated data. In this work, we explore these two factors systematically for improving handwritten recognition for scanned off-line document images. We propose a modified CNN-RNN hybrid architecture with a major focus on effective training using: (i) efficient initialization of network using synthetic data for pretraining, (ii) image normalization for slant correction and (iii) domain specific data transformation and distortion for learning important invariances. We perform a detailed ablation study to analyze the contribution of individual modules and present state of art results for the task of unconstrained line and word recognition on popular datasets such as IAM, RIMES and GW.

Improved Road Connectivity by Joint Learning of Orientation and Segmentation

Abstract: Road network extraction from satellite images often produce fragmented road segments leading to road maps unfit for real applications. Pixel-wise classification fails to predict topologically correct and connected road masks due to the absence of connectivity supervision and difficulty in enforcing topological constraints. In this paper, we propose a connectivity task called Orientation Learning, motivated by the human behavior of annotating roads by tracing it at a specific orientation. We also develop a stacked multi-branch convolutional module to effectively utilize the mutual information between orientation learning and segmentation tasks. These contributions ensure that the model predicts topologically correct and connected road masks. We also propose Connectivity Refinement approach to further enhance the estimated road networks. The refinement model is pre-trained to connect and refine the corrupted ground-truth masks and later fine-tuned to enhance the predicted road masks. We demonstrate the advantages of our approach on two diverse road extraction datasets SpaceNet and DeepGlobe. Our approach improves over the state-of-the-art techniques by 9% and 7.5% in road topology metric on SpaceNet and DeepGlobe, respectively.