Abstract

India’s linguistic diversity is a testament to the cultural richness of the subcontinent, with 22 officially recognized languages, each possessing its unique script and identity. In this context, the need for efficient Optical Character Recognition (OCR) tools tailored to the complexities of these languages is paramount. IndicOCR is introduced as an innovative OCR pipeline designed to address this challenge. This paper aims to shed light on the capabilities of IndicOCR, underlining its role in bridging the gap between India’s linguistic heritage and the ever-expanding digital world. Finally, IndicOCR1 is a powerful tool for inclusivity, preservation, and progress in a linguistically diverse society.

Abstract

With the recent advancements, organizations have brought data to the forefront of their digital transformation journeys. Financial services industry is also moving towards adopting data-driven strategies for improved and faster decision making and providing enhanced customer experience. While advances generally in Artificial Intelligence (AI) and specifically in Machine Learning (ML) have fueled a lot of analytics, it is largely restricted to structured data as it is well organized and is easy to work with. This tutorial presents the opportunities to unlock the potential in unstructured documents in financial domain. These forms of data are more challenging to interpret, but can deliver a more comprehensive and holistic understanding of the bigger picture. While there are challenges around processing such document, ability to quickly make decisions by leveraging such data can provide differentiated value propositions and competitive benefits. This tutorial start with select problems & challenges in Document AI space and use cases involving such documents, show the business opportunities present and describe the technical challenges involved. Subsequently, we discuss techniques and algorithms for several document processing requirements and real world applications. References

Abstract

Large-scale capturing of real-world scenes as 3D point clouds (e.g., using LIDAR scanning) generates billions of points that are challenging to visualize. High storage requirements prevent the quick and easy inspection of captured datasets on user-grade hardware. The fastest real-time rendering methods are limited by the available GPU memory and render only around 1 billion points interactively. We show that we can achieve state-of-the-art in both while simultaneously supporting datasets that surpass the capabilities of other methods. We present an on-the-fly point cloud decompression scheme that tightly integrates with software rasterization to reduce on-chip memory requirements by more than 4×. Our method compresses geometry losslessly and provides high visual quality at real-time framerates. We use a GPU-friendly, clipped Huffman encoding for compression. Point clouds are divided into equal-sized batches, which are Huffman-encoded independently. Batches are further subdivided to form easy-to-consume streams of data for massively parallel execution. The compressed point clouds are stored in an access-aware manner to achieve coherent GPU memory access

Abstract

Phase-unwrapping (PU) is a critical signal processing step used in fields such as radar, sonar, and laser technology. This paper presents a faster and more efficient VLSI architecture for implementing the phase-unwrapping algorithm on FPGA platforms. To evaluate the effectiveness of the proposed FPGAbased VLSI architecture for the phase-unwrapping algorithm in chest wall vibration sensing, we compared its performance with both a PYNQ board implementation and an equivalent software solution. The results are compared in terms of speed, resource utilization, and power consumption. Additionally, prototypes were developed on both the ZedBoard and PYNQ board, and the outcomes were physically verified. The proposed VLSI architecture achieves nearly 70× and 111× speed-up compared to software-based solutions and PYNQ board implementations, respectively.

Abstract

These days, autonomous vehicles are equipped with a variety of sensors that allow them to sense their environment and control several functions. In particular, if a child is left alone in a parked car, the passenger occupancy detection system can detect it. Traditionally, camera sensors have been used to detect vehicle occupancy. Cameras perform well in bright light but struggle in low light. To address these limitations, we opted to detect vehicle occupancy using millimeter-wave radar which operates accurately regardless of lighting conditions. Figure 1 shows the pipeline of the proposed algorithm. Figure 2 depicts the setup for Vehicle occupancy Detection with FMCW radar, specifically the Texas Instruments AWR1843 booster pack evaluation board, which operates in the 76-81 GHz band. Figure 3 depicts vehicle occupancy detection images.

Abstract

Semantic Labels-Aware Transformer Model for Searching over a Large Collection of Lecture-Slides K. V. Jobin1 Anand Mishra2 C. V. Jawahar1 1IIIT Hyderabad 2 IIT Jodhpur {jobin.kv@research., jawahar@}iiit.ac.in mishra@iitj.ac.in https://jobinkv.github.io/lecsd Abstract Massive Open Online Courses (MOOCs) enable easy access to many educational materials, particularly lecture slides, on the web. Searching through them based on user queries becomes an essential problem due to the availability of such vast information. To address this, we present Lec- ture Slide Deck Search Engine – a model that supports nat- ural language queries and hand-drawn sketches and per- forms searches on a large collection of slide images on com- puter science topics. This search engine is trained using a novel semantic label-aware transformer model that extracts the semantic labels in the slide images and seamlessly en- codes them with the visual cues from the slide images and textual cues from the natural language query. Further, to study the problem in a challenging setting, we introduce a novel dataset, namely the Lecture Slide Deck (LecSD) Dataset containing 54K slide images from the Data Struc- ture, Computer Networks, and Optimization courses and provide associated manual annotation for the query in the form of natural language or hand-drawn sketch. The pro- posed Lecture Slide Deck Search Engine outperforms the competitive baselines and achieves nearly 4% superior Re- call@1 on an absolute scale compared to the state-of-the- art approach. We firmly believe that this work will open up promising directions for improving the accessibility and us- ability of educational resources, enabling students and edu- cators to find and utilize lecture materials more effectively.

Abstract

A method for identifying a soundtrack for a digital book by automatically aligning the digital book and the soundtrack with a movie using a movie adaptation technique is provided. The method includes (i) receiving media content through a user device that includes the digital book, the soundtrack, and the movie,(ii) segmenting (a) the chapters of the digital book into paragraph segments,(b) the movie into scene boundaries, and (c) tracks of the soundtrack into cohesive track segments,(iii) aligning the scene boundaries with the paragraph segments to generate aligned paragraph segments,(iv) aligning a background soundtracks of the movie with the cohesive track segments of the soundtrack using a majority key and a minority key of the cohesive track segments and the background soundtracks to generate aligned cohesive track segments and (v) aligning the aligned paragraph segments with the aligned cohesive

Abstract

We study information leakage through guesswork, the minimum expected number of guesses required to guess a random variable. In particular, we define maximal guesswork leakage as the multiplicative decrease, upon observing Y, of the guesswork of a randomized function of X, maximized over all such randomized functions. We also study a pointwise form of the leakage which captures the leakage due to the release of a single realization of Y. We also study these two notions of leakage with oblivious (or memoryless) guessing. We obtain closed-form expressions for all these leakage measures, with the exception of one. Specifically, we are able to obtain closed-form expression for maximal guesswork leakage for the binary erasure source only; deriving expressions for arbitrary sources appears challenging. Some of the consequences of our results are - a connection between guesswork and differential privacy and a new operational interpretation to maximal α -leakage in terms of guesswork.

Abstract

Big data analytics in the Internet of Things (IoT) realm demands a substantial volume of data for training models and making reliable inferences. In most cases, data availability is scarce, and synthetic data is generated from real-world data to meet the needs. Yet, there remains a risk of exposing private and sensitive information without proper data security measures. In this article, we aim to develop a secure collaborative model learning methodology trained on synthetic data, ensuring data availability, privacy and confidentiality through differential privacy and key management. Additionally, we propose a secured inference framework where user data, sent for inference to the deployed model is protected, preserving both the accuracy of the predicted data and the security of the input data. Our experimental evaluation, along with performance and security analysis, exhibits that our approach offers accuracy and scalability while maintaining privacy and security.

Abstract

—With the rise of Big data generated by Internet of Things (IoT) smart devices, there is an increasing need to leverage its potential while protecting privacy and maintaining confidentiality. Privacy and confidentiality in Big Data aims to enable data analysis and machine learning on large-scale datasets without compromising the dataset sensitive information. Usually current Big Data analytics models either efficiently achieves privacy or confidentiality. In this article, we aim to design a novel blockchain-enabled secured collaborative machine learning approach that provides privacy and confidentially on large scale datasets generated by IoT devices. Blockchain is used as secured platform to store and access data as well as to provide immutability and traceability. We also propose an efficient approach to obtain robust machine learning model through use of cryptographic techniques and differential privacy in which the data among involved parties is shared in a secured way while maintaining privacy and confidentiality of the data. The experimental evaluation along with security and performance analysis show that the proposed approach provides accuracy and scalability without compromising the privacy and security.