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

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

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.

Abstract

Research over several decades has demonstrated modest and moderately consistent relationships between personality and music preference, but has primarily relied on self-reported data and lab-based listening experiments. Recently, music preference research has begun to take advantage of online listening data from platforms such as Spotify and Last.fm to more directly link listening behavior to individual differences. This study extends this new line of research by investigating the associations between naturally occurring music listening behaviors and personality traits, utilizing listening data acquired from Last.fm. We examined social-tagging data by extracting tags related to musical genre and emotion from frequently listened tracks of each participant and clustered them into broader categories to study their association with OCEAN traits. We further evaluated preferences in terms of co-occurring genre and emotion tags and analyzed listening patterns over time to better understand natural patterns of listening as they relate to personality. Our results corroborated previous research, demonstrating a positive correlation between Extraversion and high-arousal music genres such as hip-hop and rap, while Openness was linked with jazz sub-genres. Several novel and nuanced associations were unveiled, such as Extraversion being associated with nostalgic hip-hop and jazz, and Neuroticism correlating with calming music from unconventional genres like shoegaze. Finally, we comment on existing music preference frameworks and their relevance to naturally occurring music listening behavior.

Abstract

The people with Major Depressive Disorder (MDD) exhibit the symptoms of tonal variations in their speech compared to the healthy counterparts. However, these tonal variations not only confine to the state of MDD but also on the language, which has unique tonal patterns. This work analyzes automatic speech-based depression detection across two languages, English and Malayalam, which exhibits distinctive prosodic and phonemic characteristics. We propose an approach that utilizes speech data collected along with self-reported labels from participants reading sentences from IViE corpus, in both English and Malayalam. The IViE corpus consists of five sets of sentences: simple sentences, WH-questions, questions without morphosyntactic markers, inversion questions and coordinations, that can naturally prompt speakers to speak in different tonal patterns. Convolutional Neural Networks (CNNs) are employed for detecting depression from speech. The CNN model is trained to identify acoustic features associated with depression in speech, focusing on both languages. The model's performance is evaluated on the collected dataset containing recordings from both depressed and non-depressed speakers, analyzing its effectiveness in detecting depression across the two languages. Our findings and collected data could contribute to the development of language-agnostic speech-based depression detection systems, thereby enhancing accessibility for diverse populations.

Abstract

Preserving the privacy of preferences (or rewards) of a sequential decision-making agent when decisions are observable is crucial in many physical and cybersecurity domains. For instance, in wildlife monitoring, forest rangers must conduct surveillance without revealing animal locations to poachers. This paper addresses privacy preservation in planning over a sequence of actions in MDPs, where the reward function represents the preference structure to be protected. Observers can use Inverse RL (IRL) to learn these preferences, making this a challenging task. Current research on Differential Privacy (DP) in this setting fails to ensure a lower bound on the minimum expected reward and offers theoretical guarantees that are inadequate against IRL-based observers. To bridge this gap, we propose a novel approach rooted in the theory of deception. Deception includes two models: dissimulation (hiding the truth) and simulation (showing the wrong). As our first contribution, we theoretically demonstrate a significant privacy leak in the current dissimulation-based method. Our second contribution is a novel RL-based planning algorithm that uses simulation to effectively address these privacy concerns while ensuring a guarantee on the expected reward. Through experimentation on multiple benchmark problems, we show that our proposed approach outperforms existing methods in preserving the privacy of reward functions.