Abstract

Intelligent vehicle systems require a deep understanding of the interplay between road conditions, surrounding entities, and the ego vehicle's driving behavior for safe and efficient navigation. This is particularly critical in developing countries where traffic situations are often dense and unstructured with heterogeneous road occupants. Existing datasets, predominantly geared towards structured and sparse traffic scenarios, fall short of capturing the complexity of driving in such environments. To fill this gap, we present IDD-X, a large-scale dual-view driving video dataset. With 697K bounding boxes, 9K important object tracks, and 1-12 objects per video, IDD-X offers comprehensive ego-relative annotations for multiple important road objects covering 10 categories and 19 explanation label categories. The dataset also incorporates rearview information to provide a more complete representation of the driving environment. We also introduce custom-designed deep networks aimed at multiple important object localization and per-object explanation prediction. Overall, our dataset and introduced prediction models form the foundation for studying how road conditions and surrounding entities affect driving behavior in complex traffic situations.

Abstract

In addition to innate human intelligence, having access to extensive context and world knowledge is a crucial factor that aids in comprehending natural language, making it smooth and effortless to understand words with multiple meanings for humans. Although machines lack intrinsic intelligence, their capacity to learn language can greatly improve with access to more data, which serves as valuable context. In Natural Language Processing (NLP), the task of identifying and attributing the right sense of a word in a given context is called Word Sense Disambiguation (WSD). WSD, as a sub-task, plays a crucial role in several NLP applications such as Machine Translation. Every language has a set of words that have multiple senses. Sanskrit, one of the ancient and classical languages of the Indian subcontinent is no exception to this. Like many other languages with a rich literary tradition, Sanskrit features a multitude of polysemous words. However, it is essential to acknowledge that the data used to train machine models on Sanskrit is considerably less compared to European and a few other Indian languages. Consequently, the task of disambiguating word senses in Sanskrit presents a highly complex challenge for machines, especially when considering the unique and rich nature of its literary language. The purpose of this paper is to delineate the potential areas where the infusion of additional data can enhance language learning, through a manual error analysis taxonomy focused on the Bhagavadgītā. Our analysis will delve into the translation outcomes produced by Google Translate, which is considered the state-of-the-art tool for handling Sanskrit and other languages with limited available resources.

Abstract

Random Numbers are widely employed in cryptography and security applications. This paper presents a novel approach to generate high-quality random bitstreams by harnessing the inherent noise properties of ring oscillators. We implemented ring oscillators with varying numbers of stages (3, 5, and 7), different geometries and different startup voltages in Cadence and recorded their total output power, which includes the cumulative noise effects. Subsequently, we exported these power measurements to MATLAB, where we applied a Fast Fourier Transform (FFT)-based technique to extract the total noise characteristics for each ring oscillator. Using the obtained noise data, we generated separate random bitstreams of 10 million bits for the 3-stage, 5-stage, and 7-stage ring oscillators. The final random bitstream, consisting of 10 million bits, was created by performing a bitwise XOR operation on the bitstreams generated by each ring oscillator. The degree of randomness of the generated bitstreams was assessed using the NIST 800-22 statistical test suite. Remarkably, the final random bitstream exhibited strong robustness and suitability for cryptographic applications. This innovative approach leverages the noise properties of ring oscillators to create reliable random bitstreams, offering potential applications in secure communications and cryptography. The results highlight the feasibility of using ring oscillators as noise sources for random bit generation and underscore their effectiveness in meeting stringent randomness criteria

Abstract

How we move and interact with our surroundings can reveal a lot about us as an individual. This study delves into the interplay of music, movement, and individual identity within the framework of embodied cognition. Drawing inspiration from Carlson et al. (2020)’s work, which showcased remarkably high accuracy in identifying individuals based on free-form dance movements in a marker-based setting, our investigation extends their work into two novel contexts: markerless-choreographic and marker-based-dyadic dance settings. In the choreographic setting, professional dancers perform identical routines in a markerless setting. In the dyadic setting, individuals danced with a partner. We found that the dancer identification accuracy was at least two times better than the chance level in the choreographic setting and notably high accuracy in the dyadic setting. These results showcase the robustness of Carlson et al. (2020)’s method in generalizing to new settings and the presence of motoric fingerprints in choreographic as well as dyadic settings.

Abstract

Abstract—Safety-critical real-time systems are conventionally designed to meet specific hard real-time deadline requirements. Many applications in such systems consist of task chains, which exhibit complex temporal dependencies based on the activation rates of the tasks. As a result, there has been an increasing interest in analyzing the age of data (i.e., the time elapsed since the data was first updated) that propagates through the task chains as an important system performance parameter. Transient faults in safety-critical systems can lead to undesirable consequences. One of the most common methods used for fault tolerance in such systems is checkpointing. However, the interference due to checkpointing can significantly impact the data age, reducing the predictability of the system’s performance. This paper proposes an analytical framework for calculating the data age in real-time task chains with checkpointing for transient faults in both single-core and multi-core platforms. The proposed analysis has been validated by comparing it with extensive simulations of the execution of real-time task chain- based systems under faults. It shows comparable data age values with low time complexity.

Abstract

We review the main applications of machine learning models that are not fully supervised in particle physics, i.e., clustering, anomaly detection, detector simulation, and unfolding. Unsupervised methods are ideal for anomaly detection tasks—machine learning models can be trained on background data to identify deviations if we model the background data precisely. The learning can also be partially unsupervised when we can provide some information about the anomalies at the data level. Generative models are useful in speeding up detector simulations—they can mimic the computationally intensive task without large resources. They can also efficiently map detector-level data to parton-level data (i.e., data unfolding). In this review, we focus on interesting ideas and connections and briefly overview the underlying techniques wherever necessary.

Abstract

Abstract This document contains the details of the authors' submission to the proceedings of SemEval 2024's Task 8: Multigenerator, Multidomain, and Multilingual Black-Box Machine-Generated Text Detection Subtask A (monolingual) and B. Detection of machine-generated text is becoming an increasingly important task, with the advent of large language models (LLMs). In this paper, we lay out how using weighted averages of RoBERTa layers lets us capture information about text that is relevant to machine-generated text detection

Abstract

We present a hypergraph coloring based approach to pliable index coding (PICOD). We represent the given PICOD problem using a hypergraph consisting of m messages as vertices and the request-sets of the n clients as hyperedges. A conflict- free coloring of a hypergraph is an assignment of colors to its vertices so that each hyperedge contains a uniquely colored vertex. We show that various parameters arising out of conflict- free colorings (and some new variants) of the PICOD hypergraph result in new upper bounds for the optimal PICOD length. Using these new upper bounds, we show the existence of single-request PICOD schemes with length O(log2 Γ), where Γ is the maximum number of hyperedges overlapping with any hyperedge. For the t-request PICOD scenario, we show the existence of PICOD schemes of length max(O(log Γ log m), O(t log m)), under some mild conditions on the graph parameters. These results improve upon earlier work in general. We also show that our achievable lengths in the t-request case are asymptotically optimal, up to a multiplicative factor of log t. Our existence results are accompanied by randomized constructive algorithms, which have complexity polynomial in the parameters of the PICOD problem, in expectation or with high probability. Index Terms—Index Coding, Pliabl

Abstract

In the natural course of spoken language, individuals often engage in thinking and self-correction during speech production. These instances of interruption or correction are commonly referred to as disfluencies. When preparing data for subsequent downstream NLP tasks, these linguistic elements can be systematically removed, or handled as required, to enhance data quality. In this study, we present a comprehensive research on disfluencies in Indian languages. Our approach involves not only annotating real-world conversation transcripts but also conducting a detailed analysis of linguistic nuances inherent to Indian languages that are necessary to consider during annotation. Additionally, we introduce a robust algorithm for the synthetic generation of disfluent data. This algorithm aims to facilitate more effective model training for the identification of disfluencies in real-world conversations, thereby contributing to the advancement of disfluency research in Indian languages

Abstract

India's education sector faces a significant challenge due to its linguistic diversity, hindering inclusivity. The dominance of English on the internet underscores the critical need for translating educational content into Indian languages to enhance accessibility. Although Speech-to-Speech Machine Translation (SSMT) technologies exist, their deficiency in reproducing intonation results in monotonous translations, diminishing audience engagement and interest in the content. To address this issue, this paper demonstrates an SSMT application with a Text-to-Speech (TTS) architecture capable of incorporating stress into synthesized speech to give a more engaging experience. The SSMT pipeline also has components like a stress classifier that captures the stress in the source speech and allows it to be utilized during speech generation. The application takes in a speech file and gives a translated speech file with stress transferred from the source.