Federated learning (FL) enables collaborative model training across distributed clients while preserving data privacy. However, the choice of optimizer on both the client and server sides significantly impacts training ...
This thesis explores advanced techniques in the field of audio spoofing detection. With the emergence of high-quality deepfake generation techniques and the vulnerabilities in automatic speaker verification (ASV) systems, ...
Motion forecasting of surrounding agents is fundamental for autonomous systems navigating complex, dynamic environments. This capability enables autonomous vehicles and robots to anticipate the future trajectories of ...
The increasing demand for live online classes, especially in remote and underserved areas, underscores the importance of providing a seamless and high-quality experience to support effective learning. These real-time, ...
Pandey, Anupma; Raghava, Gajendra Pal Singh (Advisor)(IIIT-Delhi, 2025-06-01)
The original CBTOPE method, introduced in 2009, was one of the first approaches for predicting conformational B-cell epitopes using only protein sequence information. While it has been widely adopted in the scientific ...
Tables are the most common form of structured data found in documents. Proper interpretation of such raw tabular data by computer systems remains an open challenge. We take a deep dive into document intelligence - which ...
Siddiqui, Abu Osama; Subramanyam, A V (Advisor)(IIIT-Delhi, 2025-05-21)
Understanding a video from concise summaries is of great importance for various applications such as browsing, retrieval and assistive technologies. In this work, we present unsupervised summarization of videos. Video ...
Serialisation latency is a significant concern in modern cloud applications that leverage the microservice paradigm. A cloud service request typically traverses a sequence of microservices across nodes, increasing latency ...
As enterprises migrate from single-cloud to multi-cloud architecture, they encounter challenges due to geographical dispersion, varying WAN characteristics, and diverse cloud policies. These challenges demand a re-evaluation ...
Object co-part segmentation, which involves segmenting shared objects into meaningful parts in a group of images, is a challenging joint-processing task. Although fully unsupervised deep learning algorithms exist for this ...
Eyewitness accounts are crucial to legal and investigative proceedings, serving as foundational sources for reconstructing events. Agencies typically collect multiple statements to achieve a thorough understanding of the ...
Sepsis and diabetes present intricate medical conditions that present substantial challenges to healthcare systems globally. Timely detection and precise diagnosis are critical in facilitating effective treatment and ...
This thesis investigates the integration of Mixture Density Networks (MDNs) within Federated Learning (FL) frameworks to tackle challenges in data privacy, security, and model robustness, focusing on Automatic Speech ...
As educational assessments migrate to digital platforms, ensuring academic integrity becomes crucial. Traditional plagiarism detection systems struggle to catch instances of intelligent cheating, especially when students ...
In cross-device federated learning (FL) [1], a machine learning model is developed by leveraging communication between a central server and numerous edge device clients. In practical scenarios, the ability of these edge ...
This thesis explores the integration of quaternion algebra into neural network architectures to enhance their efficiency for diverse audio processing tasks. Quaternion-based transformations are employed to achieve structural ...
Taxonomy is a hierarchical structure that deals with knowledge. It can be perceivedas Knowledge graph with all the relations being only ’is-a’. Automatic creation of taxonomies can be achieved by creation scratch, by ...
Speaker verification (SV) focuses on confirming or denying the claimed identity of a speaker. It is a one-to-one comparison between the test utterance and the claimant’s stored reference voice sample. This process is ...
Developing NLP-based techniques to automate tasks in the Indian legal domain is highly demanding due to the enormously increasing volume of legal text documents, intricate legal terminologies, and the need for efficient ...
Documents play a pivotal role in conveying information, serving as integral carriers of knowledge across various domains. Their importance lies in their ability to encapsulate ideas, facts, and insights, thereby facilitating ...