Pathak, Harsh; Govil, Shreedhar; Subramanyam, A V (Advisor)(IIIT-Delhi, 2019-11-16)
With recent advancement in deep learning, it has been made possible to create fake images and videos with near perfect precision. This has led to a growing concern about the possible misuse of this technology in context ...
Arora, Ansh; Subramanyam, A V (Advisor)(IIIT-Delhi, 2022-05)
Re-identification offers a useful tool for non-invasive biometric validation, surveillance, and human-robot interaction in a broad range of applications from crowd traffic management to personalised healthcare. Given the ...
Sharma, Kunal; Chaudhary, Vipin; Subramanyam, A V (Advisor)(IIIT-Delhi, 2019-11)
Video summarization is an important step in analysing video feeds in various scenarios such as surveillance, events and other applications. However, it is a challenging task due to inherent dynamic nature of video due to ...
Code clones, duplicate code fragments sharing similar syntax or semantics, have become increasingly prevalent due to the success of software management tools like GitHub and advancements in Open Source Software (OSS). ...
Dhawan, Siddharth; Subramanyam, A V (Advisor)(IIIT-Delhi, 2019-11-16)
Person re-identi cation is the task of retrieving images of a query person, from a gallery of images obtained from a non-overlapping camera network. Many supervised deep learning methods have been proposed for person ...
The diagnostic process for Autism Spectrum Disorder (ASD) is complex,requiring extensive expertise to integrate information from diverse sourcessuch as parental reports and clinical observations. However, limited accessto ...
Summarization, an essential technique for efficiently condensing extensive textual content into concise versions, has become increasingly valuable in the face of the information deluge characterizing the modern digital ...
Tyagi, Arjun; Subramanyam, A V (Advisor)(IIIT-Delhi, 2020-07-01)
Correlation filter (CF) based tracker often disregard or weakly incorporate the importance of feature channels as well as channel similarity. To address this, we propose a channel-graph regularization correlation filter-based ...
Chaudhuri, Dibyendu Roy; Subramanyam, A V (Advisor)(IIIT-Delhi, 2021-07-01)
Adversarial attacks have been extensively investigated in the recent past. Quite interestingly, a majority of these attacks primarily work in the lp space. In this work, we propose a novel approach for generating adversarial ...
Jain, Harsh Kumar; Subramanyam, A V (Advisor)(IIIT-Delhi, 2020-06-01)
Unsupervised cross-domain Person Re-Identi cation (Re-ID) severely su ers from the domain gap. While di erent works address this issue, bridging domain gap with high-level representation is hard as it comprises of entangled ...
Deva, a pioneering religious technology startup, presents an innovative solution to the evolving needs of Hindu religious practice in the digital age. This report delves into the multifaceted aspects of Deva’s mobile ...
This paper provides an analysis of different serialization libraries on various performance and memory-related metrics. The analysis is done for different scenarios that may occur in a real world setting, in terms of ...
The project focuses on controlling text generation through Large Language Models (LLMs) using advanced prompt engineering and knowledge representation. The project aims to improve controllable citation text generation and ...
The project aims to validate user credentials using blockchain technology, which can help enhance security and trust in the certification process. The platform allows employers to issue certificates to their employees, ...
This B.Tech project at IIIT-Delhi reimagines the traditional course feedback system, ”opine,” by transitioning to a personalized model using Language Models (LLMs). The project is designed for flexibility, allowing easy ...
Maintaining lipid homeostasis, the equilibrium of lipid levels, including fats and cholesterol within cells and organisms, is vital for numerous physiological functions. Disruptions in lipid homeostasis, often spurred by ...
Viyaash, V.; Aggarwal, Shivanshu; Deb, Sujay (Advisor)(IIIT-Delhi, 2023-11-29)
This project report investigates the development of a drone control system using ARM Cortex-M3 based System on Chip (SoC) and the need for indigenously designed SoCs. The objective was to interface the Cortex M3 processor, ...
Despite the growing capabilities of Large Language Models (LLMs) in various domains, their proficiency in addressing domain-specific high-school physics questions remains an unexplored area. In this study, we present a ...
In this research, we attempt to create a state-of-the-art model for the classification of the PTBXL dataset and improve upon already established metrics. Firstly, we use the previous best model, ST-CNN-GAP-5 and introduce ...