Surveillance camera networks are a useful monitoring infrastructure dat can be used for various visual analytics applications, where high-level inferences and predictions could be made based on target tracking across teh ...
Sinha, Mitali; Deb, Sujay (Advisor)(IIIT-Delhi, 2022-04)
In recent years, as multi-core processors are emerging as a solution to the limitations of power scaling, the software domain is also experiencing a surge of compute and data-intensive applications. These applications are ...
The swift escalation in hostile content on the web and specifically on Online Social Media (OSM) has lately become a matter of concern that we must tackle. The situation worsens to a whole different level with recent events ...
Curbing hate speech is undoubtedly a major challenge for online microblogging platforms like Twitter. While there have been studies around hate speech detection, it is not clear how hate speech finds its way into an online ...
Sarcasm is a pervading linguistic phenomenon and highly challenging to explain due to
its subjectivity, lack of context and deeply-felt opinion. In the multimodal setup, sarcasm
is conveyed through the incongruity between ...
The COVID19 pandemic, a public health emergency which broke out globally in December 2019 and is still going on, has put us all into an unprecedented situation where there are strict limitations on physical social interaction ...
Entity matching (EM) has been one of the long-standing challenges in databases domain. Tra- ditionally, the approaches for EM focuses on developing matching algorithms and works on pairwise similarity between attributes. ...
In 2015, Unicode introduced five different skin tone modifiers, that could be applied to the existing emojis that denoted humans. In this project, we analyze how people pose certain personalities using emoji skin colour ...
Ever since the 2014 Lok Sabha election, social media platforms such as Twitter, Facebook etc.have become a vital part of election campaigns in India with political parties investing heavily in the expansion of their ...
This project aims to characterize the role of the NaMo app in shaping political discourse on social media. The Narendra Modi app, or the NaMo app, is the official app ofthe Prime Minister of India. It has an inbuilt social ...
Most of the Reinforcement Learning(RL) tasks in today's world involve high dimensional data. Training deep reinforcement learning based models is already a very challenging task and varies lot with the choice of hyper ...
A lot of people are learning English around the world and take assessments every year. With the rise of candidates taking these assessments and the shortage of qualified experts rating these assessments, there is a need ...
Data is expanding at an unimaginable rate, and with this development comes the responsibility of the quality of data. Data Quality refers to the relevance of the information present and helps in various operations like ...
The analysis of flow cytometry data requires identification of cell clusters. This clustering is done manually by applying gating techniques and by analyzing the plot scatter across each dimension. Since all of this is ...
With recent advancements in AI algorithms, data processing for AI applications is primarily done in a cloud-based data center with deep-learning models that require massive computing capacity. The decision-making process ...
There are concerns that the ability of language models (LMs) to generate high quality synthetic text can be misused to launch spam, dis-information, or propaganda. Therefore, the re-search community is actively working on ...
Health care systems all around the world have an ever-growing burden of intensive care on them. Complications such as sepsis, organ failure and shock contribute to a large portion of the deaths. However they can be treated ...
Explanation of predictions made by black-box deep learning models has been rather challenging,
especially when neither the model details nor its training data are known. Various techniques based
on shadow-model have been ...
This study focuses on understanding content and coherence for Automated Oral Proficiency Scoring and Feedback Generating System in the context of spontaneous speech of non-native(L2) English learners. We aim to understand ...
Clique counting is a well studied problem in low memory models like graph streaming. There are algorithms which provide good space complexity bounds for general graphs. For constant pass, approximation algorithms counting ...