• Investigating robustness of unsupervised stylegan image restoration 

  Ali, Akbar; Mastan, Indra Deep; Raman, Shanmuganathan (Institute of Electrical and Electronics Engineers, 2025-09-14)

  Recently, generative priors have shown significant improvement for unsupervised image restoration. This study explores the incorporation of multiple loss functions that capture various perceptual and structural aspects of ...
• COT-AD: cotton analysis dataset 

  Ali, Akbar; Vyas, Mahek; Debnath, Soumyaratna; Kamra, Chanda Grover; Khalane, Jaidev Sanjay; Devanesan, Reuben Shibu; Mastan, Indra Deep; Sankaranarayanan, Subramanian; Khanna, Pankaj; Raman, Shanmuganathan (Institute of Electrical and Electronics Engineers, 2025-09-14)

  This paper presents COT-AD, a comprehensive Dataset designed to enhance cotton crop analysis through computer vision. Comprising over 25,000 images captured throughout the cotton growth cycle, with 5,000 annotated images, ...
• Deep unsupervised despeckling with unbiased risk estimation 

  Gupta, Ashutosh; Seelamantula, Chandra Sekhar; Blu, Thierry; Dube, Nitant; Raman, Shanmuganathan (Institute of Electrical and Electronics Engineers, 2025-09-14)

  Despeckling of Synthetic Aperture Radar (SAR) images has seen significant progress in recent years, largely driven by advancements in deep learning techniques. However, many of these approaches face challenges when applied ...
• Bicriteria FPT-approximation algorithms for vertex deletion to bounded degeneracy graphs 

  Inamdar, Tanmay; Kanesh, Lawqueen; Krithika, R.; Mittal, Harshil; Saurabh, Saket (Springer, 2025-07-21)
• Improved 2-approximate shortest paths for close vertex pairs 

  Gupta, Manoj (Institute of Electrical and Electronics Engineers (IEEE), 2025-12-14)
• Model hubs and beyond: analyzing model popularity, performance, and documentation 

  Kadasi, Pritam; Reddy, Sriman; Chaturvedula, Srivathsa Vamsi; Sen, Rudranshu; Saha, Agnish; Sikdar, Soumavo; Sarkar, Sayani; Mittal, Suhani; Jindal, Rohit; Singh, Mayank (2025-06-23)

  With the massive surge in ML models on platforms like Hugging Face, users often lose track and struggle to choose the best model for their downstream tasks, frequently relying on model popularity indicated by download ...
• A Unified browser-based consent management framework 

  Priyadarsini, Gayatri; Bichhawat, Abhishek (Institute of Electrical and Electronics Engineers (IEEE), 2025-04-27)

  Today’s users are concerned about the privacy of their personal or sensitive information on the Web because of the different techniques employed to track their online activities and behavior. Privacy laws like the GDPR, ...
• Spacers and Mismatches-based Algorithm (SMA): G domain prediction and application in human Biology and human health 

  Sanghavi, Hiral M.; Rashmi, Richa; Dasgupta, Anirban; Majumdar, Sharmistha (Springer, 16-10-2023)

  Guanine nucleotide-binding proteins (G proteins) are seen to play an important role in cellular processes such as sensual and visual perception, protein synthesis, vesicular transport, cell growth and differentiation to ...
• Tab-shapley: identifying top-k tabular data quality insights 

  Padala, Manisha; Nagalapatti, Lokesh; Tyagi, Atharv; Narayanam, Ramasuri; Saini, Shiv Kumar (Association for the Advancement of Artificial Intelligence, 2025-02-25)

  We present an unsupervised method for aggregating anomalies in tabular datasets by identifying the top-k tabular data quality insights. Each insight consists of a set of anomalous attributes and the corresponding subsets ...
• Characterizing possible failure modes: insights from LSTM-based streamflow predictions 

  Dubey, Sarth; Bhasme, Pravin; Bhatia, Udit (2025-04-27)
• BloomCoreset: fast coreset sampling using bloom filters for fine-grained self-supervised learning 

  Singh, Prajwal; Vashishtha, Gautam; Mastan, Indra Deep; Raman, Shanmuganathan (Institute of Electrical and Electronics Engineers (IEEE), 2025-04-06)

  The success of deep learning in supervised fine-grained recognition for domain-specific tasks relies heavily on expert annotations. The Open-Set for fine-grained Self-Supervised Learning (SSL) problem aims to enhance ...
• L3D-Pose: lifting pose for 3D Avatars from a single camera in the wild 

  Debnath, Soumyaratna; Katti, Harish; Verma, Shashikant; Raman, Shanmuganathan (2025-04-06)

  While 2D pose estimation has advanced our ability to interpret body movements in animals and primates, it is limited by the lack of depth information, constraining its application range. 3D pose estimation provides a more ...
• Least privilege access for persistent storage mechanisms in web browsers 

  Priyadarsini, Gayatri; Goel, Dishank; Bichhawat, Abhishek (2025-04-28)

  Web applications often include third-party content to personalize a user's online experience. These scripts have unrestricted access to a user's private data stored in the browser's persistent storage, associated with the ...
• Optimized random features for the neural tangent kernel 

  Das, Shrutimoy; Maity, Binita (2025-02-25)
• Online authentication habits of Indian users 

  Choudhary, Pratyush; Das, Subhrajit; Potta, Mukul Paras; Das, Prasuj; Bichhawat, Abhishek (Institute of Electrical and Electronics Engineers (IEEE), 2024-12-19)

  Passwords have been long used as the primary authentication method for web services. Weak passwords used by the users have prompted the use of password management tools and two-factor authentication to ensure better account ...
• SciDQA: a deep reading comprehension dataset over scientific papers 

  Singh, Shruti; Sarkar, Nandan; Cohan, Arman (Association for Computational Linguistics, 2024-11-12)

  Scientific literature is typically dense, requiring significant background knowledge and deep comprehension for effective engagement. We introduce SciDQA, a new dataset for reading comprehension that challenges language ...
• Protection against person-identification from EEG patterns: a blockchain-based approach 

  Mondal, Susmita; Pandey, Pankaj; Miyapuram, Krishna Prasad; Chakraborty, Suchetana (Institute of Electrical and Electronics Engineers (IEEE), 2024-12-19)

  Monitoring brain cognition functions with the help of wearables like Electroencephalography (EEG) sensors has recently become a popular assistive technology for the Internet of Medical Things (IoMT). EEG is popularly ...
• The isomorphism problem of power graphs and a question of cameron 

  Das, Bireswar; Ghosh, Jinia; Kumar, Anant (2024-12-16)
• Web privacy perceptions amongst Indian users 

  Priyadarsini, Gayatri; Saxena, Anshika; Dey, Aditi; Prakriti; Bichhawat, Abhishek (Springer, 2024-12-16)

  While personalized content in the digital world is necessary for a better browsing experience, users knowingly or unknowingly share a lot of data with third-party advertising networks, market analysts, and trackers. Although ...
• On the parameterized complexity of diverse SAT 

  Misra, Neeldhara; Mittal, Harshil; Rai, Ashutosh (2024-12-08)

  We study the Boolean Satisfiability problem (SAT) in the framework of diversity, where one asks for multiple solutions that are mutually far apart (i.e., sufficiently dissimilar from each other) for a suitable notion of ...

View more