13 accepted papers
Foundational Models pretrained on huge amount of data learn representations that evolve across depth, forming a hierarchy of embeddings with distinct semantic content and geometric structure. Contrary to the widespread practice of using only the final layer or shallow mixtures, we show that task-rel…
Cardiovascular diseases (CVDs) are a major cause of death worldwide, taking almost 18 million lives each year. ST Elevation Myocardial Infarction (STEMI) is one of the highest contributors to the same. The immediate 30-day period post-STEMI is critical in judging long-term patient outcomes. Thus, th…
Recent advances in synthetic speech generation technology have facilitated the generation of high-quality synthetic (fake) speech that emulates human voices. These technologies pose a threat of misuse for identity theft and the spread of misinformation. Consequently, the misuse of such powerful tech…
International benchmarking competitions have become fundamental for the comparative performance assessment of image analysis methods. However, little attention has been given to investigating what can be learnt from these competitions. Do they really generate scientific progress? What are common and…
COVID-19 pandemic spreaded across the world in early 2020. It forced many countries to impose lockdown to pre-vent surge in the number of infected cases. There has been a huge impact on social and economic activities worldwide. In this work, we carry out the functional modeling of COVID-19 infection…
Sub-Nyquist sampling is used in modern high-resolution pulse-Doppler radar systems to reduce system resources and improve resolution. Xampling with Doppler focusing is utilized to implement these sub-Nyquist radar systems. Signal recovery involves iterative optimization requiring large computational…
Accurate nuclei identification is an important step in diagnosis of several diseases. The problem is complex due to heterogeneity in structure, color, and texture among the different categories of cells. The problem is further complicated due to overlapped/clustered nuclei. To address these challeng…
Most of the existing question answering models can be largely compiled into two categories: i) open domain question answering models that answer generic questions and use large-scale knowledge base along with the targeted web-corpus retrieval and ii) closed domain question answering models that addr…
There are three fundamental components of teaching a course: course content plan, delivery, and assessment. While teaching methodologies have evolved vis-a`-vis all the above components, signal processing domain has itself evolved significantly over the past few years. It would not be wrong to say t…
Wireless sensor network (WSN) data is prone to huge losses and corruption. Hence, the existing matrix completion algorithms experience high estimation errors in such scenarios. Therefore, a robust matrix completion algorithm is required for WSN data to meet the above challenges. This paper proposes…
Most of the bioinformatics tools used in the analysis of gene expression data require complete data matrices. Missing values in data can adversely influence the downstream analysis for diagnostics and treatment. Several methods to impute missing values in gene data have been developed. However, most…
Motivated with the concept of transform learning and the utility of rational wavelet transform in audio and speech processing, this paper proposes Rational Wavelet Transform Learning in the Statistical sense (RWLS) for natural images. The proposed RWLS design is carried out via lifting framework and…
Wavelet transform is used for efficient signal analysis in various applications. The traditional wavelet system is implemented using integer decimation factors, although frequency tiling offered by rational decimation may better adapt to signal characteristics. In this paper, we propose a design met…