About
396
Publications
48,870
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
2,450
Citations
Introduction
I work in the area of Signal Processing and its application to Communications and Image Processing. I also work in the area of computer vision and neural networks
Additional affiliations
August 2018 - present
December 2010 - July 2018
Publications
Publications (396)
To prevent unauthorized use of text in images, Scene Text Removal (STR) has become a crucial task. It focuses on automatically removing text and replacing it with a natural, text-less background while preserving significant details such as texture, color, and contrast. Despite its importance in privacy protection, STR faces several challenges, incl...
With the advent of 5G and beyond, the mobile network operator is integrated with edge computing capabilities along with the cloud. This paradigm requires the application at UE to consist of multiple microservices that are appropriately placed at the edge/cloud with dynamic relocation to enhance the overall Quality of Service (QoS) of the applicatio...
Synthetic infrared (IR) scene and target generation is an important computer vision problem as it allows the generation of realistic IR images and targets for training and testing of various applications, such as remote sensing, surveillance, and target recognition. It also helps reduce the cost and risk associated with collecting real-world IR dat...
The groundbreaking performance of transformers in Natural Language Processing (NLP) tasks has led to their replacement of traditional Convolutional Neural Networks (CNNs), owing to the efficiency and accuracy achieved through the self-attention mechanism. This success has inspired researchers to explore the use of transformers in computer vision ta...
There has recently been a great deal of interest in the application of Vision Transformers (ViT) on complex vision-based tasks, particularly in object detection and tracking. However, the ViT backbone is extremely data hungry and requires large amounts of data and computational power to produce the significant results on the various object detectio...
The dual thinking framework considers fast, intuitive processing and slower, logical processing. The perception of dual thinking in vision requires images where inferences from intuitive and logical processing differ. We introduce an adversarial dataset to provide evidence for the dual thinking framework in human vision, which also aids in studying...
Virtual try-on, a rapidly evolving field in computer vision, is transforming e-commerce by improving customer experiences through precise garment warping and seamless integration onto the human body. While existing methods such as TPS and flow address the garment warping but overlook the finer contextual details. In this paper, we introduce a novel...
This study investigates a cooperative user relaying non-orthogonal multiple access (NOMA), in which the near user (NU) works as a relay for the far user (FU) to convey data from the base station (BS). Two situations are explored: (1) No direct link (NDL) between the BS and the FU, and (2) Direct link (DL) between the BS and the FU. The NU communica...
Decoding the intentions of passengers and other road users remains a critical challenge for autonomous vehicles and intelligent transportation systems. Hand gestures are key in these interactions, offering a direct communication channel. Moreover, egocentric videos mimic a first-person perspective, aligning closely with human visual perception. Yet...
Ensemble methods are among the most effective concept‐drift adaptation techniques due to their high learning performance and flexibility. However, they are computationally expensive and pose a challenge in applications involving high‐speed data streams. In this paper, we present a computationally efficient heterogeneous classifier ensemble entitled...
The landscape of wireless communication networks has undergone a breathtaking evolution in recent years, reshaping how we connect, communicate, and interact with the world. This transformation is not merely a technological revolution but a profound societal shift that has touched every aspect of our lives. This book, "Wireless Communication Network...
Plant phenotyping is the study of plants’ physiological, morphological and biochemical traits resulting from their interaction with the environment. These traits (e.g., leaf area, leaf count, tillering, wilting etc.) are crucial in current plant research, focused on improving plant quality i.e., disease resistance, drought resistance and productivi...
Human-centric bilateral teleoperation of robots over a network enables a human controller to perform assistive or corrective control to modify the state of a remotely placed robot. However, the timeliness of control depends on dynamics such as communication latency, bandwidth and quality/quantity of feedback information. In various specific use cas...
Several real-world signals exhibit semi-periodicity in that the period of repetition varies from pulse to pulse about a mean value instead of being constant. Some examples, including among others, are ECG signals, voiced phonemes in speech, carrier jitter in communication etc. In order to model/generate such signals, one can pass a train of discret...
This study investigates the performance of cooperative relaying-based non-orthogonal multiple access (NOMA) with simultaneous wireless information and power transfer. Assuming the battery-assisted non-linear energy harvesting (NL-EH) in which the near user (NU) works as a relay for the far user (FU) to convey data from the base station (BS); two sc...
The bone structure in a chest x-ray creates trouble for a radiologist to examine the organs, manifestation of disease, and hidden tiny abnormalities. Bone suppression in chest x-rays allows better examination of lung fields. This has the potential to improve diagnostic accuracy. Dual-energy subtraction imaging is a standard bone suppression techniq...
Massive machine-type communication (mMTC) has been identified as a key service type in fifth-generation new radio (5G NR) communication systems. The third-generation partnership (3GPP) project, starting with 5G, has introduced grant-free (GF) or configured grant (CG) scheduling for uplink traffic with small data packets to reduce signaling and late...
Device-to-device (D2D) communication in 5G wireless communication networks (WCNs) is gaining popularity, providing higher network capacity and competently meeting the imminent user demands. The achievable capacities can be further scaled up with the use of beamforming in D2D networks. This paper considers a university campus, modelled as a D2D comm...
The foundation of any image processing tasks lies in an efficient representation of visual information and capturing significant information in an image concisely. The objective of this work is to present a novel classification framework that generates a concise representation of an indoor scene using a deep neural network (DNN) in conjunction with...
Face Recognition has been an active area of research but limited work has been done in the domains where the captured face images are of very low resolution, blurred and occluded. The other challenges in the domains like face recognition at a distance or unconstrained face recognition, include pose and expression variations. Additionally, for use c...
Large pretrained models, such as Bert, GPT, and Wav2Vec, have demonstrated great potential for learning representations that are transferable to a wide variety of downstream tasks. It is difficult to obtain a large quantity of supervised data due to the limite d availability of resources and time. In light of this, a significant amount of research...
Biosensors are becoming more common in the healthcare industry, but battery life is a significant barrier to broader adoption. Another concern is that these sensors heavily rely on radio frequency technology, which is dangerous to the human body and the environment. This research presents an optical wireless communication (OWC) based battery-effici...
Convolutional neural networks (CNNs) have become deeper and wider over time. However due to low
computational power, mobile devices or embedded systems cannot use very deep models. Filter pruning
solves this by eliminating redundant filters. Pruning can be performed in a feature dependent or independent
manner. Feature dependent methods require ext...
Compensating for nonlinear effects using digital signal processing (DSP) is complex and computationally expensive in long-haul optical communication systems due to intractable interactions between Kerr nonlinearity, chromatic dispersion (CD), and amplified spontaneous emission (ASE) noise from inline amplifiers. The application of machine learning...
The Internet is expanding with new bandwidth-intensive applications and the network's sensor count, resulting in spectrum constraints. The IEEE 802.15.7 standard specifies optical wireless communication (OWC) as a solution as it utilizes terahertz of unlicensed spectrum, is resistant to radio frequencies, and is more secure to harness. Nevertheless...
Drones or Unmanned Aerial Vehicles (UAVs) usage has increased considerably over the past years. Drones are being
increasingly used for malicious activities in the recent times.
So, there is a need for a good Anti Drone System(ADS). Dataset is a big issue if we are using machine learning techniques
for drone detection. In this paper we present an ap...
Text-to-Image (T2I) ReID has attracted a lot of attention in the recent past. CUHK-PEDES, RSTPReid and ICFG-PEDES are the three available benchmarks to evaluate T2I ReID methods. RSTPReid and ICFG-PEDES comprise of identities from MSMT17 but due to limited number of unique persons, the diversity is limited. On the other hand, CUHK-PEDES comprises o...
Due to rising water quality-related issues, a periodic and continuous monitoring system is mandatory for inland water bodies. Water quality estimation is essential for water resource management and the sustainability of riverine ecosystems. Existing in-situ, field-based, and wet laboratory estimations, although precise and accurate, account for the...
Despite the tremendous progress made by deep learning models in image semantic segmentation, they typically require large annotated examples, and increasing attention is being diverted to problem settings like Few-Shot Learning (FSL) where only a small amount of annotation is needed for generalisation to novel classes. This is especially seen in me...
Increasing attention is being diverted to data-efficient problem settings like Open Vocabulary Semantic Segmentation (OVSS) which deals with segmenting an arbitrary object that may or may not be seen during training. The closest standard problems related to OVSS are Zero-Shot and Few-Shot Segmentation (ZSS, FSS) and their Cross-dataset variants whe...
In Natural Language Processing (NLP), Transformers have already revolutionized the field by utilizing an attention-based encoder-decoder model. Recently, some pioneering works have employed Transformer-like architectures in Computer Vision (CV) and they have reported outstanding performance of these architectures in tasks such as image classificati...
The millimeter-wave (mm-wave) bands enable very large antenna arrays that can generate narrow beams for beamforming and spatial multiplexing. However, directionality introduces beam misalignment and leads to reduced energy efficiency. Thus, employing the narrowest possible beam in a cell may not necessarily imply maximum coverage. The objective of...
Biosensors are becoming more common in the health care industry, but battery life is a significant barrier to broader adoption. Another concern is that these sensors heavily rely on radio frequency technology, which is dangerous to the human body and the environment. This research presents an optical wireless communication (OWC) based battery-effic...
Hyperspectral Image reconstruction from RGB images is a low-cost and convenient alternative to acquiring hyperspectral images directly. The challenge in estimating the spectral response function and using it for generating the hyperspectral image data is addressed effectively by the use of Deep convolutional networks for the task. Deep networks, ho...
Large pretrained models like Bert, GPT, and Wav2Vec have demonstrated their ability to learn transferable representations for various downstream tasks. However, obtaining a substantial amount of supervised data remains a challenge due to resource and time limitations. As a solution, researchers have turned their attention to using large pretrained...
The study highlights the efficiency of various current generation hyperspectral satellites over traditional multispectral images for pollution assessment at Bhalswa landfill in New Delhi using six selected spectral indices and a composite risk score map.
An accurate mathematical ECG model helps comprehend the heart’s workings, which in turn helps identify various heart-related abnormalities. A typical ECG waveform consists of recurrent QRS complexes at almost regular intervals. In the most general scenario, the amplitude, the period after which it repeats, and the shape of the QRS complex may chang...
Compensating for nonlinear effects using digital signal processing (DSP) is complex and computationally expensive in long-haul optical communication systems due to intractable interactions between Kerr nonlinearity, chromatic dispersion (CD), and amplified spontaneous emission (ASE) noise from inline amplifiers. The application of machine learning...