B. V. K. Vijaya Kumar
YOU?
Author Swipe
View article: Comparison of Conventional to the <i>Vedic</i> Mathematics System: Through Statistical Analysis of Pre and Post Test Result
Comparison of Conventional to the <i>Vedic</i> Mathematics System: Through Statistical Analysis of Pre and Post Test Result Open
Any business, like mining, where observation and procedure call for a lot of fast calculations, must prioritize speed and accuracy. India has a wealth of minerals, and government agencies such as NMDC actively participate in the process of…
View article: Towards More Accurate Fake Detection on Images Generated from Advanced Generative and Neural Rendering Models
Towards More Accurate Fake Detection on Images Generated from Advanced Generative and Neural Rendering Models Open
The remarkable progress in neural-network-driven visual data generation, especially with neural rendering techniques like Neural Radiance Fields and 3D Gaussian splatting, offers a powerful alternative to GANs and diffusion models. These m…
View article: Writing on dirty flash memory: Combating inter-cell interference via coding with side information
Writing on dirty flash memory: Combating inter-cell interference via coding with side information Open
High-density flash memories suffer from inter-cell interference (ICI) which threatens the reliability of stored data. In order to cope with the ICI problem, we propose a channel coding scheme with channel state information of flash memorie…
View article: Fundus GAN - GAN-based Fundus Image Synthesis for Training Retinal Image Classifiers
Fundus GAN - GAN-based Fundus Image Synthesis for Training Retinal Image Classifiers Open
Two major challenges in applying deep learning to develop a computer-aided diagnosis of fundus images are the lack of enough labeled data and legal issues with patient privacy. Various efforts are being made to increase the amount of data …
View article: The Structural, Electronic and Optical Properties of Hydrofluorinated Germanene (GeH1-xFx): A First-Principles Study
The Structural, Electronic and Optical Properties of Hydrofluorinated Germanene (GeH1-xFx): A First-Principles Study Open
The structural, electronic, and optical properties of hydrofluorinated germanene have been studied with different occupancy ratios of fluorine and hydrogen. The hybridization of H-1s and Ge-4p orbitals in hydrogenated germanene and F-2p an…
View article: Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection
Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection Open
Weakly Supervised Object Detection (WSOD) has emerged as an effective tool to train object detectors using only the image-level category labels. However, without object-level labels, WSOD detectors are prone to detect bounding boxes on sal…
View article: Towards occlusion-aware multifocal displays
Towards occlusion-aware multifocal displays Open
The human visual system uses numerous cues for depth perception, including disparity, accommodation, motion parallax and occlusion. It is incumbent upon virtual-reality displays to satisfy these cues to provide an immersive user experience…
View article: Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification
Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification Open
Although a significant progress has been witnessed in supervised person re-identification (re-id), it remains challenging to generalize re-id models to new domains due to the huge domain gaps. Recently, there has been a growing interest in…
View article: Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection
Comprehensive Attention Self-Distillation for Weakly-Supervised Object Detection Open
Weakly Supervised Object Detection (WSOD) has emerged as an effective tool to train object detectors using only the image-level category labels. However, without object-level labels, WSOD detectors are prone to detect bounding boxes on sal…
View article: Design and Development of Techniques for Equipment Health Monitoring System
Design and Development of Techniques for Equipment Health Monitoring System Open
Machines in Industries are often subjected to enormous wear and tear, which if unnoticed, may lead to production delays and increased maintenance cost. Machines must be able to analyse and provide statistics about its health, so that preve…
View article: Deep Classification Network for Monocular Depth Estimation
Deep Classification Network for Monocular Depth Estimation Open
Monocular Depth Estimation is usually treated as a supervised and regression problem when it actually is very similar to semantic segmentation task since they both are fundamentally pixel-level classification tasks. We applied depth increm…
View article: Confidence Regularized Self-Training
Confidence Regularized Self-Training Open
Recent advances in domain adaptation show that deep self-training presents a powerful means for unsupervised domain adaptation. These methods often involve an iterative process of predicting on target domain and then taking the confident p…
View article: Attention Control with Metric Learning Alignment for Image Set-based Recognition
Attention Control with Metric Learning Alignment for Image Set-based Recognition Open
This paper considers the problem of image set-based face verification and identification. Unlike traditional single sample (an image or a video) setting, this situation assumes the availability of a set of heterogeneous collection of order…
View article: Permutation-invariant Feature Restructuring for Correlation-aware Image Set-based Recognition
Permutation-invariant Feature Restructuring for Correlation-aware Image Set-based Recognition Open
We consider the problem of comparing the similarity of image sets with variable-quantity, quality and un-ordered heterogeneous images. We use feature restructuring to exploit the correlations of both inner$\&$inter-set images. Specifically…
View article: Dependency-aware Attention Control for Unconstrained Face Recognition with Image Sets
Dependency-aware Attention Control for Unconstrained Face Recognition with Image Sets Open
This paper targets the problem of image set-based face verification and identification. Unlike traditional single media (an image or video) setting, we encounter a set of heterogeneous contents containing orderless images and videos. The i…
View article: RELIABLE CLOUD INPUT UNDER GUIDE DISCLOSURE
RELIABLE CLOUD INPUT UNDER GUIDE DISCLOSURE Open
Improved databases that the data uses as a technical for many applications. In recent days, previous attempts have been completely improved in reducing communication conversations. In the firmware system soon, the basic problem is the priv…
View article: Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training
Domain Adaptation for Semantic Segmentation via Class-Balanced Self-Training Open
Recent deep networks achieved state of the art performance on a variety of semantic segmentation tasks. Despite such progress, these models often face challenges in real world `wild tasks' where large difference between labeled training/so…
View article: Simultaneous Edge Alignment and Learning
Simultaneous Edge Alignment and Learning Open
Edge detection is among the most fundamental vision problems for its role in perceptual grouping and its wide applications. Recent advances in representation learning have led to considerable improvements in this area. Many state of the ar…
View article: DATA ACROSS IN MALIGNANT SECURITY GUARANTEES IN PUBLIC NETS
DATA ACROSS IN MALIGNANT SECURITY GUARANTEES IN PUBLIC NETS Open
Within this work, we present a normal data lineage framework LIME for data flow across multiple entities that take two characteristic, principal roles. In some instances, identification from the leaker is thanks to forensic techniques, but…
View article: One Network to Solve Them All --- Solving Linear Inverse Problems using Deep Projection Models
One Network to Solve Them All --- Solving Linear Inverse Problems using Deep Projection Models Open
While deep learning methods have achieved state-of-the-art performance in many challenging inverse problems like image inpainting and super-resolution, they invariably involve problem-specific training of the networks. Under this approach,…
View article: Inter-track interference mitigation with two-dimensional variable equalizer for bit patterned media recording
Inter-track interference mitigation with two-dimensional variable equalizer for bit patterned media recording Open
The increased track density in bit patterned media recording (BPMR) causes increased inter-track interference (ITI), which degrades the bit error rate (BER) performance. In order to mitigate the effect of the ITI, signals from multiple tra…
View article: FLM volume 814 Cover and Front matter
FLM volume 814 Cover and Front matter Open
An abstract is not available for this content so a preview has been provided. As you have access to this content, a full PDF is available via the ‘Save PDF’ action button.
View article: 2^16 shades of gray: high bit-depth projection using light intensity control
2^16 shades of gray: high bit-depth projection using light intensity control Open
Projectors create grayscale images by outputting a series of bitplanes or binary images within a short time period. While this technique works well for projecting low bit-depth (8-bit) images, it becomes infeasible for high bit-depth (say,…
View article: FE-SViT
FE-SViT Open
As a promising bio-cryptographic technique, the fuzzy extractor seamlessly binds biometrics and cryptography for template protection and key generation. However, most existing methods hardly solve the following issues simultaneously: (1) F…
View article: Locally rewritable codes for resistive memories
Locally rewritable codes for resistive memories Open
We propose locally rewritable codes (LWC) for resistive memories inspired by\nlocally repairable codes (LRC) for distributed storage systems. Small values of\nrepair locality of LRC enable fast repair of a single failed node since the\nlos…
View article: On Order-Constrained Transitive Distance Clustering
On Order-Constrained Transitive Distance Clustering Open
We consider the problem of approximating order-constrained transitive distance (OCTD) and its clustering applications. Given any pairwise data, transitive distance (TD) is defined as the smallest possible "gap" on the set of paths connecti…
View article: Performance Analysis of 1310/1490 Nm Demultiplexer based on Multimode Interference Coupler for PON
Performance Analysis of 1310/1490 Nm Demultiplexer based on Multimode Interference Coupler for PON Open
The design and analysis of a 1310/1490-nm demultiplexer based on Multimode Interference (MMI) coupler for Passive Optical Networks (PON) has been studied in this paper. Numerical simulations with finite difference Beam Propagation Method (…