Subrahmanyam Murala
YOU?
Author Swipe
View article: Former-HGR: Hand Gesture Recognition with Hybrid Feature-Aware Transformer
Former-HGR: Hand Gesture Recognition with Hybrid Feature-Aware Transformer Open
View article: FEDHC: Enhanced Federated Learning with Hessian and Cosine Correlation for Proximal Correction
FEDHC: Enhanced Federated Learning with Hessian and Cosine Correlation for Proximal Correction Open
View article: Bridging Feature and Classifier Divergence for Consistent local-global Collaboration in Personalized Federated Learning
Bridging Feature and Classifier Divergence for Consistent local-global Collaboration in Personalized Federated Learning Open
View article: Fedhmed: Adaptive Progressive Loss and Kl-Divergence Regularization for Federated Heterogeneous Medical Image Classification Tasks
Fedhmed: Adaptive Progressive Loss and Kl-Divergence Regularization for Federated Heterogeneous Medical Image Classification Tasks Open
View article: Phaseformer: Phase-based Attention Mechanism for Underwater Image Restoration and Beyond
Phaseformer: Phase-based Attention Mechanism for Underwater Image Restoration and Beyond Open
Quality degradation is observed in underwater images due to the effects of light refraction and absorption by water, leading to issues like color cast, haziness, and limited visibility. This degradation negatively affects the performance o…
View article: Occlusion Boundary Prediction and Transformer Based Depth-Map Refinement From Single Image
Occlusion Boundary Prediction and Transformer Based Depth-Map Refinement From Single Image Open
Due to the numerous applications of boundary maps and occlusion orientation maps (ORI-maps) in high-level vision problems, accurate estimation of these maps is a crucial task. The existing deep networks employ a single-stream network to es…
View article: Gated Multi-Resolution Transfer Network for Burst Restoration and Enhancement
Gated Multi-Resolution Transfer Network for Burst Restoration and Enhancement Open
Burst image processing is becoming increasingly popular in recent years. However, it is a challenging task since individual burst images undergo multiple degradations and often have mutual misalignments resulting in ghosting and zipper art…
View article: Hyperrealistic Image Inpainting with Hypergraphs
Hyperrealistic Image Inpainting with Hypergraphs Open
Image inpainting is a non-trivial task in computer vision due to multiple possibilities for filling the missing data, which may be dependent on the global information of the image. Most of the existing approaches use the attention mechanis…
View article: A novel feature descriptor for image retrieval by combining modified color histogram and diagonally symmetric co-occurrence texture pattern
A novel feature descriptor for image retrieval by combining modified color histogram and diagonally symmetric co-occurrence texture pattern Open
View article: Vision Based Computing Systems for Healthcare Applications
Vision Based Computing Systems for Healthcare Applications Open
View article: Depth‐based end‐to‐end deep network for human action recognition
Depth‐based end‐to‐end deep network for human action recognition Open
Recognition of human actions from videos can be improved if depth information is available. Depth information certainly helps in segregating foreground motion from the background. Single image depth estimation (SIDE) is a commonly used met…
View article: CANDID: Robust Change Dynamics and Deterministic Update Policy for Dynamic Background Subtraction
CANDID: Robust Change Dynamics and Deterministic Update Policy for Dynamic Background Subtraction Open
Background subtraction in video provides the preliminary information which is essential for many computer vision applications. In this paper, we propose a sequence of approaches named CANDID to handle the change detection problem in challe…
View article: Local Neighborhood Intensity Pattern–A new texture feature descriptor for image retrieval
Local Neighborhood Intensity Pattern–A new texture feature descriptor for image retrieval Open
View article: Multichannel Distributed Local Pattern for Content Based Indexing and\n Retrieval
Multichannel Distributed Local Pattern for Content Based Indexing and\n Retrieval Open
A novel color feature descriptor, Multichannel Distributed Local Pattern\n(MDLP) is proposed in this manuscript. The MDLP combines the salient features\nof both local binary and local mesh patterns in the neighborhood. The\nmulti-distance …
View article: CANDID: Robust Change Dynamics and Deterministic Update Policy for\n Dynamic Background Subtraction
CANDID: Robust Change Dynamics and Deterministic Update Policy for\n Dynamic Background Subtraction Open
Background subtraction in video provides the preliminary information which is\nessential for many computer vision applications. In this paper, we propose a\nsequence of approaches named CANDID to handle the change detection problem in\ncha…
View article: C^2MSNet: A Novel Approach for Single Image Haze Removal
C^2MSNet: A Novel Approach for Single Image Haze Removal Open
Degradation of image quality due to the presence of haze is a very common phenomenon. Existing DehazeNet [3], MSCNN [11] tackled the drawbacks of hand crafted haze relevant features. However, these methods have the problem of color distort…
View article: A Novel Feature Descriptor for Image Retrieval by Combining Modified\n Color Histogram and Diagonally Symmetric Co-occurrence Texture Pattern
A Novel Feature Descriptor for Image Retrieval by Combining Modified\n Color Histogram and Diagonally Symmetric Co-occurrence Texture Pattern Open
In this paper, we have proposed a novel feature descriptors combining color\nand texture information collectively. In our proposed color descriptor\ncomponent, the inter-channel relationship between Hue (H) and Saturation (S)\nchannels in …
View article: Multichannel Distributed Local Pattern for Content Based Indexing and Retrieval
Multichannel Distributed Local Pattern for Content Based Indexing and Retrieval Open
A novel color feature descriptor, Multichannel Distributed Local Pattern (MDLP) is proposed in this manuscript. The MDLP combines the salient features of both local binary and local mesh patterns in the neighborhood. The multi-distance inf…
View article: Edgy salient local binary patterns in inter-plane relationship for image retrieval in Diabetic Retinopathy
Edgy salient local binary patterns in inter-plane relationship for image retrieval in Diabetic Retinopathy Open
In this paper, a novel approach for content based image retrieval (CBIR) in diabetic retinopathy (DR) is proposed. The concept of salient point selection and inter-plane relationship technique is used. Salient points are selected from edgy…
View article: An Expert Local Mesh Correlation Histograms for Biomedical Image Indexing and Retrieval
An Expert Local Mesh Correlation Histograms for Biomedical Image Indexing and Retrieval Open