Search Results - "VS, Vibashan"

Image Fusion Transformer by Vs, Vibashan, Jose Valanarasu, Jeya Maria, Oza, Poojan, Patel, Vishal M.

“…In image fusion, images obtained from different sensors are fused to generate a single image with enhanced information. In recent years, state-of-the-art…”
Get full text

Mixture of Teacher Experts for Source-Free Domain Adaptive Object Detection by Vs, Vibashan, Oza, Poojan, Sindagi, Vishwanath A., Patel, Vishal M.

“…Unsupervised domain adaptive object detection methods transfer knowledge from the labelled source domain to a visually distinct and unlabeled target domain…”
Get full text

ST-MTL: Spatio-Temporal multitask learning model to predict scanpath while tracking instruments in robotic surgery by Islam, Mobarakol, VS, Vibashan, Lim, Chwee Ming, Ren, Hongliang

“…•Propose a spatio-temporal MTL (ST-MTL) model with a weight-shared encoder and taskaware spatio-temporal decoders.•Introduce a novel way to train the proposed…”
Get full text

Meta-UDA: Unsupervised Domain Adaptive Thermal Object Detection using Meta-Learning by Vs, Vibashan, Poster, Domenick, You, Suya, Hu, Shuowen, Patel, Vishal M.

“…Object detectors trained on large-scale RGB datasets are being extensively employed in real-world applications. However, these RGB-trained models suffer a…”
Get full text

Machine Learning Techniques for the Diagnosis of Attention-Deficit/Hyperactivity Disorder from Magnetic Resonance Imaging: A Concise Review by Periyasamy, R, Vibashan, V, Varghese, George, Aleem, M

“…Background: Attention-deficit/hyperactivity disorder (ADHD) is a neuro-developmental disease commonly seen in children and it is diagnosed via extensive…”
Get full text

AP-MTL: Attention Pruned Multi-task Learning Model for Real-time Instrument Detection and Segmentation in Robot-assisted Surgery by Islam, Mobarakol, Vibashan, V. S., Ren, Hongliang

“…Surgical scene understanding and multi-tasking learning are crucial for image-guided robotic surgery. Training a real-time robotic system for the detection and…”
Get full text

Unsupervised Domain Adaptation of Object Detectors: A Survey by Oza, Poojan, Sindagi, Vishwanath A., VS, Vibashan, Patel, Vishal M.

“…Recent advances in deep learning have led to the development of accurate and efficient models for various computer vision applications such as classification,…”
Get full text

MeGA-CDA: Memory Guided Attention for Category-Aware Unsupervised Domain Adaptive Object Detection by VS, Vibashan, Gupta, Vikram, Oza, Poojan, Sindagi, Vishwanath A., Patel, Vishal M.

“…Existing approaches for unsupervised domain adaptive object detection perform feature alignment via adversarial training. While these methods achieve…”
Get full text

Towards Online Domain Adaptive Object Detection by VS, Vibashan, Oza, Poojan, Patel, Vishal M.

“…Existing object detection models assume both the training and test data are sampled from the same source do-main. This assumption does not hold true when these…”
Get full text

Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection by VS, Vibashan, Oza, Poojan, Patel, Vishal M.

“…Unsupervised Domain Adaptation (UDA) is an effective approach to tackle the issue of domain shift. Specifically, UDA methods try to align the source and target…”
Get full text

Identifying risk factors of intracerebral hemorrhage stability using explainable attention model by Rangaraj, Seshasayi, Islam, Mobarakol, VS, Vibashan, Wijethilake, Navodini, Uppal, Utkarsh, See, Angela An Qi, Chan, Jasmine, James, Michael Lucas, King, Nicolas Kon Kam, Ren, Hongliang

“…Segmentation of intracerebral hemorrhage (ICH) helps improve the quality of diagnosis, draft the desired treatment methods, and clinically observe the…”
Get full text

Open-Set Automatic Target Recognition by Safaei, Bardia, VS, Vibashan, de Melo, Celso M., Hu, Shuowen, Patel, Vishal M.

“…Automatic Target Recognition (ATR) is a category of computer vision algorithms which attempts to recognize targets on data obtained from different sensors. ATR…”
Get full text

Mask-Free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotations by VS, Vibashan, Yu, Ning, Xing, Chen, Qin, Can, Gao, Mingfei, Niebles, Juan Carlos, Patel, Vishal M., Xu, Ran

“…Existing instance segmentation models learn task-specific information using manual mask annotations from base (training) categories. These mask annotations…”
Get full text

LQMFormer: Language-Aware Query Mask Transformer for Referring Image Segmentation by Shah, Nisarg A., VS, Vibashan, Patel, Vishal M.

“…Referring Image Segmentation (RIS) aims to segment objects from an image based on a language description. Recent advancements have introduced transformer-based…”
Get full text

FaceXFormer: A Unified Transformer for Facial Analysis by Narayan, Kartik, VS, Vibashan, Chellappa, Rama, Patel, Vishal M

“…In this work, we introduce FaceXformer, an end-to-end unified transformer model for a comprehensive range of facial analysis tasks such as face parsing,…”
Get full text

PosSAM: Panoptic Open-vocabulary Segment Anything by VS, Vibashan, Borse, Shubhankar, Park, Hyojin, Das, Debasmit, Patel, Vishal, Hayat, Munawar, Porikli, Fatih

“…In this paper, we introduce an open-vocabulary panoptic segmentation model that effectively unifies the strengths of the Segment Anything Model (SAM) with the…”
Get full text

Towards Online Domain Adaptive Object Detection by VS, Vibashan, Oza, Poojan, Patel, Vishal M

“…Existing object detection models assume both the training and test data are sampled from the same source domain. This assumption does not hold true when these…”
Get full text

Entropic Open-set Active Learning by Safaei, Bardia, VS, Vibashan, de Melo, Celso M, Patel, Vishal M

“…Active Learning (AL) aims to enhance the performance of deep models by selecting the most informative samples for annotation from a pool of unlabeled data…”
Get full text

Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection by VS, Vibashan, Oza, Poojan, Patel, Vishal M

“…Unsupervised Domain Adaptation (UDA) is an effective approach to tackle the issue of domain shift. Specifically, UDA methods try to align the source and target…”
Get full text

Open-Set Automatic Target Recognition by Safaei, Bardia, VS, Vibashan, de Melo, Celso M, Hu, Shuowen, Patel, Vishal M

“…Automatic Target Recognition (ATR) is a category of computer vision algorithms which attempts to recognize targets on data obtained from different sensors. ATR…”
Get full text