Search Results - "Sindagi, Vishwanath"

A survey of recent advances in CNN-based single image crowd counting and density estimation by Sindagi, Vishwanath A., Patel, Vishal M.

“…•Survey on CNN-based approaches for crowd counting and density estimation.•Discussion on recent hand-crafted representations-based methods.•Recently datasets…”
Get full text

JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method by Sindagi, Vishwanath A., Yasarla, Rajeev, Patel, Vishal M.

“…We introduce a new large scale unconstrained crowd counting dataset (JHU-CROWD++) that contains "4,372" images with "1.51 million" annotations. In comparison…”
Get full text

HA-CCN: Hierarchical Attention-Based Crowd Counting Network by Sindagi, Vishwanath A., Patel, Vishal M.

“…Single image-based crowd counting has recently witnessed increased focus, but many leading methods are far from optimal, especially in highly congested scenes…”
Get full text

Multi-Level Bottom-Top and Top-Bottom Feature Fusion for Crowd Counting by Sindagi, Vishwanath, Patel, Vishal

“…Crowd counting presents enormous challenges in the form of large variation in scales within images and across the dataset. These issues are further exacerbated…”
Get full text

KiU-Net: Overcomplete Convolutional Architectures for Biomedical Image and Volumetric Segmentation by Valanarasu, Jeya Maria Jose, Sindagi, Vishwanath A., Hacihaliloglu, Ilker, Patel, Vishal M.

“…Most methods for medical image segmentation use U-Net or its variants as they have been successful in most of the applications. After a detailed analysis of…”
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

Domain Adaptation for Automatic OLED Panel Defect Detection Using Adaptive Support Vector Data Description by Sindagi, Vishwanath A., Srivastava, Sumit

“…Detection of surface defects on organic light emitting diode (OLED) panels pose challenges such as irregular shapes and sizes along with varying textures and…”
Get full text

Syn2Real Transfer Learning for Image Deraining Using Gaussian Processes by Yasarla, Rajeev, Sindagi, Vishwanath A., Patel, Vishal M.

“…Recent CNN-based methods for image deraining have achieved excellent performance in terms of reconstruction error as well as visual quality. However, these…”
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

Semi-Supervised Image Deraining Using Gaussian Processes by Yasarla, Rajeev, Sindagi, Vishwanath A., Patel, Vishal M.

“…Recent CNN-based methods for image deraining have achieved excellent performance in terms of reconstruction error as well as visual quality. However, these…”
Get full text

Pushing the Frontiers of Unconstrained Crowd Counting: New Dataset and Benchmark Method by Sindagi, Vishwanath, Yasarla, Rajeev, Patel, Vishal

“…In this work, we propose a novel crowd counting network that progressively generates crowd density maps via residual error estimation. The proposed method uses…”
Get full text

Generating High-Quality Crowd Density Maps Using Contextual Pyramid CNNs by Sindagi, Vishwanath A., Patel, Vishal M.

“…We present a novel method called Contextual Pyramid CNN (CP-CNN) for generating high-quality crowd density and count estimation by explicitly incorporating…”
Get full text

Unsupervised Restoration of Weather-affected Images using Deep Gaussian Process-based CycleGAN by Yasarla, Rajeev, Sindagi, Vishwanath A., Patel, Vishal M.

“…Existing approaches for restoring weather-degraded images follow a fully-supervised paradigm and they require paired data for training. However, collecting…”
Get full text

High-Quality Facial Photo-Sketch Synthesis Using Multi-Adversarial Networks by Wang, Lidan, Sindagi, Vishwanath, Patel, Vishal

“…Synthesizing face sketches from real photos and its inverse have many applications. However, photo/sketch synthesis remains a challenging problem due to the…”
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

Inverse Attention Guided Deep Crowd Counting Network by Sindagi, Vishwanath A., Patel, Vishal M.

“…In this paper, we address the challenging problem of crowd counting in congested scenes. Specifically, we present Inverse Attention Guided Deep Crowd Counting…”
Get full text

Joint Transmission Map Estimation and Dehazing Using Deep Networks by Zhang, He, Sindagi, Vishwanath, Patel, Vishal M.

“…Single image haze removal is an extremely challenging problem due to its inherent ill-posed nature. Several prior-based and learning-based methods have been…”
Get full text

Image De-Raining Using a Conditional Generative Adversarial Network by Zhang, He, Sindagi, Vishwanath, Patel, Vishal M.

“…Severe weather conditions, such as rain and snow, adversely affect the visual quality of images captured under such conditions, thus rendering them useless for…”
Get full text

MVX-Net: Multimodal VoxelNet for 3D Object Detection by Sindagi, Vishwanath A., Zhou, Yin, Tuzel, Oncel

“…Many recent works on 3D object detection have focused on designing neural network architectures that can consume point cloud data. While these approaches…”
Get full text

CNN-Based cascaded multi-task learning of high-level prior and density estimation for crowd counting by Sindagi, Vishwanath A., Patel, Vishal M.

“…Estimating crowd count in densely crowded scenes is an extremely challenging task due to non-uniform scale variations. In this paper, we propose a novel…”
Get full text