R
Rajeev Yasarla
Researcher at Johns Hopkins University
Publications - 35
Citations - 1087
Rajeev Yasarla is an academic researcher from Johns Hopkins University. The author has contributed to research in topics: Computer science & Residual. The author has an hindex of 12, co-authored 30 publications receiving 425 citations. Previous affiliations of Rajeev Yasarla include Indian Institute of Technology Madras.
Papers
More filters
Journal ArticleDOI
JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method
TL;DR: A novel crowd counting network that progressively generates crowd density maps via residual error estimation and the Confidence Guided Deep Residual Counting Network (CG-DRCN) is evaluated on recent complex datasets, and it achieves significant improvements In errors.
Proceedings ArticleDOI
Uncertainty Guided Multi-Scale Residual Learning-Using a Cycle Spinning CNN for Single Image De-Raining
Rajeev Yasarla,Vishal M. Patel +1 more
TL;DR: In this paper, an Uncertainty guided Multi-scale Residual Learning (UMRL) network is proposed to estimate the final de-rained output by learning the rain content at different scales.
Posted Content
Uncertainty Guided Multi-Scale Residual Learning-using a Cycle Spinning CNN for Single Image De-Raining
Rajeev Yasarla,Vishal M. Patel +1 more
TL;DR: The proposed Uncertainty guided Multi-scale Residual Learning (UMRL) network attempts to address the single image de-raining problem by learning the rain content at different scales and using them to estimate the final de-rained output.
Proceedings ArticleDOI
Syn2Real Transfer Learning for Image Deraining Using Gaussian Processes
TL;DR: In this paper, a Gaussian Process-based semi-supervised learning framework is proposed to enable the network in learning to derain using synthetic dataset while generalizing better using unlabeled real-world images.
Proceedings ArticleDOI
Pushing the Frontiers of Unconstrained Crowd Counting: New Dataset and Benchmark Method
TL;DR: In this paper, a confidence-guided deep residual counting network (CG-DRCN) is proposed to progressively generate crowd density maps via residual error estimation, which uses VGG16 as the backbone network and employs density map generated by the final layer as a coarse prediction to refine and generate finer density maps in a progressive fashion using residual learning.