User profiles for R. Venkatesh Babu
R. Venkatesh BabuCDS, Indian Institute of Science, Bangalore, India Verified email at iisc.ac.in Cited by 13492 |
Switching convolutional neural network for crowd counting
…, S Surya, R Venkatesh Babu - Proceedings of the …, 2017 - openaccess.thecvf.com
We propose a novel crowd counting model that maps a given crowd scene to its density.
Crowd analysis is compounded by myriad of factors like inter-occlusion between people due to …
Crowd analysis is compounded by myriad of factors like inter-occlusion between people due to …
Deepfuse: A deep unsupervised approach for exposure fusion with extreme exposure image pairs
…, V Sai Srikar, R Venkatesh Babu - Proceedings of the …, 2017 - openaccess.thecvf.com
We present a novel deep learning architecture for fusing static multi-exposure images.
Current multi-exposure fusion (MEF) approaches use hand-crafted features to fuse input …
Current multi-exposure fusion (MEF) approaches use hand-crafted features to fuse input …
Deligan: Generative adversarial networks for diverse and limited data
…, R Venkatesh Babu - Proceedings of the …, 2017 - openaccess.thecvf.com
A class of recent approaches for generating images, called Generative Adversarial Networks
(GAN), have been used to generate impressively realistic images of objects, bedrooms, …
(GAN), have been used to generate impressively realistic images of objects, bedrooms, …
Data-free parameter pruning for deep neural networks
S Srinivas, RV Babu - arXiv preprint arXiv:1507.06149, 2015 - arxiv.org
Deep Neural nets (NNs) with millions of parameters are at the heart of many state-of-the-art
computer vision systems today. However, recent works have shown that much smaller …
computer vision systems today. However, recent works have shown that much smaller …
Crowdnet: A deep convolutional network for dense crowd counting
Our work proposes a novel deep learning framework for estimating crowd density from static
images of highly dense crowds. We use a combination of deep and shallow, fully …
images of highly dense crowds. We use a combination of deep and shallow, fully …
Deepfix: A fully convolutional neural network for predicting human eye fixations
Understanding and predicting the human visual attention mechanism is an active area of
research in the fields of neuroscience and computer vision. In this paper, we propose DeepFix, …
research in the fields of neuroscience and computer vision. In this paper, we propose DeepFix, …
Training sparse neural networks
…, A Subramanya, R Venkatesh Babu - Proceedings of the …, 2017 - openaccess.thecvf.com
The emergence of Deep neural networks has seen human-level performance on large scale
computer vision tasks such as image classification. However these deep networks typically …
computer vision tasks such as image classification. However these deep networks typically …
Universal source-free domain adaptation
There is a strong incentive to develop versatile learning techniques that can transfer the
knowledge of class-separability from a labeled source domain to an unlabeled target domain in …
knowledge of class-separability from a labeled source domain to an unlabeled target domain in …
Generalize then adapt: Source-free domain adaptive semantic segmentation
… [35] Jogendra Nath Kundu, Naveen Venkat, Ambareesh Revanur, Rahul MV, and R.
Venkatesh Babu. Towards inheritable models for open-set domain adaptation. In CVPR, 2020. …
Venkatesh Babu. Towards inheritable models for open-set domain adaptation. In CVPR, 2020. …
No-reference image quality assessment using modified extreme learning machine classifier
In this paper, we present a machine learning approach to measure the visual quality of
JPEG-coded images. The features for predicting the perceived image quality are extracted by …
JPEG-coded images. The features for predicting the perceived image quality are extracted by …