Match!
Pavan Turaga
Arizona State University
114Publications
24H-index
3,106Citations
Publications 112
Newest
Ground-based sky imaging has won popularity due to its higher temporal and spatial resolution when compared with satellite or air-borne sky imaging systems. Cloud identification and segmentation is the first step in several areas, such as climate research and lately photovoltaic power generation forecast. Cloud-sky segmentation involves several variables including sun position and type and altitude of clouds. We proposed a training-free cloud/sky segmentation based on a threshold that adapts to ...
Source
#1Rajhans Singh (ASU: Arizona State University)H-Index: 1
#2Pavan Turaga (ASU: Arizona State University)H-Index: 24
Last.Martin W. Braun (Intel)H-Index: 3
view all 5 authors...
The advent of generative adversarial networks (GAN) has enabled new capabilities in synthesis, interpolation, and data augmentation heretofore considered very challenging. However, one of the common assumptions in most GAN architectures is the assumption of simple parametric latent-space distributions. While easy to implement, a simple latent-space distribution can be problematic for uses such as interpolation. This is due to distributional mismatches when samples are interpolated in the latent ...
#1Henry Braun (ASU: Arizona State University)H-Index: 6
#2Pavan Turaga (ASU: Arizona State University)H-Index: 24
Last.Cihan Tepedelenlioglu (ASU: Arizona State University)H-Index: 26
view all 6 authors...
Abstract Compressed sensing (CS) allows signals and images to be reliably inferred from undersampled measurements. Exploiting CS allows the creation of new types of high-performance sensors includi...
Source
#1Ankita Shukla (IIIT-D: Indraprastha Institute of Information Technology)H-Index: 6
#2Sarthak Bhagat (IIIT-D: Indraprastha Institute of Information Technology)H-Index: 1
Last.Pavan Turaga (ASU: Arizona State University)H-Index: 24
view all 5 authors...
Learning representations that can disentangle explanatory attributes underlying the data improves interpretabilty as well as provides control on data generation. Various learning frameworks such as VAEs, GANs and auto-encoders have been used in the literature to learn such representations. Most often, the latent space is constrained to a partitioned representation or structured by a prior to impose disentangling. In this work, we advance the use of a latent representation based on a product spac...
Jan 1, 2019 in CVPR (Computer Vision and Pattern Recognition)
#1Suhas Lohit (ASU: Arizona State University)H-Index: 6
#2Qiao Wang (ASU: Arizona State University)H-Index: 3
Last.Pavan Turaga (ASU: Arizona State University)H-Index: 24
view all 3 authors...
1 Citations
Deep generative models like variational autoencoders approximate the intrinsic geometry of high dimensional data manifolds by learning low-dimensional latent-space variables and an embedding function. The geometric properties of these latent spaces has been studied under the lens of Riemannian geometry; via analysis of the non-linearity of the generator function. In new developments, deep generative models have been used for learning semantically meaningful `disentangled' representations; that c...
2 Citations
We present a novel unsupervised domain adaptation (DA) method for cross-domain visual recognition. Though subspace methods have found success in DA, their performance is often limited due to the assumption of approximating an entire dataset using a single low-dimensional subspace. Instead, we develop a method to effectively represent the source and target datasets via a collection of low-dimensional subspaces, and subsequently align them by exploiting the natural geometry of the space of subspac...
1 Citations
Oct 1, 2018 in ICIP (International Conference on Image Processing)
#1Sameeksha Katoch (ASU: Arizona State University)H-Index: 3
#2Pavan Turaga (ASU: Arizona State University)H-Index: 24
Last.Cihan Tepedelenlioglu (ASU: Arizona State University)H-Index: 26
view all 4 authors...
This paper aims to develop a fast dynamic-texture prediction method, using tools from non-linear dynamical modeling, and fast approaches for approximate regression. We consider dynamic textures to be described by patch-level non-linear processes, thus requiring tools such as delay-embedding to uncover a phase-space where dynamical evolution can be more easily modeled. After mapping the observed time-series from a dynamic texture video to its recovered phase-space, a time-efficient approximate pr...
2 CitationsSource
Oct 1, 2018 in ICIP (International Conference on Image Processing)
#1Li-Chi Huang (ASU: Arizona State University)H-Index: 1
#2Kuldeep Kulkarni (CMU: Carnegie Mellon University)H-Index: 7
Last.Pavan Turaga (ASU: Arizona State University)H-Index: 24
view all 6 authors...
Visual Question Answering (VQA) is a complex semantic task requiring both natural language processing and visual recognition. In this paper, we explore whether VQA is solvable when images are captured in a sub-Nyquist compressive paradigm. We develop a series of deep-network architectures that exploit available compressive data to increasing degrees of accuracy, and show that VQA is indeed solvable in the compressed domain. Our results show that there is nominal degradation in VQA performance wh...
1 CitationsSource
Jun 1, 2018 in CVPR (Computer Vision and Pattern Recognition)
#1Suhas Lohit (ASU: Arizona State University)H-Index: 6
#2Ankan Bansal (UMD: University of Maryland, College Park)H-Index: 9
Last.Rama Chellappa (UMD: University of Maryland, College Park)H-Index: 93
view all 6 authors...
A human pose often conveys not only the configuration of the body parts, but also implicit predictive information about the ensuing motion. This dynamic information can benefit vision applications which lack explicit motion cues. The human visual system can easily perceive the dynamic information in still images. However, computational algorithms to infer and utilize it in computer vision applications are limited. In this paper, we propose a probabilistic framework to infer the dynamic informati...
Source
12345678910