N
Nasser Kehtarnavaz
Researcher at University of Texas at Dallas
Publications - 358
Citations - 9681
Nasser Kehtarnavaz is an academic researcher from University of Texas at Dallas. The author has contributed to research in topics: Image processing & Deep learning. The author has an hindex of 43, co-authored 348 publications receiving 6990 citations. Previous affiliations of Nasser Kehtarnavaz include University of Texas at Austin & MathWorks.
Papers
More filters
Posted Content
Image Segmentation Using Deep Learning: A Survey
Shervin Minaee,Yuri Boykov,Fatih Porikli,Antonio Plaza,Nasser Kehtarnavaz,Demetri Terzopoulos +5 more
TL;DR: A comprehensive review of recent pioneering efforts in semantic and instance segmentation, including convolutional pixel-labeling networks, encoder-decoder architectures, multiscale and pyramid-based approaches, recurrent networks, visual attention models, and generative models in adversarial settings are provided.
Journal ArticleDOI
Image Segmentation Using Deep Learning: A Survey.
Shervin Minaee,Yuri Boykov,Fatih Porikli,Antonio Plaza,Nasser Kehtarnavaz,Demetri Terzopoulos +5 more
TL;DR: A comprehensive review of deep learning-based image segmentation can be found in this article, where the authors investigate the relationships, strengths, and challenges of these DL-based models, examine the widely used datasets, compare performances, and discuss promising research directions.
Proceedings ArticleDOI
UTD-MHAD: A multimodal dataset for human action recognition utilizing a depth camera and a wearable inertial sensor
TL;DR: A freely available dataset, named UTD-MHAD, which consists of four temporally synchronized data modalities, which includes RGB videos, depth videos, skeleton positions, and inertial signals from a Kinect camera and a wearable inertial sensor for a comprehensive set of 27 human actions is described.
Journal ArticleDOI
Real-time human action recognition based on depth motion maps
TL;DR: A l2-regularized collaborative representation classifier with a distance-weighted Tikhonov matrix is employed for action recognition, shown to be computationally efficient allowing it to run in real-time.
Journal ArticleDOI
A survey of depth and inertial sensor fusion for human action recognition
TL;DR: The thrust of this survey is on the utilization of depth cameras and inertial sensors as these two types of sensors are cost-effective, commercially available, and more significantly they both provide 3D human action data.