Search Results for author: Mehran Maghoumi

Found 4 papers, 2 papers with code

NVAutoNet: Fast and Accurate 360$^{\circ}$ 3D Perception For Self Driving

no code implementations23 Mar 2023 Trung Pham, Mehran Maghoumi, Wanli Jiang, Bala Siva Sashank Jujjavarapu, Mehdi Sajjadi Xin Liu, Hsuan-Chu Lin, Bor-Jeng Chen, Giang Truong, Chao Fang, Junghyun Kwon, Minwoo Park

The network is robust to sensor mounting variations (within some tolerances) and can be quickly customized for different vehicle types via efficient model fine-tuning thanks of its capability of taking calibration parameters as additional inputs during training and testing.

DeepNAG: Deep Non-Adversarial Gesture Generation

1 code implementation18 Nov 2020 Mehran Maghoumi, Eugene M. Taranta II, Joseph J. LaViola Jr

We find that DeepNAG outperforms DeepGAN in accuracy, training time (up to 17x faster), and realism, thereby opening the door to a new line of research in generator network design and training for gesture synthesis.

Data Augmentation Dynamic Time Warping +2

DeepGRU: Deep Gesture Recognition Utility

1 code implementation30 Oct 2018 Mehran Maghoumi, Joseph J. LaViola Jr

We propose DeepGRU, a novel end-to-end deep network model informed by recent developments in deep learning for gesture and action recognition, that is streamlined and device-agnostic.

Action Recognition Gesture Recognition +2

Cannot find the paper you are looking for? You can Submit a new open access paper.