5 Hits in 0.44 sec

DeepGRU: Deep Gesture Recognition Utility [article]

Mehran Maghoumi, Joseph J. LaViola Jr
2019 arXiv   pre-print
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.  ...  For instance, we achieve a recognition accuracy of 84.9% and 92.3% on cross-subject and cross-view tests of the NTU RGB+D dataset respectively, and also 100% recognition accuracy on the UT-Kinect dataset  ...  Portions of this research used the NTU RGB+D Action Recognition Dataset [46] made available by the ROSE Lab at the Nanyang Technological University, Singapore.  ... 
arXiv:1810.12514v4 fatcat:wrkdmeczvbfufmvzhk4ty7vscq

Online Gesture Recognition

F. M. Caputo, S. Burato, G. Pavan, T. Voillemin, H. Wannous, J. P. Vandeborre, M. Maghoumi, E. M. Taranta II, A. Razmjoo, J. J. LaViola Jr., F. Manganaro, S. Pini (+6 others)
2019 Eurographics Workshop on 3D Object Retrieval, EG 3DOR  
Unlike previous contests and benchmarks on trajectory-based gesture recognition, we proposed an online gesture recognition task, not providing pre-segmented gestures, but asking the participants to find  ...  This paper presents the results of the Eurographics 2019 SHape Retrieval Contest track on online gesture recognition.  ...  uDeepGRU: Unsegmented Deep Gesture Recognition Utility by Mehran Maghoumi, Eugene M. Taranta II, Alaleh Razmjoo, Joseph J.  ... 
doi:10.2312/3dor.20191067 fatcat:q7etatrk7rejjddagihm6wkxnu

DeepNAG: Deep Non-Adversarial Gesture Generation [article]

Mehran Maghoumi, Eugene M. Taranta II, Joseph J. LaViola Jr
2020 arXiv   pre-print
Through evaluations, we compare the utility of DeepGAN and DeepNAG against two alternative techniques for training five recognizers using data augmentation over six datasets.  ...  We first discuss a novel, device-agnostic GAN model for gesture synthesis called DeepGAN.  ...  Early on, the simplicity and the recognition power of the recently proposed DeepGRU model [27] inspired us to adopt it as our discriminator.  ... 
arXiv:2011.09149v1 fatcat:jhaqzmowtnd7jifx3dr5sppcau

American Sign Language Words Recognition of Skeletal Videos Using Processed Video Driven Multi-Stacked Deep LSTM

Sunusi Bala Abdullahi, Kosin Chamnongthai
2022 Sensors  
Complex hand gesture interactions among dynamic sign words may lead to misclassification, which affects the recognition accuracy of the ubiquitous sign language recognition system.  ...  LMDHG data set is accessed (13 May 2021) at  ...  The work [32] has similar shape with our approach because this method utilized gestures from ASL dictionary.  ... 
doi:10.3390/s22041406 pmid:35214309 pmcid:PMC8963088 fatcat:fvzz6pn56nblpcvpdtk5edsol4

Multimodal machine translation through visuals and speech

Umut Sulubacak, Ozan Caglayan, Stig-Arne Grönroos, Aku Rouhe, Desmond Elliott, Lucia Specia, Jörg Tiedemann
2020 Machine Translation  
These tasks are distinguished from their monolingual counterparts of speech recognition, image captioning, and video captioning by the requirement of models to generate outputs in a different language.  ...  However, multilingual datasets that augment text with only speech or only images are somewhat less rare than those with videos, given their utility for tasks such as automatic speech recognition and image  ...  Inspired by the successful use of deep neural networks in language modelling (Bengio et al. 2003; Mikolov et al. 2010 ) and automatic speech recognition (Graves et al. 2013) , there has been a plethora  ... 
doi:10.1007/s10590-020-09250-0 fatcat:jod3ghcsnnbipotcqp6sme4lna