Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Shagan Sah"'
Autor:
Shagan Sah, Akash Chintha, Thomastine Sarchet, Akhil Santha, Priyanshu Srivastava, Raymond Ptucha, Nikunj R. Kotecha, Ifeoma Nwogu, Brian P. Landy, Tejaswini Ananthanarayana, Andre Webster, Joseph Panaro
Publikováno v:
ACM Transactions on Accessible Computing. 14:1-30
Many sign languages are bona fide natural languages with grammatical rules and lexicons hence can benefit from machine translation methods. Similarly, since sign language is a visual-spatial language, it can also benefit from computer vision methods
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5edff3524edfb7a40ce62fa0ec4e3019
https://doi.org/10.1145/3477498
https://doi.org/10.1145/3477498
Publikováno v:
Pattern Analysis and Applications. 23:147-159
Recent research in convolutional and recurrent neural networks has fueled incredible advances in video understanding. We propose a video captioning framework that achieves the performance and quality necessary to be deployed in distributed surveillan
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::20f57347fcd9b6bded31d8cfaedd48f8
https://doi.org/10.1007/s10044-018-00770-3
https://doi.org/10.1007/s10044-018-00770-3
Autor:
Shagan Sah
In this paper, various machine learning techniques are discussed. These algorithms are used for many applications which include data classification, prediction, or pattern recognition. The primary goal of machine learning is to automate human assista
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::22a516712973897d4f8f22aab9195841
Autor:
Raymond Ptucha, Andrew M. Michael, Chao Zhang, Shagan Sah, Miguel Dominguez, Felipe Petroski Such, Nathan D. Cahill, Suhas Pillai
Publikováno v:
IEEE Journal of Selected Topics in Signal Processing. 11:884-896
Convolutional Neural Networks (CNNs) have recently led to incredible breakthroughs on a variety of pattern recognition problems. Banks of finite impulse response filters are learned on a hierarchy of layers, each contributing more abstract informatio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::588d479dcf29e5585d979669f0d07255
https://doi.org/10.1109/jstsp.2017.2726981
https://doi.org/10.1109/jstsp.2017.2726981
Publikováno v:
AIPR
Deep learning frameworks have proven to be very effective at tasks like classification, segmentation, detection, and translation. Before being processed by a deep learning model, objects are first encoded into a suitable vector representation. For ex
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::97efea66ac712ffd7fb72615e15e30b4
https://doi.org/10.1109/aipr47015.2019.9174583
https://doi.org/10.1109/aipr47015.2019.9174583
Autor:
Chi Zhang, Aneesh Bhat, Sahaj Gandhi, Raymond Ptucha, Tejaswini Ananthanarayana, Tiantian Yuan, Shagan Sah
Publikováno v:
FG
Sign language is the primary way of communication between deaf people, but the majority of hearing people do not know how to sign. The reliance of deaf people on interpreters is both inconvenient and cost inefficient. Many research groups have experi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9d78685caf2709ad434437fdc31982a9
https://doi.org/10.1109/fg.2019.8756506
https://doi.org/10.1109/fg.2019.8756506
Publikováno v:
ICIP
Humans have an incredible ability to process and understand information from multiple sources such as images, video, text, and speech. Recent success of deep neural networks has enabled us to develop algorithms which give machines the ability to unde
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4086c24a70fb1f7763082725e16db7e7
http://arxiv.org/abs/1903.06275
http://arxiv.org/abs/1903.06275
Publikováno v:
Computational Imaging
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9181381a53917f20ad493de85b402696
https://doi.org/10.2352/issn.2470-1173.2016.19.coimg-152
https://doi.org/10.2352/issn.2470-1173.2016.19.coimg-152
Publikováno v:
Journal of Electronic Imaging. 29:1
Deep learning has been attributed to incredible advances in computer vision, natural language processing, and general pattern understanding. Recent discoveries have enabled efficient vector representations of both visual and written stimuli. Robustly
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f823e97e4441d8ada9f526594163de3e
https://doi.org/10.1117/1.jei.29.2.023013
https://doi.org/10.1117/1.jei.29.2.023013
Publikováno v:
ICIP
Recent work has demonstrated that neural embedding from multiple modalities can be utilized to focus the results of generative adversarial networks. However, little work has been done towards developing a procedure to combine vectors from different m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cebd83fe1bcb3531ec596e11715bcad6
https://doi.org/10.1109/icip.2018.8451439
https://doi.org/10.1109/icip.2018.8451439