Zobrazeno 1 - 10
of 35
pro vyhledávání: '"Albert Gordo"'
Autor:
Albert Gordo, Jacqueline Pan, Joanna Bitton, Brian Dolhansky, Caner Hazirbas, Cristian Canton Ferrer
Publikováno v:
CVPR Workshops
This paper introduces a novel "fairness" dataset to measure the robustness of AI models to a diverse set of age, genders, apparent skin tones and ambient lighting conditions. Our dataset is composed of 3,011 subjects and contains over 45,000 videos,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e6d25786e8a9ce4afba59624e26c1fc8
https://doi.org/10.1109/cvprw53098.2021.00258
https://doi.org/10.1109/cvprw53098.2021.00258
Autor:
Caner Hazirbas, Joanna Bitton, Brian Dolhansky, Jacqueline Pan, Albert Gordo, Cristian Canton Ferrer
This paper introduces a novel dataset to help researchers evaluate their computer vision and audio models for accuracy across a diverse set of age, genders, apparent skin tones and ambient lighting conditions. Our dataset is composed of 3,011 subject
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7fe3b4ab98bc96bd08cace79d71fcf3a
http://arxiv.org/abs/2104.02821
http://arxiv.org/abs/2104.02821
Publikováno v:
Computer Vision – ECCV 2020 ISBN: 9783030586034
ECCV (28)
ECCV (28)
Query expansion is a technique widely used in image search consisting in combining highly ranked images from an original query into an expanded query that is then reissued, generally leading to increased recall and precision. An important aspect of q
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::57600d08a972dd2c5280388148e446bc
https://doi.org/10.1007/978-3-030-58604-1_11
https://doi.org/10.1007/978-3-030-58604-1_11
In this paper we present a deployed, scalable optical character recognition (OCR) system, which we call Rosetta, designed to process images uploaded daily at Facebook scale. Sharing of image content has become one of the primary ways to communicate i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::de45109659103e159c5596bbd9e17e51
http://arxiv.org/abs/1910.05085
http://arxiv.org/abs/1910.05085
Autor:
Albert Gordon Omulo
Publikováno v:
Cogent Arts & Humanities, Vol 10, Iss 1 (2023)
Contemporary scholarship overwhelmingly suggests that political elites cannot be trusted to initiate and lead reconciliation processes, for various reasons such as the manipulation of collective memory for political expediency. Accordingly, this pape
Externí odkaz:
https://doaj.org/article/76133e8fb6514e97a77d306eb4b008c1
Autor:
Albert Gordon Omulo
Publikováno v:
Cogent Social Sciences, Vol 9, Iss 1 (2023)
Uhuru Kenyatta, Kenya’s fourth president, ascended to power in 2013 amid a barrage of threats from Western diplomats and an acrimonious relationship with the Western world because of the International Criminal Court (ICC) charges he faced. Yet, by
Externí odkaz:
https://doaj.org/article/6b1038a09f3c4a019347979299b8bd38
Publikováno v:
International Journal of Computer Vision. 113:193-207
The standard approach to recognizing text in images consists in first classifying local image regions into candidate characters and then combining them with high-level word models such as conditional random fields. This paper explores a new paradigm
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0616608ca4b4bb897fe2877b211ea538
https://doi.org/10.1007/s11263-014-0793-6
https://doi.org/10.1007/s11263-014-0793-6
Publikováno v:
Pattern Recognition. 47:3967-3978
In this paper we propose an unsupervised segmentation-free method for word spotting in document images. Documents are represented with a grid of HOG descriptors, and a sliding-window approach is used to locate the document regions that are most simil
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f114e1b8906c6c5a781ec4232fab9d5a
https://doi.org/10.1016/j.patcog.2014.06.005
https://doi.org/10.1016/j.patcog.2014.06.005
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. 36:2552-2566
This paper addresses the problems of word spotting and word recognition on images. In word spotting, the goal is to find all instances of a query word in a dataset of images. In recognition, the goal is to recognize the content of the word image, usu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a78a83fd0f9c0ed4c9b74d3cd80f730c
https://doi.org/10.1109/tpami.2014.2339814
https://doi.org/10.1109/tpami.2014.2339814
Autor:
Diane Larlus, Albert Gordo
Publikováno v:
CVPR
Querying with an example image is a simple and intuitive interface to retrieve information from a visual database. Most of the research in image retrieval has focused on the task of instance-level image retrieval, where the goal is to retrieve images
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1f6250f6c0f959208c7661f14479251c
https://doi.org/10.1109/cvpr.2017.560
https://doi.org/10.1109/cvpr.2017.560