Zobrazeno 1 - 10
of 48
pro vyhledávání: '"Sergio Guadarrama"'
Publikováno v:
International Journal of Computational Intelligence Systems, Vol 3, Iss 2 (2010)
This paper contains some naïve reflections on the currently large field of Soft Computing. After some general considerations, and of recalling some successful well known examples, it is posed the relationship between Soft Computing and Machine Intel
Externí odkaz:
https://doaj.org/article/7d9d36475e5d46ef84a5ebf7dbe8b1b8
Autor:
Summer Yue, Ebrahim M. Songhori, Joe Wenjie Jiang, Toby Boyd, Anna Goldie, Azalia Mirhoseini, Sergio Guadarrama
Publikováno v:
Proceedings of the 2022 International Symposium on Physical Design.
Autor:
Oscar Cordón, B. Rosario Campomanes-Álvarez, Sergio Guadarrama, Oscar Ibáñez, Carmen Campomanes-Alvarez
Publikováno v:
Fuzzy Sets and Systems. 318:100-119
Skull–face overlay is the most time-consuming and error-prone stage in craniofacial superimposition, an important skeleton-based forensic identification technique. This task focuses on achieving the best possible overlay of an unknown skull found a
Publikováno v:
Computer Vision – ECCV 2018 ISBN: 9783030012601
ECCV (13)
ECCV (13)
We use large amounts of unlabeled video to learn models for visual tracking without manual human supervision. We leverage the natural temporal coherency of color to create a model that learns to colorize gray-scale videos by copying colors from a ref
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0b6d5d4b2c3830c606a31644cab8dbd4
https://doi.org/10.1007/978-3-030-01261-8_24
https://doi.org/10.1007/978-3-030-01261-8_24
Autor:
Chen Sun, Zbigniew Wojna, Menglong Zhu, Yang Song, Jonathan Huang, Sergio Guadarrama, Alireza Fathi, Ian Fischer, Anoop Korattikara, Kevin Murphy, Vivek Rathod
Publikováno v:
CVPR
The goal of this paper is to serve as a guide for selecting a detection architecture that achieves the right speed/memory/accuracy balance for a given application and platform. To this end, we investigate various ways to trade accuracy for speed and
Publikováno v:
BMVC
We propose a novel approach to automatically produce multiple colorized versions of a grayscale image. Our method results from the observation that the task of automated colorization is relatively easy given a low-resolution version of the color imag
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6df64b932846a906cc290289a05df3e9
Autor:
Jasper Uijlings, Nathan Silberman, Liang-Chieh Chen, Zbigniew Wojna, Sergio Guadarrama, Vittorio Ferrari, Alireza Fathi
Publikováno v:
BMVC
Many machine vision applications require predictions for every pixel of the input image (for example semantic segmentation, boundary detection). Models for such problems usually consist of encoders which decreases spatial resolution while learning a
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 27:541-547
We present a holistic data-driven technique that generates natural-language descriptions for videos. We combine the output of state-of-the-art object and activity detectors with "real-world' knowledge to select the most probable subject-verb-object t
Autor:
Subhashini Venugopalan, Kate Saenko, Sergio Guadarrama, Trevor Darrell, Marcus Rohrbach, Jeff Donahue, Lisa Anne Hendricks
Publikováno v:
CVPR
Models based on deep convolutional networks have dominated recent image interpretation tasks; we investigate whether models which are also recurrent, or "temporally deep", are effective for tasks involving sequences, visual and otherwise. We develop
Publikováno v:
ICRA
In this paper we propose a technique to adapt convolutional neural network (CNN) based object detectors trained on RGB images to effectively leverage depth images at test time to boost detection performance. Given labeled depth images for a handful o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4c78ef1b65caec50912a38b3e228b0a2
https://zenodo.org/record/1271563
https://zenodo.org/record/1271563