Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Luvizon, Diogo C"'
Autor:
Carvalho, Gustavo Sutter P., Luvizon, Diogo C., Neto, Antonio Joia, Pacheco, Andre G. C., Penatti, Otavio A. B.
Generating static novel views from an already captured image is a hard task in computer vision and graphics, in particular when the single input image has dynamic parts such as persons or moving objects. In this paper, we tackle this problem by propo
Externí odkaz:
http://arxiv.org/abs/2110.09380
In this paper, we propose a new Sound Event Classification (SEC) method which is inspired in recent works for out-of-distribution detection. In our method, we analyse all the activations of a generic CNN in order to produce feature representations us
Externí odkaz:
http://arxiv.org/abs/2102.11771
Autor:
Luvizon, Diogo C., Carvalho, Gustavo Sutter P., Santos, Andreza A. dos, Conceicao, Jhonatas S., Flores-Campana, Jose L., Decker, Luis G. L., Souza, Marcos R., Pedrini, Helio, Joia, Antonio, Penatti, Otavio A. B.
In the last few years, several works have tackled the problem of novel view synthesis from stereo images or even from a single picture. However, previous methods are computationally expensive, specially for high-resolution images. In this paper, we a
Externí odkaz:
http://arxiv.org/abs/2011.13317
Autor:
Pinto, Allan, Córdova, Manuel A., Decker, Luis G. L., Flores-Campana, Jose L., Souza, Marcos R., Santos, Andreza A. dos, Conceição, Jhonatas S., Gagliardi, Henrique F., Luvizon, Diogo C., Torres, Ricardo da S., Pedrini, Helio
Publikováno v:
2020 IEEE International Conference on Image Processing (ICIP), Abu Dhabi, United Arab Emirates, 2020, pp. 1621-1625
Stereo vision is a growing topic in computer vision due to the innumerable opportunities and applications this technology offers for the development of modern solutions, such as virtual and augmented reality applications. To enhance the user's experi
Externí odkaz:
http://arxiv.org/abs/2010.02680
Human pose estimation and action recognition are related tasks since both problems are strongly dependent on the human body representation and analysis. Nonetheless, most recent methods in the literature handle the two problems separately. In this wo
Externí odkaz:
http://arxiv.org/abs/1912.08077
3D human pose estimation is frequently seen as the task of estimating 3D poses relative to the root body joint. Alternatively, we propose a 3D human pose estimation method in camera coordinates, which allows effective combination of 2D annotated data
Externí odkaz:
http://arxiv.org/abs/1911.09245
Action recognition and human pose estimation are closely related but both problems are generally handled as distinct tasks in the literature. In this work, we propose a multitask framework for jointly 2D and 3D pose estimation from still images and h
Externí odkaz:
http://arxiv.org/abs/1802.09232
In this paper, we propose an end-to-end trainable regression approach for human pose estimation from still images. We use the proposed Soft-argmax function to convert feature maps directly to joint coordinates, resulting in a fully differentiable fra
Externí odkaz:
http://arxiv.org/abs/1710.02322
Publikováno v:
In Computers & Graphics December 2019 85:15-22
Autor:
Luvizon, Diogo C.1 (AUTHOR) diogo.luvizon@ensea.fr, Picard, David2 (AUTHOR), Tabia, Hedi3 (AUTHOR)
Publikováno v:
International Journal of Computer Vision. Mar2022, Vol. 130 Issue 3, p869-882. 14p.