Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Gabriel L. Oliveira"'
Predicting multiple heterogeneous biological and medical targets is a challenge for traditional deep learning models. In contrast to single-task learning, in which a separate model is trained for each target, multi-task learning (MTL) optimizes a sin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b59665bcc447daffa316ce87600381c7
Autor:
Gabriel L. Oliveira, Jingwei Zhang, Abhinav Valada, Oier Mees, Tayyab Naseer, Noha Radwan, Andreas Eitel, Wolfram Burgard, Johan Vertens
Publikováno v:
Springer Proceedings in Advanced Robotics ISBN: 9783030286187
ISRR
ISRR
In the last decade, deep learning has revolutionized various components of the conventional robot autonomy stack including aspects of perception, navigation and manipulation. There have been numerous advances in perfecting individual tasks such as sc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8970b79241a108e3cf76c4a7ec3640b7
https://doi.org/10.1007/978-3-030-28619-4_3
https://doi.org/10.1007/978-3-030-28619-4_3
Publikováno v:
ICRA
Densely connected networks for classification enable feature exploration and result in state-of-the-art performance on multiple classification tasks. The alternative to dense networks is the residual network which enables feature re-usage. In this wo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0c74342a56854bb1cc7351ff3536489a
https://doi.org/10.1109/icra.2018.8461089
https://doi.org/10.1109/icra.2018.8461089
Publikováno v:
IROS
Robots are expected to operate autonomously in dynamic environments. Understanding the underlying dynamic characteristics of objects is a key enabler for achieving this goal. In this paper, we propose a method for pointwise semantic classification of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::780355a2a1ee976a147d9970812899f5
https://doi.org/10.1109/iros.2017.8206198
https://doi.org/10.1109/iros.2017.8206198
Publikováno v:
ICRA
Visual place recognition under difficult perceptual conditions remains a challenging problem due to changing weather conditions, illumination and seasons. Long-term visual navigation approaches for robot localization should be robust to these dynamic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2ac9dde275e9ba4076cc241e0c2b3d9c
https://doi.org/10.1109/icra.2017.7989305
https://doi.org/10.1109/icra.2017.7989305
Publikováno v:
ICCV
General human action recognition requires understanding of various visual cues. In this paper, we propose a network architecture that computes and integrates the most important visual cues for action recognition: pose, motion, and the raw images. For
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2d2487c82b3902da2c407136bce358da
http://arxiv.org/abs/1704.00616
http://arxiv.org/abs/1704.00616
Publikováno v:
IEEE Transactions on Image Processing. 23:2719-2731
Successful image-based object recognition techniques have been constructed founded on powerful techniques such as sparse representation, in lieu of the popular vector quantization approach. However, one serious drawback of sparse space-based methods
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::64fc2f20a6f24157e49f691f81e9adc4
https://doi.org/10.1109/tip.2014.2317988
https://doi.org/10.1109/tip.2014.2317988
Autor:
Zicheng Liu, Mario F. M. Campos, Erickson R. Nascimento, Antônio Wilson Vieira, Gabriel L. Oliveira
Publikováno v:
Pattern Recognition Letters. 36:221-227
We present a new visual representation for 3D action recognition from sequences of depth maps. In this new representation, space and time axes are divided into multiple segments to define a 4D grid for each depth map sequences. Each cell in the grid
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7445109b75ba12693d6214090da0f998
https://doi.org/10.1016/j.patrec.2013.07.011
https://doi.org/10.1016/j.patrec.2013.07.011
Publikováno v:
Neurocomputing. 120:141-155
In this paper we introduce BRAND—Binary Robust Appearance and Normal Descriptor, a novel descriptor which efficiently combines appearance and geometric information from RGB-D images, that is largely invariant to rotation and scale transformations.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1e92d16e71c8cb5cd0424dab4595002a
https://doi.org/10.1016/j.neucom.2012.08.064
https://doi.org/10.1016/j.neucom.2012.08.064
Publikováno v:
IROS
This paper addresses the problem of road scene segmentation in conventional RGB images by exploiting recent advances in semantic segmentation via convolutional neural networks (CNNs). Segmentation networks are very large and do not currently run at i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8d5664f448ae2315dd38f7bc2ec6563e
https://doi.org/10.1109/iros.2016.7759717
https://doi.org/10.1109/iros.2016.7759717