Carlos Antônio Caetano Júnior Motion-Based Representations for Activity Recognition Tese PhD Universidade Federal of Minas Gerais, 2020. @phdthesis{CarlosCaetano:2020:PhD,
title = {Motion-Based Representations for Activity Recognition},
author = {Carlos Antônio Caetano Júnior},
year = {2020},
date = {2020-01-27},
school = {Universidade Federal of Minas Gerais},
abstract = {In this dissertation we propose four different representations based on motion information for activity recognition. The first is a spatiotemporal local feature descriptor that extracts a robust set of statistical measures to describe motion patterns. This descriptor measures meaningful properties of co-occurrence matrices and captures local space-time characteristics of the motion through the neighboring optical flow magnitude and orientation. The second, is the proposal of a compact novel mid-level representation based on co-occurrence matrices of codewords. This representation expresses the distribution of the features at a given offset over feature codewords from a pre-computed codebook and encodes global structures in various local region-based features. The third representation, is the proposal of a novel temporal stream for two-stream convolutional networks that employs images computed from the optical flow magnitude and orientation to learn the motion in a better and richer manner. The method applies simple non-linear transformations on the vertical and horizontal components of the optical flow to generate input images for the temporal stream. Finally, the forth is a novel skeleton image representation to be used as input of convolutional neural networks (CNNs). The proposed approach encodes the temporal dynamics by explicitly computing the magnitude and orientation values of the skeleton joints. Moreover, the representation has the advantage of combining the use of reference joints and a tree structure skeleton, incorporating different spatial relationships between the joints and preserving important spatial relations. The experimental evaluations carried out on challenging well-known activity recognition datasets (KTH, UCF Sports, HMDB51, UCF101, NTU RGB+D 60 and NTU RGB+D 120) demonstrated that the proposed representations achieved better or similar accuracy results in comparison to the state of the art, indicating the suitability of our approaches as video representations.},
keywords = {},
pubstate = {published},
tppubtype = {phdthesis}
}
In this dissertation we propose four different representations based on motion information for activity recognition. The first is a spatiotemporal local feature descriptor that extracts a robust set of statistical measures to describe motion patterns. This descriptor measures meaningful properties of co-occurrence matrices and captures local space-time characteristics of the motion through the neighboring optical flow magnitude and orientation. The second, is the proposal of a compact novel mid-level representation based on co-occurrence matrices of codewords. This representation expresses the distribution of the features at a given offset over feature codewords from a pre-computed codebook and encodes global structures in various local region-based features. The third representation, is the proposal of a novel temporal stream for two-stream convolutional networks that employs images computed from the optical flow magnitude and orientation to learn the motion in a better and richer manner. The method applies simple non-linear transformations on the vertical and horizontal components of the optical flow to generate input images for the temporal stream. Finally, the forth is a novel skeleton image representation to be used as input of convolutional neural networks (CNNs). The proposed approach encodes the temporal dynamics by explicitly computing the magnitude and orientation values of the skeleton joints. Moreover, the representation has the advantage of combining the use of reference joints and a tree structure skeleton, incorporating different spatial relationships between the joints and preserving important spatial relations. The experimental evaluations carried out on challenging well-known activity recognition datasets (KTH, UCF Sports, HMDB51, UCF101, NTU RGB+D 60 and NTU RGB+D 120) demonstrated that the proposed representations achieved better or similar accuracy results in comparison to the state of the art, indicating the suitability of our approaches as video representations. |
Victor Hugo Cunha de Melo; Jesimon Barreto Santos; Carlos Antonio Caetano Junior; Jessica Sena; Otavio A B Penatti; William Robson Schwartz Object-based Temporal Segment Relational Network for Activity Recognition Inproceedings Em: Conference on Graphic, Patterns and Images (SIBGRAPI), pp. 1-8, 2018. @inproceedings{DeMelo:2018:SIBGRAPI,
title = {Object-based Temporal Segment Relational Network for Activity Recognition},
author = {Victor Hugo Cunha de Melo and Jesimon Barreto Santos and Carlos Antonio Caetano Junior and Jessica Sena and Otavio A B Penatti and William Robson Schwartz},
year = {2018},
date = {2018-09-21},
booktitle = {Conference on Graphic, Patterns and Images (SIBGRAPI)},
pages = {1-8},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Carlos Antonio Caetano Junior; Jefersson A dos Santos; William Robson Schwartz Statistical Measures from Co-occurrence of Codewords for Action Recognition Inproceedings Em: VISAPP 2018 - International Conference on Computer Vision Theory and Applications, pp. 1-8, 2018. @inproceedings{Caetano:2018:VISAPP,
title = {Statistical Measures from Co-occurrence of Codewords for Action Recognition},
author = {Carlos Antonio Caetano Junior and Jefersson A dos Santos and William Robson Schwartz},
url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/VISAPP_2018_CarlosCaetano.pdf},
year = {2018},
date = {2018-01-27},
booktitle = {VISAPP 2018 - International Conference on Computer Vision Theory and Applications},
pages = {1-8},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Igor Leonardo Oliveira Bastos; Larissa Rocha Soares; William Robson Schwartz Pyramidal Zernike Over Time: A spatiotemporal feature descriptor based on Zernike Moments Inproceedings Em: Iberoamerican Congress on Pattern Recognition (CIARP 2017), pp. 77-85, 2017. @inproceedings{Bastos:2017:CIARP,
title = {Pyramidal Zernike Over Time: A spatiotemporal feature descriptor based on Zernike Moments},
author = {Igor Leonardo Oliveira Bastos and Larissa Rocha Soares and William Robson Schwartz},
url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/PZOT_camera_ready.pdf},
year = {2017},
date = {2017-11-07},
booktitle = {Iberoamerican Congress on Pattern Recognition (CIARP 2017)},
pages = {77-85},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Carlos Antonio Caetano Junior; Victor Hugo Cunha de Melo; Jefersson Alex dos Santos; William Robson Schwartz Activity Recognition based on a Magnitude-Orientation Stream Network Inproceedings Em: Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 1-8, 2017. @inproceedings{Caetano:2017:SIBGRAPI,
title = {Activity Recognition based on a Magnitude-Orientation Stream Network},
author = {Carlos Antonio Caetano Junior and Victor Hugo Cunha de Melo and Jefersson Alex dos Santos and William Robson Schwartz},
url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/paper_2017_SIBGRAPI_Caetano.pdf},
year = {2017},
date = {2017-01-01},
booktitle = {Conference on Graphics, Patterns and Images (SIBGRAPI)},
pages = {1-8},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Carlos Antonio Caetano Junior; Jefersson A dos Santos; William Robson Schwartz Optical Flow Co-occurrence Matrices: A Novel Spatiotemporal Feature Descriptor Inproceedings Em: IAPR International Conference on Pattern Recognition (ICPR), pp. 1-6, 2016. @inproceedings{Caetano:2016:ICPR,
title = {Optical Flow Co-occurrence Matrices: A Novel Spatiotemporal Feature Descriptor},
author = {Carlos Antonio Caetano Junior and Jefersson A dos Santos and William Robson Schwartz},
url = {http://smartsenselab.dcc.ufmg.br/wp-content/uploads/2019/02/ICPR2016.pdf},
year = {2016},
date = {2016-12-13},
booktitle = {IAPR International Conference on Pattern Recognition (ICPR)},
pages = {1-6},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
|
Dados
