Home > Research > Publications & Outputs > Multi-Branch with Attention Network for Hand-Ba...

Links

Text available via DOI:

View graph of relations

Multi-Branch with Attention Network for Hand-Based Person Recognition

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

Multi-Branch with Attention Network for Hand-Based Person Recognition. / Baisa, Nathanael L.; Williams, Bryan; Rahmani, Hossein et al.
2022 26th International Conference on Pattern Recognition, ICPR 2022. IEEE, 2022. p. 727-732 (Proceedings - International Conference on Pattern Recognition; Vol. 2022-August).

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Baisa, NL, Williams, B, Rahmani, H, Angelov, P & Black, S 2022, Multi-Branch with Attention Network for Hand-Based Person Recognition. in 2022 26th International Conference on Pattern Recognition, ICPR 2022. Proceedings - International Conference on Pattern Recognition, vol. 2022-August, IEEE, pp. 727-732, 26th International Conference on Pattern Recognition, ICPR 2022, Montreal, Canada, 21/08/22. https://doi.org/10.1109/ICPR56361.2022.9956555

APA

Baisa, N. L., Williams, B., Rahmani, H., Angelov, P., & Black, S. (2022). Multi-Branch with Attention Network for Hand-Based Person Recognition. In 2022 26th International Conference on Pattern Recognition, ICPR 2022 (pp. 727-732). (Proceedings - International Conference on Pattern Recognition; Vol. 2022-August). IEEE. https://doi.org/10.1109/ICPR56361.2022.9956555

Vancouver

Baisa NL, Williams B, Rahmani H, Angelov P, Black S. Multi-Branch with Attention Network for Hand-Based Person Recognition. In 2022 26th International Conference on Pattern Recognition, ICPR 2022. IEEE. 2022. p. 727-732. (Proceedings - International Conference on Pattern Recognition). Epub 2022 Aug 21. doi: 10.1109/ICPR56361.2022.9956555

Author

Baisa, Nathanael L. ; Williams, Bryan ; Rahmani, Hossein et al. / Multi-Branch with Attention Network for Hand-Based Person Recognition. 2022 26th International Conference on Pattern Recognition, ICPR 2022. IEEE, 2022. pp. 727-732 (Proceedings - International Conference on Pattern Recognition).

Bibtex

@inproceedings{f2f7856606e44b818a9ac843f330d209,
title = "Multi-Branch with Attention Network for Hand-Based Person Recognition",
abstract = "In this paper, we propose a novel hand-based person recognition method for the purpose of criminal investigations since the hand image is often the only available information in cases of serious crime such as sexual abuse. Our proposed method, Multi-Branch with Attention Network (MBA-Net), incorporates both channel and spatial attention modules in branches in addition to a global (without attention) branch to capture global structural information for discriminative feature learning. The attention modules focus on the relevant features of the hand image while suppressing the irrelevant backgrounds. In order to overcome the weakness of the attention mechanisms, equivariant to pixel shuffling, we integrate relative positional encodings into the spatial attention module to capture the spatial positions of pixels. Extensive evaluations on two large multi-ethnic and publicly available hand datasets demonstrate that our proposed method achieves state-of-the-art performance, surpassing the existing hand-based identification methods. The source code is available at https://github.com/nathanlem1/MBA-Net.",
author = "Baisa, {Nathanael L.} and Bryan Williams and Hossein Rahmani and Plamen Angelov and Sue Black",
year = "2022",
month = nov,
day = "29",
doi = "10.1109/ICPR56361.2022.9956555",
language = "English",
series = "Proceedings - International Conference on Pattern Recognition",
publisher = "IEEE",
pages = "727--732",
booktitle = "2022 26th International Conference on Pattern Recognition, ICPR 2022",
note = "26th International Conference on Pattern Recognition, ICPR 2022 ; Conference date: 21-08-2022 Through 25-08-2022",

}

RIS

TY - GEN

T1 - Multi-Branch with Attention Network for Hand-Based Person Recognition

AU - Baisa, Nathanael L.

AU - Williams, Bryan

AU - Rahmani, Hossein

AU - Angelov, Plamen

AU - Black, Sue

PY - 2022/11/29

Y1 - 2022/11/29

N2 - In this paper, we propose a novel hand-based person recognition method for the purpose of criminal investigations since the hand image is often the only available information in cases of serious crime such as sexual abuse. Our proposed method, Multi-Branch with Attention Network (MBA-Net), incorporates both channel and spatial attention modules in branches in addition to a global (without attention) branch to capture global structural information for discriminative feature learning. The attention modules focus on the relevant features of the hand image while suppressing the irrelevant backgrounds. In order to overcome the weakness of the attention mechanisms, equivariant to pixel shuffling, we integrate relative positional encodings into the spatial attention module to capture the spatial positions of pixels. Extensive evaluations on two large multi-ethnic and publicly available hand datasets demonstrate that our proposed method achieves state-of-the-art performance, surpassing the existing hand-based identification methods. The source code is available at https://github.com/nathanlem1/MBA-Net.

AB - In this paper, we propose a novel hand-based person recognition method for the purpose of criminal investigations since the hand image is often the only available information in cases of serious crime such as sexual abuse. Our proposed method, Multi-Branch with Attention Network (MBA-Net), incorporates both channel and spatial attention modules in branches in addition to a global (without attention) branch to capture global structural information for discriminative feature learning. The attention modules focus on the relevant features of the hand image while suppressing the irrelevant backgrounds. In order to overcome the weakness of the attention mechanisms, equivariant to pixel shuffling, we integrate relative positional encodings into the spatial attention module to capture the spatial positions of pixels. Extensive evaluations on two large multi-ethnic and publicly available hand datasets demonstrate that our proposed method achieves state-of-the-art performance, surpassing the existing hand-based identification methods. The source code is available at https://github.com/nathanlem1/MBA-Net.

U2 - 10.1109/ICPR56361.2022.9956555

DO - 10.1109/ICPR56361.2022.9956555

M3 - Conference contribution/Paper

AN - SCOPUS:85138498461

T3 - Proceedings - International Conference on Pattern Recognition

SP - 727

EP - 732

BT - 2022 26th International Conference on Pattern Recognition, ICPR 2022

PB - IEEE

T2 - 26th International Conference on Pattern Recognition, ICPR 2022

Y2 - 21 August 2022 through 25 August 2022

ER -