The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Surat ini mencadangkan pendekatan neurobiologi untuk pengecaman tindakan. Dalam pendekatan ini, tindakan diwakili oleh ciri visual-neuron (VNF) berdasarkan model kuantitatif perwakilan objek dalam korteks visual primata. Teknik pengelasan yang diselia kemudian digunakan untuk mengklasifikasikan tindakan. VNF yang dicadangkan adalah invarian kepada terjemahan affine dan penskalaan objek bergerak sambil mengekalkan kekhususan tindakan. Selain itu, ia teguh kepada ubah bentuk pelakon. Eksperimen pada set data tindakan yang tersedia secara terbuka menunjukkan pendekatan yang dicadangkan mengatasi model pengecaman tindakan konvensional berdasarkan ciri penglihatan komputer.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Salinan
Ning LI, De XU, "Action Recognition Using Visual-Neuron Feature" in IEICE TRANSACTIONS on Information,
vol. E92-D, no. 2, pp. 361-364, February 2009, doi: 10.1587/transinf.E92.D.361.
Abstract: This letter proposes a neurobiological approach for action recognition. In this approach, actions are represented by a visual-neuron feature (VNF) based on a quantitative model of object representation in the primate visual cortex. A supervised classification technique is then used to classify the actions. The proposed VNF is invariant to affine translation and scaling of moving objects while maintaining action specificity. Moreover, it is robust to the deformation of actors. Experiments on publicly available action datasets demonstrate the proposed approach outperforms conventional action recognition models based on computer-vision features.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E92.D.361/_p
Salinan
@ARTICLE{e92-d_2_361,
author={Ning LI, De XU, },
journal={IEICE TRANSACTIONS on Information},
title={Action Recognition Using Visual-Neuron Feature},
year={2009},
volume={E92-D},
number={2},
pages={361-364},
abstract={This letter proposes a neurobiological approach for action recognition. In this approach, actions are represented by a visual-neuron feature (VNF) based on a quantitative model of object representation in the primate visual cortex. A supervised classification technique is then used to classify the actions. The proposed VNF is invariant to affine translation and scaling of moving objects while maintaining action specificity. Moreover, it is robust to the deformation of actors. Experiments on publicly available action datasets demonstrate the proposed approach outperforms conventional action recognition models based on computer-vision features.},
keywords={},
doi={10.1587/transinf.E92.D.361},
ISSN={1745-1361},
month={February},}
Salinan
TY - JOUR
TI - Action Recognition Using Visual-Neuron Feature
T2 - IEICE TRANSACTIONS on Information
SP - 361
EP - 364
AU - Ning LI
AU - De XU
PY - 2009
DO - 10.1587/transinf.E92.D.361
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E92-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 2009
AB - This letter proposes a neurobiological approach for action recognition. In this approach, actions are represented by a visual-neuron feature (VNF) based on a quantitative model of object representation in the primate visual cortex. A supervised classification technique is then used to classify the actions. The proposed VNF is invariant to affine translation and scaling of moving objects while maintaining action specificity. Moreover, it is robust to the deformation of actors. Experiments on publicly available action datasets demonstrate the proposed approach outperforms conventional action recognition models based on computer-vision features.
ER -