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
A previsão do movimento humano sempre foi um tópico de pesquisa interessante em visão computacional e robótica. Significa prever movimentos humanos no futuro condicionados a sequências históricas tridimensionais do esqueleto humano. Os algoritmos de previsão existentes geralmente dependem de extensos dados de captura de movimento anotados ou não anotados e não são adaptativos. Este artigo aborda o problema da previsão do movimento humano em poucos quadros, no espírito do recente progresso na aprendizagem múltipla. Mais precisamente, a nossa abordagem baseia-se na percepção de que alcançar uma previsão precisa depende de uma expressão suficientemente linear no espaço latente a partir de alguns dados de treino no espaço de observação. Para conseguir isso, propomos o Modelo de Variável Latente do Processo Gaussiano Regressivo (RGPLVM) que introduz uma nova função de kernel regressiva para o treinamento do modelo. Ao fazer isso, nosso modelo produz um mapeamento linear do espaço de dados de treinamento para o espaço latente, ao mesmo tempo que transforma efetivamente a previsão do movimento humano no espaço físico para a análise de regressão linear no equivalente do espaço latente. A comparação com duas abordagens de aprendizagem de predição de movimento (a meta-aprendizagem de última geração e o clássico LSTM-3LR) demonstra que nosso GPLVM melhora significativamente o desempenho de predição em várias ações no regime de tamanho de amostra pequeno.
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.
Copiar
Xin JIN, Jia GUO, "Regressive Gaussian Process Latent Variable Model for Few-Frame Human Motion Prediction" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 10, pp. 1621-1626, October 2023, doi: 10.1587/transinf.2023PCP0001.
Abstract: Human motion prediction has always been an interesting research topic in computer vision and robotics. It means forecasting human movements in the future conditioning on historical 3-dimensional human skeleton sequences. Existing predicting algorithms usually rely on extensive annotated or non-annotated motion capture data and are non-adaptive. This paper addresses the problem of few-frame human motion prediction, in the spirit of the recent progress on manifold learning. More precisely, our approach is based on the insight that achieving an accurate prediction relies on a sufficiently linear expression in the latent space from a few training data in observation space. To accomplish this, we propose Regressive Gaussian Process Latent Variable Model (RGPLVM) that introduces a novel regressive kernel function for the model training. By doing so, our model produces a linear mapping from the training data space to the latent space, while effectively transforming the prediction of human motion in physical space to the linear regression analysis in the latent space equivalent. The comparison with two learning motion prediction approaches (the state-of-the-art meta learning and the classical LSTM-3LR) demonstrate that our GPLVM significantly improves the prediction performance on various of actions in the small-sample size regime.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2023PCP0001/_p
Copiar
@ARTICLE{e106-d_10_1621,
author={Xin JIN, Jia GUO, },
journal={IEICE TRANSACTIONS on Information},
title={Regressive Gaussian Process Latent Variable Model for Few-Frame Human Motion Prediction},
year={2023},
volume={E106-D},
number={10},
pages={1621-1626},
abstract={Human motion prediction has always been an interesting research topic in computer vision and robotics. It means forecasting human movements in the future conditioning on historical 3-dimensional human skeleton sequences. Existing predicting algorithms usually rely on extensive annotated or non-annotated motion capture data and are non-adaptive. This paper addresses the problem of few-frame human motion prediction, in the spirit of the recent progress on manifold learning. More precisely, our approach is based on the insight that achieving an accurate prediction relies on a sufficiently linear expression in the latent space from a few training data in observation space. To accomplish this, we propose Regressive Gaussian Process Latent Variable Model (RGPLVM) that introduces a novel regressive kernel function for the model training. By doing so, our model produces a linear mapping from the training data space to the latent space, while effectively transforming the prediction of human motion in physical space to the linear regression analysis in the latent space equivalent. The comparison with two learning motion prediction approaches (the state-of-the-art meta learning and the classical LSTM-3LR) demonstrate that our GPLVM significantly improves the prediction performance on various of actions in the small-sample size regime.},
keywords={},
doi={10.1587/transinf.2023PCP0001},
ISSN={1745-1361},
month={October},}
Copiar
TY - JOUR
TI - Regressive Gaussian Process Latent Variable Model for Few-Frame Human Motion Prediction
T2 - IEICE TRANSACTIONS on Information
SP - 1621
EP - 1626
AU - Xin JIN
AU - Jia GUO
PY - 2023
DO - 10.1587/transinf.2023PCP0001
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2023
AB - Human motion prediction has always been an interesting research topic in computer vision and robotics. It means forecasting human movements in the future conditioning on historical 3-dimensional human skeleton sequences. Existing predicting algorithms usually rely on extensive annotated or non-annotated motion capture data and are non-adaptive. This paper addresses the problem of few-frame human motion prediction, in the spirit of the recent progress on manifold learning. More precisely, our approach is based on the insight that achieving an accurate prediction relies on a sufficiently linear expression in the latent space from a few training data in observation space. To accomplish this, we propose Regressive Gaussian Process Latent Variable Model (RGPLVM) that introduces a novel regressive kernel function for the model training. By doing so, our model produces a linear mapping from the training data space to the latent space, while effectively transforming the prediction of human motion in physical space to the linear regression analysis in the latent space equivalent. The comparison with two learning motion prediction approaches (the state-of-the-art meta learning and the classical LSTM-3LR) demonstrate that our GPLVM significantly improves the prediction performance on various of actions in the small-sample size regime.
ER -