Video person reidentification based on neural ordinary differential equations and graph convolution network

AbstractPerson reidentification rate has become a challenging research topic in the field of computer vision due to the fact that person appearance is easily affected by lighting, posture and perspective. In order to make full use of the continuity of video data on the time line and the unstructured relationship of features, a video person reidentification algorithm combining the neural ordinary differential equation with the graph convolution network is proposed in this paper. First, a continuous time model is constructed by using the ordinary differential equation (ODE) network so as to capture hidden information between video frames. By simulating the hidden space of the hidden variables with the hidden time series model, the hidden information between frames that may be ignored in the discrete model can be obtained. Then, the features of the generated video frames are given to the graph convolution network to reconstruct them. Finally, weak supervision is used to classify the features. Experiments on PRID2011 datasets show that the proposed algorithm can significantly improve person reidentification performance.

Download Full-text

Video Person Reidentification based on Neural Ordinary Differential Equations and Graph Convolution Network

10.21203/rs.3.rs-466426/v1 ◽

2021 ◽

Author(s):

Li-qiang ZHANG ◽

Long-yang HUANG ◽

Xiao-li DUAN

Keyword(s):

Differential Equation ◽

Ordinary Differential Equation ◽

Hidden Variables ◽

Video Data ◽

Data Sets ◽

Hidden Information ◽

Continuous Time Model ◽

Time Model ◽

Weak Supervision ◽

Video Frames

Abstract Person reidentification rate has become a challenging research topic in the field of computer vision due to the fact that person appearance is easily affected by lighting, posture and perspective. In order to make full use of the continuity of video data on the time line and the unstructured relationship of features, a video person reidentification algorithm combining the neural ordinary differential equation with the graph convolution network is proposed in this paper. First, a continuous time model is constructed by using the ordinary differential equation (ODE) network so as to capture hidden information between video frames. By simulating the hidden space of the hidden variables with the hidden time series model, the hidden information between frames that may be ignored in the discrete model can be obtained. Then, the features of the generated video frames are given to the graph convolution network to reconstruct them. Finally, weak supervision are used to classify the features. Experiments on PRID2011 data sets show that the proposed algorithm can significantly improve person reidentification performance.

Download Full-text

A Bayesian approach to estimating hidden variables as well as missing and wrong molecular interactions in ordinary differential equation-based mathematical models

Journal of The Royal Society Interface ◽

10.1098/rsif.2017.0332 ◽

2017 ◽

Vol 14 (131) ◽

pp. 20170332 ◽

Cited By ~ 7

Author(s):

Benjamin Engelhardt ◽

Maik Kschischo ◽

Holger Fröhlich

Keyword(s):

Differential Equation ◽

Experimental Data ◽

Ordinary Differential Equation ◽

Molecular Interactions ◽

Bayesian Approach ◽

Hidden Variables ◽

Influence Factors ◽

Erythropoietin Receptor ◽

Molecular Networks ◽

Biological Knowledge

Ordinary differential equations (ODEs) are a popular approach to quantitatively model molecular networks based on biological knowledge. However, such knowledge is typically restricted. Wrongly modelled biological mechanisms as well as relevant external influence factors that are not included into the model are likely to manifest in major discrepancies between model predictions and experimental data. Finding the exact reasons for such observed discrepancies can be quite challenging in practice. In order to address this issue, we suggest a Bayesian approach to estimate hidden influences in ODE-based models. The method can distinguish between exogenous and endogenous hidden influences. Thus, we can detect wrongly specified as well as missed molecular interactions in the model. We demonstrate the performance of our Bayesian dynamic elastic-net with several ordinary differential equation models from the literature, such as human JAK–STAT signalling, information processing at the erythropoietin receptor, isomerization of liquid α -Pinene, G protein cycling in yeast and UV-B triggered signalling in plants. Moreover, we investigate a set of commonly known network motifs and a gene-regulatory network. Altogether our method supports the modeller in an algorithmic manner to identify possible sources of errors in ODE-based models on the basis of experimental data.

Download Full-text