.png){kind=icon}
返回
Wasserstein approximate bayesian computation for visual tracking
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2022.108905.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this study, we present novel visual tracking methods based on the Wasserstein approximate Bayesian computation (ABC). For visual tracking, the proposed Wasserstein ABC (WABC) method approximates the likelihood within the Wasserstein space more accurately than the conventional ABC methods by di-rectly measuring the discrepancy between the likelihood distributions. To encode the temporal depen-dency among time-series likelihood distributions, we extend the WABC method to the time-series WABC (TWABC) method. Subsequently, the proposed Hilbert T WABC (HT WABC) method reduces the computational costs caused by the TWABC method while substituting the original Wasserstein distance with the Hilbert distance. Experimental results demonstrate that the proposed visual trackers outperform other state-of-the-art visual tracking methods quantitatively. Moreover, ablation studies verify the effectiveness of individual components consisting of the proposed method (e.g., the Wasserstein distance, curve matching, and Hilbert metric). (C) 2022 Elsevier Ltd. All rights reserved.
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
分享收藏Constructing summary statistics for approximate Bayesian computation: semi-automatic approximate Bayesian computation构造近似贝叶斯计算的汇总统计量: 半自动近似贝叶斯计算
OAAI
OAAI分享收藏Robust Multivehicle Tracking With Wasserstein Association Metric in Surveillance Videos.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏Aberrance suppressed spatio-temporal correlation filters for visual object trackingPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏 没有更多内容
没有更多内容