Wasserstein approximate bayesian computation for visual tracking

作者：

Highlights：

• Our WABC is the first to use the Wasserstein distance to approximate the likelihood in visual tracking.

• Our TWABC encodes the temporal interdependence between likelihood distributions,

• Our HTWABC uses the Hilbert distance, which makes tackers scalable to realworld environments.

摘要

•Our WABC is the first to use the Wasserstein distance to approximate the likelihood in visual tracking.•Our TWABC encodes the temporal interdependence between likelihood distributions,•Our HTWABC uses the Hilbert distance, which makes tackers scalable to realworld environments.

论文关键词：

论文评审过程：Received 4 August 2020, Revised 6 July 2022, Accepted 14 July 2022, Available online 16 July 2022, Version of Record 21 July 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108905