Exploiting Probabilistic Siamese Visual Tracking with a Conditional Variational Autoencoder
Wenhui Huang,Jason Gu,Peiyong Duan,Sujuan Hou,Yuanjie Zheng,Wenhui Huang,Jason Gu,Peiyong Duan,Sujuan Hou,Yuanjie Zheng
Visual tracking is a fundamental capability for robots tasked with humans and environment interaction. However, state-of-the-art visual tracking methods are still prone to failures and are imprecise when applied to challenging stereos, and their results are generally confidence agonistic. These methods depend on an embedded deep learning model to provide deterministic features or regression maps. ...
