Bowen Song

The book focuses on visual object tracking systems and approaches based on correlation filter and deep learning. Both foundations and implementations have been addressed. The algorithm, system design and performance evaluation have been explored for three kinds of tracking methods including correlation filter based methods, correlation filter with deep feature based methods, and deep learning based methods. Firstly, context aware and multi-scale strategy are presented in correlation filter based trackers; then, long-short term correlation filter, context aware correlation filter and auxiliary relocation in SiamFC framework are proposed for combining correlation filter and deep learning in visual object tracking; finally, improvements in deep learning based trackers including Siamese network, GAN and reinforcement learning are designed. The goal of this book is to bring, in a timely fashion, the latest advances and developments in visual object tracking, especially correlation filter and deep learning based methods, which is particularly suited for readers who are interested in the research and technology innovation in visual object tracking and related fields.

The book focuses on visual object tracking systems and approaches based on correlation filter and deep learning. Both foundations and implementations have been addressed. The algorithm, system design and performance evaluation have been explored for three kinds of tracking methods including correlation filter based methods, correlation filter with deep feature based methods, and deep learning based methods. Firstly, context aware and multi-scale strategy are presented in correlation filter based trackers; then, long-short term correlation filter, context aware correlation filter and auxiliary relocation in SiamFC framework are proposed for combining correlation filter and deep learning in visual object tracking; finally, improvements in deep learning based trackers including Siamese network, GAN and reinforcement learning are designed. The goal of this book is to bring, in a timely fashion, the latest advances and developments in visual object tracking, especially correlation filter and deep learning based methods, which is particularly suited for readers who are interested in the research and technology innovation in visual object tracking and related fields.

Based on highly detailed field investigations and test data from research on 98 different remnant basins, tectonic settings and lithostratigraphic sequences, this book describes the 4-stage evolution of the tectonic lithofacies paleogeography of the Qinghai-Tibetan Plateau, including Paleocene-Eocene, Oligocene, Miocene and Pliocene. It also discusses the contact relationship between the strata, the tectonic-lithofacies paleogeography evolution in the Cenozoic and their response to the tectonic uplift of the plateau. The continuous uplift and intensive intra-continental deformation during each turning point in the plateau divided the originally large sedimentary basins into numerous smaller ones filled with shrank of lacustrine-facies deposition and increased boulderstone accumulation, which indicates a response to the overall uplift of the plateau. Five major uplift events, which happened in 58-53 Ma, 45-30 Ma, 25-20 Ma, 13-7 Ma and since 5 Ma, respectively were identified. The paleogeographic configurations of the Tibetan Plateau turned over during the late Miocene, with high contours in the east during the pre-Miocene switching to the west after the Late Miocene