Prof. Bineng Zhong
Huaqiao University, China
Title: Deep Learning for Visual Tracking
Abstract:Visual tracking is one of the fundamental and challenging problems in computer vision, which has a variety of practical applications in the areas such as video surveillance, robot navigation and human-computer interaction. Recent years, with the rapid development of the state-of-the-art deep learning (e.g., AlexNet, ResidualNet, VGG, Faster R-CNN, GoogleNet etc.) and a number of large-scale benchmark datasets (e.g., OTB2015, VOT2019, TrackingNet, LaSOT、GOT-10k), a huge amount of deep neural architectures has been introduced into visual tracking community. However, designing a real-time, robust and accurate tracker remains a difficult problem. In this talk, we will systematically review the current deep learning-based trackers, benchmark datasets, and evaluation metrics. Meanwhile, we also extensively evaluate and discuss the leading trackers. Finally, we summarize our insights, and point out the further research directions for deep learning-based trackers.
Prof. Wenqiang Zhang
Fudan University, China
Prof. Jiping LI
South China Agricultural University,China