Template-based 3D object tracking still lacks a high-precision benchmark of real scenes due to the difficulty of annotating the accurate 3D poses of real moving video objects without using markers. In this paper, we present a multi-view approach to estimate the accurate 3D poses of real moving objects, and then use binocular data to construct a new benchmark for monocular textureless 3D object tracking. The proposed method requires no markers, and the cameras only need to be synchronous, relatively fixed as cross-view and calibrated. Based on our object-centered model, we jointly optimize t...

Hong Huang, Fan Zhong*, Xueying Qin*. Pixel-Wise Weighted Region-Based 3D Object Tracking using Contour Constraints. Transactions on Visualization and Computer Graphics, online.

Jiayao Ma, Xinbo Jiang, Songhua Xu*, Xueying Qin*. Hierarchical Temporal Multi-Instance Learning for Video-based Student Learning Engagement Assessment. International Joint Conference on Artificial Intelligence, 2021.