Xikang Zhang — accepted AI-conference papers

2017

Dynamics Enhanced Multi-Camera Motion Segmentation From Unsynchronized Videos

Xikang Zhang, Bengisu Ozbay, Mario Sznaier, Octavia Camps

ICCV 2017poster

This paper considers the multi-camera motion segmentation problem using unsynchronized videos. Specifically, given two video clips containing several moving objects, captured by unregistered, unsynchronized cameras with different viewpoints, our goal is to assign features to moving objects in the sc…

Cited by 1 PDF ↗Scholar ↗

2016

Efficient Temporal Sequence Comparison and Classification Using Gram Matrix Embeddings on a Riemannian Manifold

Xikang Zhang, Yin Wang, Mengran Gou, Mario Sznaier, Octavia Camps

CVPR 2016poster

In this paper we propose a new framework to compare and classify temporal sequences. The proposed approach captures the underlying dynamics of the data while avoiding expensive estimation procedures, making it suitable to process large numbers of sequences. The main idea is to first embed the seque…

Cited by 127 PDF ↗Scholar ↗