This paper presents a 2D skeleton-based action segmentation method with
...
This paper presents a novel self-supervised temporal video alignment
fra...
This paper presents a novel transformer-based framework for unsupervised...
We introduce a novel approach for temporal activity segmentation with
ti...
We present a novel approach for unsupervised activity segmentation, whic...
We present a self-supervised approach for learning video representations...
In this paper, we derive a new differential homography that can account ...
Monocular visual odometry (VO) suffers severely from error accumulation
...
Classical monocular Simultaneous Localization And Mapping (SLAM) and the...
Inexpensive sensing and computation, as well as insurance innovations, h...
Self-calibration of camera intrinsics and radial distortion has a long
h...
Interest point descriptors have fueled progress on almost every problem ...
Recent data-driven approaches to scene interpretation predominantly pose...
Monocular 3D object parsing is highly desirable in various scenarios
inc...