66 citations · 66 across the 2 of their papers we have counts for
3 papers
TDT: Teaching Detectors to Track without Fully Annotated Videos
Shuzhi Yu, Guanhang Wu, Chunhui Gu +1
Recently, one-stage trackers that use a joint model to predict both detections and appearance embeddings in one forward pass received much attention and achieved state-of-the-art r…
Hierarchical Metric Learning and Matching for 2D and 3D Geometric Correspondences
Mohammed E. Fathy, Quoc-Huy Tran, M. Zeeshan Zia +2
Interest point descriptors have fueled progress on almost every problem in computer vision. Recent advances in deep neural networks have enabled task-specific learned descriptors t…
Fundamental Matrix Estimation: A Study of Error Criteria
Mohammed E. Fathy, Ashraf S. Hussein, Mohammed F. Tolba
The fundamental matrix (FM) describes the geometric relations that exist between two images of the same scene. Different error criteria are used for estimating FMs from an input se…