Search Results for author:
Found 3 papers, 0 papers with code
2D Human Pose Estimation with Explicit Anatomical Keypoints Structure Constraints
Recently, human pose estimation mainly focuses on how to design a more effective and better deep network structure as human features extractor, and most designed feature extraction networks only introduce the position of each anatomical keypoint to guide their training process.
Sparse Regularized Correlation Filter for UAV Object Tracking with adaptive Contextual Learning and Keyfilter Selection
Another approaches can alleviate the temporal degeneration of learned filters by introducing the temporal regularizer, which depends on the assumption that the filers between consecutive frames should be coherent.
Part-based Visual Tracking via Structural Support Correlation Filter
In addition, to mitigate the issue of drift away from object further, we introduce inter-frame consistencies of local parts into our model.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
