7 citations · 11 across the 2 of their papers we have counts for
3 papers
cs.CV2019
Adversarial Attack on Skeleton-based Human Action Recognition
Jian Liu, Naveed Akhtar, Ajmal Mian
Deep learning models achieve impressive performance for skeleton-based human action recognition. However, the robustness of these models to adversarial attacks remains largely unex…
cs.CV2019★ 7 cited
Temporally Coherent Full 3D Mesh Human Pose Recovery from Monocular Video
Jian Liu, Naveed Akhtar, Ajmal Mian
Advances in Deep Learning have recently made it possible to recover full 3D meshes of human poses from individual images. However, extension of this notion to videos for recovering…
cs.CV2017★ 4 cited
Viewpoint Invariant Action Recognition using RGB-D Videos
Jian Liu, Naveed Akhtar, Ajmal Mian
In video-based action recognition, viewpoint variations often pose major challenges because the same actions can appear different from different views. We use the complementary RGB…