2 papers
cs.CV2022
Context-Aware Sequence Alignment using 4D Skeletal Augmentation
Taein Kwon, Bugra Tekin, Siyu Tang +1
Temporal alignment of fine-grained human actions in videos is important for numerous applications in computer vision, robotics, and mixed reality. State-of-the-art methods directly…
cs.CV2021
H2O: Two Hands Manipulating Objects for First Person Interaction Recognition
Taein Kwon, Bugra Tekin, Jan Stuhmer +2
We present a comprehensive framework for egocentric interaction recognition using markerless 3D annotations of two hands manipulating objects. To this end, we propose a method to c…