73 citations · 212 across the 46 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
cs.CV2022
Actor-identified Spatiotemporal Action Detection -- Detecting Who Is Doing What in Videos
Fan Yang, Norimichi Ukita, Sakriani Sakti +1
The success of deep learning on video Action Recognition (AR) has motivated researchers to progressively promote related tasks from the coarse level to the fine-grained level. Comp…
cs.CV2022
MotionAug: Augmentation with Physical Correction for Human Motion Prediction
Takahiro Maeda, Norimichi Ukita
This paper presents a motion data augmentation scheme incorporating motion synthesis encouraging diversity and motion correction imposing physical plausibility. This motion synthes…