Search Results for author:
Found 6 papers, 0 papers with code
Scale-Aware Crowd Count Network with Annotation Error Correction
Furthermore, the use of a fixed Gaussian kernel fails to account for the varying pixel distribution with respect to the camera distance.
Tracking Players in a Badminton Court by Two Cameras
We leverage two off-the-shelf cameras, one on the top of the court and the other on the side of the court.
Multi-scale Motion-Aware Module for Video Action Recognition
When installed into TSM ResNet-50, the MSMA module introduces ≈ 17. 6% more latency on NVIDIA Tesla V100 GPU, yet, it achieves state-of-the-art performance on SomethingSomething V1 & V2 and Diving-48.
Ranked #11 on
Action Recognition
on Something-Something V1
Scale-Aware Crowd Counting Using a Joint Likelihood Density Map and Synthetic Fusion Pyramid Network
We then approximate the joint distribution of crowd density maps with the full covariance of multiple scales and derive a low-rank approximation for tractability and efficient implementation.
CoachAI: A Project for Microscopic Badminton Match Data Collection and Tactical Analysis
For automatically and systematically competition data collection and tactical analysis, a project called CoachAI has been supported by the Ministry of Science and Technology, Taiwan.
Fusing Video and Inertial Sensor Data for Walking Person Identification
In this paper, we propose an effective and practical system which combines video and inertial sensors for person identification (PID).
