Search Results for author:
Found 7 papers, 4 papers with code
Ice hockey player identification via transformers and weakly supervised learning
Obtaining player identities is essential for analyzing the game and is used in downstream tasks such as game event recognition.
Optical Character Recognition
Optical Character Recognition (OCR)
+3
Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation
In keypoint estimation tasks such as human pose estimation, heatmap-based regression is the dominant approach despite possessing notable drawbacks: heatmaps intrinsically suffer from quantization error and require excessive computation to generate and post-process.
Ranked #8 on
Pose Estimation
on CrowdPose
DeepDarts: Modeling Keypoints as Objects for Automatic Scorekeeping in Darts using a Single Camera
In the primary dataset containing 15k images captured from a face-on view of the dartboard using a smartphone, DeepDarts predicted the total score correctly in 94. 7% of the test images.
EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight Transfer
Neural architecture search has proven to be highly effective in the design of efficient convolutional neural networks that are better suited for mobile deployment than hand-designed networks.
Ranked #1 on
Multi-Person Pose Estimation
on MS COCO
(Validation AP metric)
PuckNet: Estimating hockey puck location from broadcast video
The network is able to regress the puck location from broadcast hockey video clips with varying camera angles.
GolfDB: A Video Database for Golf Swing Sequencing
The golf swing is a complex movement requiring considerable full-body coordination to execute proficiently.
STAR-Net: Action Recognition using Spatio-Temporal Activation Reprojection
As such, there has been recent interest on human action recognition using low-cost, readily-available RGB cameras via deep convolutional neural networks.
Ranked #5 on
Multimodal Activity Recognition
on UTD-MHAD
