Object Tracking on Badminton

Metric: Accuracy (%) (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	Accuracy (%)▼	Extra Data	Paper	Date↕	Code
1	WASB (Step=1)	89	No	Widely Applicable Strong Baseline for Sports Bal...	2023-11-09	Code
2	WASB (Step=3)	87	No	Widely Applicable Strong Baseline for Sports Bal...	2023-11-09	Code
3	MonoTrack	85.9	No	MonoTrack: Shuttle trajectory reconstruction fro...	2022-04-04	Code
4	TrackNetV2	85.6	No	-	-	Code
5	ResTrackNetV2	84	No	Widely Applicable Strong Baseline for Sports Bal...	2023-11-09	Code
6	BallSeg	72.2	No	Real-time CNN-based Segmentation Architecture fo...	2020-07-23	Code
7	DeepBall	38.6	No	DeepBall: Deep Neural-Network Ball Detector	2019-02-19	Code
8	DeepBall-Large	36.8	No	Widely Applicable Strong Baseline for Sports Bal...	2023-11-09	Code

#1WASB (Step=1)SOTA
89
Accuracy (%)· 2023-11-09
Widely Applicable Strong Baseline for Sports Ball Detection and Tracking Code
#2WASB (Step=3)
87
Accuracy (%)· 2023-11-09
Widely Applicable Strong Baseline for Sports Ball Detection and Tracking Code
#3MonoTrackSOTA
85.9
Accuracy (%)· 2022-04-04
MonoTrack: Shuttle trajectory reconstruction from monocular badminton video Code
#4TrackNetV2
85.6
Accuracy (%)
No paperCode
#5ResTrackNetV2
84
Accuracy (%)· 2023-11-09
Widely Applicable Strong Baseline for Sports Ball Detection and Tracking Code
#6BallSegSOTA
72.2
Accuracy (%)· 2020-07-23
Real-time CNN-based Segmentation Architecture for Ball Detection in a Single View Setup Code
#7DeepBallSOTA
38.6
Accuracy (%)· 2019-02-19
DeepBall: Deep Neural-Network Ball Detector Code
#8DeepBall-Large
36.8
Accuracy (%)· 2023-11-09
Widely Applicable Strong Baseline for Sports Ball Detection and Tracking Code