Table 3 Performance comparisons on the PoseTrack 2018 validation dataset (%).

From: Learning spatio-temporal context for basketball action pose estimation with a multi-stream network

Model

Head

Shou

Elb

Wri

Hip

Knee

Ankl

MAP

AlphaPose11

63.7

78.7

77.4

71.0

73.7

73.0

69.7

71.9

MDPN36

75.4

81.2

79.0

74.1

72.4

73.0

69.9

75.0

Dynamic-GNN31

80.6

84.5

80.6

74.4

75.0

76.7

71.8

77.9

MSTCFL35

81.2

84.8

80.6

74.8

75.1

77.2

71.0

78.5

Ours

82.1

85.3

81.8

76.1

77.1

78.4

72.5

80.2

  1. Significant values are in bold.