Table 2 Performance comparisons on the PoseTrack 2017 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

PoseFlow12

66.7

73.3

68.3

61.1

67.5

67.0

61.3

66.5

JointFlow32

–

–

–

–

–

–

–

66.5

FastPost33

80.0

80.3

69.5

59.1

71.4

67.5

59.4

70.3

STEmbedding34

83.8

81.6

77.1

70.0

77.4

74.5

70.8

77.0

HRNet15

82.1

83.6

80.4

73.3

75.5

75.3

68.5

77.3

MSTCFL35

83.8

82.7

81.1

74.1

74.2

74.0

70.2

78.8

Ours

84.5

83.8

82.3

75.7

75.8

75.7

71.3

79.7

  1. Significant values are in bold.
Back to article page