3D Skeletal Human Action Recognition Using a CNN Fusion Model

Figure 5

Sample frames of the Florence3D-Action dataset. The red points in each frame were plotted according to the 3D positions of skeletal joints obtained using the method of [1]. (a) Wave. (b) Drink from a bottle. (c) Bow. (d) Read watch. (e) Sit down. (f) Answer phone.

(a)

(b)

(c)

(d)

(e)

(f)