Transferable Feature Representation for Visible-to-Infrared Cross-Dataset Human Action Recognition

Figure 5

12 actions of the newly constructed visible light action dataset XD145.

(a) Fight

(b) Handclapping

(c) Handshake

(d) Hug

(e) Jog

(f) Jump

(g) Punch

(h) Push

(i) Skip

(j) Walk

(k) Wave 1

(l) Wave 2