Correlations Between 48 Human Actions Improve Their Detection
Gertjan J. Burghouts, Klamer Schutte · TNO Repository · 2012
Many human actions are correlated, because of compound and/or sequential actions, and similarity.Indeed, human actions are highly correlated in human annotations of 48 actions in the 4,774 videos fromvisint.org. We exploit such correlations to improve the detection of these 48 human actions, ranging fromsimple actions such as walk to complex actions such as exchange. We apply a basic pipeline of STIP features, aRandom Forest to quantize the features into histograms, and an SVM classifier. First, we show thatthe sampling for the Random Forest can be improved by exploiting the correlations between human actions.Second, we show that exploiting all 48 actions' posteriors for detecting a particular action alsoimproves further the detection in general. We demonstrate a 50% relative improvement for humanaction detection in 1,294 realistic test videos.