Correlations Between 48 Human Actions Improve Their Detection
conference paper
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 from
visint.org. We exploit such correlations to improve the detection of these 48 human actions, ranging from
simple actions such as walk to complex actions such as exchange. We apply a basic pipeline of STIP features, a
Random Forest to quantize the features into histograms, and an SVM classifier. First, we show that
the 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 also
improves further the detection in general. We demonstrate a 50% relative improvement for human
action detection in 1,294 realistic test videos.
Indeed, human actions are highly correlated in human annotations of 48 actions in the 4,774 videos from
visint.org. We exploit such correlations to improve the detection of these 48 human actions, ranging from
simple actions such as walk to complex actions such as exchange. We apply a basic pipeline of STIP features, a
Random Forest to quantize the features into histograms, and an SVM classifier. First, we show that
the 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 also
improves further the detection in general. We demonstrate a 50% relative improvement for human
action detection in 1,294 realistic test videos.
TNO Identifier
461917
Source title
21st International Conference on Pattern Recognition, ICPR 2012, 11-15 November 2012, Tsukuba, Japan
Files
To receive the publication files, please send an e-mail request to TNO Repository.