Skip to main content

Advertisement

Table 6 Comparative result with the public dataset in Table 4

From: First-person reading activity recognition by deep learning with synthetically generated images

  Baselines Proposed  
  1-NN + FV SVM + FV DCNN  
  Others Reading Others Reading Others Reading  
Scores Precision 54.2 53.1 88.5 50.7 79.0 92.8
for each class Recall 46.1 61.1 3.0 99.6 94.2 74.9
  F-measure 49.8 55.8 5.8 62.2 85.9 82.9
Averages Precision 53.7 69.6 85.9
over classes Recall 53.6 51.3 84.6
  F-measure 52.8 34.0 84.4
  1. Best methods for a given measure are specified in italic type