Table 2.

Representation of previously published classification models tested on the data from Jhuang et al. (2010) alongside results obtained with DeepEthoProfile

MethodFrame Acc (%)Macro Acc (%)Accuracy for each behavior (%)
DrinkEatGroomHangMmRearRestWalk
Full database
 DeepEthoProfile74.278.79190709766809177
Jhuang et al. (2010)78.376.47275709283709455
 Human (3)71.675.87887579164669568
Jiang et al. (2017)72.9
Jiang et al. (2019)81.579.260.381.182.295.874.674.997.167.7
 CleverSys (3)60.964.06373308264359669
Le and Murari (2019)73.576.5
Clipped database
 DeepEthoProfile97.696.8989996100909510097
Jhuang et al. (2010)93
Jiang et al. (2017)95.990.772.495.797.497.669.894.999.598.3
 Dollar (2)82.270.5416988.480.832.257.998.896.1
Wang et al. (2015) (1)96.188.545.99298.398.880.695.29997.9
Wang et al. (2017) (1)94.587.650.890.1979677.893.297.199.1
Jiang et al. (2019)97.994.37797.399.199.286.196.799.199.6
 I3D (4)96.9
 R(2 + 1)D (4)96.3
Nwokedi et al. (2023) (5)82
  • Results marked with (1) were published in Jiang et al. (2019), those with (2) were published in Jiang et al. (2017), and those with (3) appeared in Jhuang et al. (2010). The methods marked with (4) were tested in Nguyen et al. (2019). The results from (5) were trained on the “full database” and tested on the “clipped database”.