Fig. 7From: Analyzing temporal dynamics of cell deformation and intracellular movement with video feature aggregationThe contrast experiment about the performance with different frame intervals. Three figures from left to right show the classification accuracy of FV, VLAD and H-VLAD on DataSet I respectively. And the green dashed line, blue dashed line and red plain line are corresponding to different vocabulary size (16, 32, 64)Back to article page