Representation for Action Recognition Using Trajectory-Based Low-Level Local Feature and Mid-Level Motion Feature

<table class="figure-group"><tr class="fig-image" id="a"><td><object data="https://static.hindawi.com/articles/acisc/volume-2017/4019213/figures/4019213.fig.004a.svgz" name="4019213.fig.004a" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(a) </b>J-HMDB dataset</td></tr><tr class="fig-image" id="b"><td><object data="https://static.hindawi.com/articles/acisc/volume-2017/4019213/figures/4019213.fig.004b.svgz" name="4019213.fig.004b" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(b) </b>YouTube dataset</td></tr></table>

<div>The accuracy of different features comparisons between low-level and two-layer model. (a) The comparison on J-HMDB dataset. (b) The comparison on YouTube dataset.</div>

Applied Computational Intelligence and Soft Computing

fig4

Figure 4

Figure 4: Representation for Action Recognition Using Trajectory-Based Low-Level Local Feature and Mid-Level Motion Feature 