Multi-Scale Locality-Constrained Spatiotemporal Coding for Local Feature Based Human Action Recognition

<table class="table-group" id="tab3"><tr><td><table class="table"><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr class="thead"><td align="left">Methods</td><td align="center">KTH</td><td align="center">UCF sports</td><td align="center">Weizmann</td></tr><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr><td align="left">SRC + MLSC</td><td align="center">96.5</td><td align="center">92.1</td><td align="center">100</td></tr><tr><td align="left">LGSR + MLSC</td><td align="center"><b>98.5</b></td><td align="center"><b>93.5</b></td><td align="center"><b>100</b></td></tr><tr class="table-tr"><td colspan="4"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

Comparison results between LGSR and SRC (UNIT: %).

The Scientific World Journal

tab3

Table 3

Table 3: Multi-Scale Locality-Constrained Spatiotemporal Coding for Local Feature Based Human Action Recognition 