Iv Sjsn edited untitled.tex  almost 9 years ago

Commit id: 72aeac4eb2734695547de5a1296c4ed535a48407

deletions | additions      

       

The experiment is performed with UCF Sport Action Dataset. Each x instance is normalized visual word frequency histogram of local features extracted from supervoxel region in the video. The split consists of training $3886$, testing $2277$ instances, respectively with $20k$ dimension.   \begin{itemize}  \item Linear Kernel: mAP: $31.91\%$ ( Runtime = $2.5$ mins with 20k dimensional 2277 )  \item Intersection Kernel: mAP: $31.91\%$ $35.65\%$ ( Runtime = $3.3$ mins )  \item Chi-square Kernel: mAP: $31.91\%$  \item Jenson-Shannon Kernel: mAP: $31.91\%$  \end{itemize}