deletions | additions       diff --git a/subsection_Video_Graph_Data_Structure__.tex b/subsection_Video_Graph_Data_Structure__.tex  index ba8f129..865e878 100644  --- a/subsection_Video_Graph_Data_Structure__.tex  +++ b/subsection_Video_Graph_Data_Structure__.tex 
...
\subsection{Video Graph Data Structure}  A video sequence is partitioned into a set of non-overlapping supervoxel regions $S = \{s_0,s_1,..,s_N\}$.   The supervoxel is mapped into graph: $f_{map}: S \mapsto G(V,E)$, where each G(V,E)$.   Each  node $e_i$ $e_i \in E$  has following attributes: \begin{itemize}  \item $size_i$ : the total number of cells making up the region $s_i$, $\mathbb{R}$.  \item $min_i$ : the minimum most location of 3D bounding box point in cell-coordinate $\mathbb{R}^3$. 
...
\item $sparsity_i$: the number of non-zeros bins in the bow histogram $hist_i$.   \item $$  \end{itemize}  The edge $e_ij$ has also following attributes:  \begin{itemize}  \item $intsize_ij$: the number of mutually adjacent cells between supervoxel $s_i$ and $s_j$, $\mathbb{R}^(N \times N$.  \end{itemize}