deletions | additions       diff --git a/subsection_Video_Graph_Data_Structure__.tex b/subsection_Video_Graph_Data_Structure__.tex  index e1ba1ab..27f9063 100644  --- a/subsection_Video_Graph_Data_Structure__.tex  +++ b/subsection_Video_Graph_Data_Structure__.tex 
...
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: $f_{map}: S \mapsto G(V,E)$.   Each node $e_i $v_i  \in E$ V$  has following attributes: \begin{itemize}  \item $size_i$ : the total number of cells making up the region $s_i$, $\mathbb{R}$. 
...
\item $$  \end{itemize}  The Each  edge $e_{ij}$ $e_{ij} \in E$  between node $u_i$ and $u_j$ has also following attribute: \begin{itemize}  \item $intsize_{ij}$: the number of mutually adjacent cells between supervoxel $s_i$ and $s_j$, $\mathbb{R}^{N \times N}$ ( $27$-neigborhood is used to compute this attribute).  \end{itemize}