this is for holding javascript data
Iv Sjsn edited subsection_Video_Graph_Data_Structure__.tex
almost 9 years ago
Commit id: c957ec7dd555f8e107b463e2e1d50933a663d031
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}