this is for holding javascript data
Dario WurmD added begin_quote_5_If_I__.tex
over 8 years ago
Commit id: 70d8236f1b74c638036266417776d9d90508620e
deletions | additions
diff --git a/begin_quote_5_If_I__.tex b/begin_quote_5_If_I__.tex
new file mode 100644
index 0000000..06518f5
--- /dev/null
+++ b/begin_quote_5_If_I__.tex
...
\
\begin{quote}
5. If I understand CMC correctly, it is a performance measure that can be used for a re-id method (excluding detection part) based on ranking gallery images. If I assume based on the name that the proposed filtering-based approach does not provide ranking, I think it cannot be evaluated with the original CMC. Is this correct? If this is correct, why the authors need to mention the CMC?
\end{quote}
\textit{That is quite correct, the window-based classifier is not being evaluated by the CMC in Figure 10, but is only evaluated in Table 4 and Figure 11 through the precision and recall metrics.}
\textit{We mention the CMC because it is the single most used metric in Re-Identification works, and we'd like to stress how incomplete it is to evaluate a real system (that will have false positives and missed detections).}
\textit{We've changed the caption of Figure 10 to make this clearer as follows:}
\textbf{\textit{Figure 10: Cumulative Matching Characteristic curves comparing the performance of the single-frame classifier for various configurations of the integrated Re-Identification system.} }
\
\begin{quote}
6. I don’t see the difference between the original precision/recall and the proposed precision/recall. I think the paper needs more specific description on them.
\end{quote}
\textit{Well pointed out. We did not mean to imply we had innovated in this aspect, therefore we edited the corresponding part of the abstract to}
\textbf{\textit{In this paper, we apply precision and recall metrics to evaluate such integrated system}}
