deletions | additions       diff --git a/section_Reviewer_Comments_for_Authors__.tex b/section_Reviewer_Comments_for_Authors__.tex  index 7280667..b09e994 100644  --- a/section_Reviewer_Comments_for_Authors__.tex  +++ b/section_Reviewer_Comments_for_Authors__.tex 
...
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?  \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, therefor 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}}  \begin{quote}  7. There are some small errors and unclear writings. I think they need to be elaborated.  \end{quote}  \begin{quote}  A)Section 5.4, Paragraph 4: “... a baseline for precision and accuracy” What is accuracy?  \end{quote}  \textit{Well spotted. Ambiguous terms indeed should have no place in scientific papers. We have deleted accuracy from that sentence.}  \begin{quote}  B) Section 5.4, Paragraph 6: “... impossible for the re-id to correctly classify” -> “... impossible for the re-id to be correctly classified”?  \end{quote}  \textit{Thank you for noticing this passage was not clear.}  \textit{For clarity, we have changed it to}  \textbf{\textit{Note that the 155 FPs generated by the detector cannot be correctly re-identified, since they do not have a respective class in the gallery.}}  \begin{quote}  C) Table 3: Is parenthesis after 198 necessary?  \end{quote}  \textit{No, indeed it is not. The table even looks better without it. Thank you for pointing it out.}  D) Section 7, Paragraph 2: Something is wrong with parameter values after T.  \textit{Fixed.}  E) Section 7, Paragraph 6: “They sport the most number of ...” Is this correct?  \textit{We believe so. Nevertheless, for clarity we changed it to}  \textbf{\textit{Scenarios MANUALclean and MANUALcleanhalf are also baselines, complementary to MANUALall. They suffer from the most number of MDs of all scenarios, thus exhibiting the lowest recall values.}} 
...
\begin{quote}  1. The references are not enough. Most recent related works, such as ReID papers in CVPR2014,15, are not included.  \end{quote}  \textit{Hmm, indeed. We thank you for calling our attention to this. We have added some references and now have four 2014 papers, two of those from CVPR, and seven 2015 CVPR papers.}  \begin{quote}  2. In Chapter 2, the organization could be improved. The two main parts are the taxonomy and the overview, which should be distinguished clearly or split into two subsections. What's more, there's no analysis after the taxonomy. And what's this taxonomy used for?  \end{quote}  \textit{Agreed, we have now divided Chapter 2 into a Taxonomy and an Overview sections.}  Q DIZER SOBRE O USO DA TAXONOMIA? :S  \begin{quote}  3. I think the Window-based Classifier is exactly multi-shot. Some other multi-shot methods also do not require contiguous frames and in-camera trackers. The proposed Window-based Classifier is straightforward and reasonable. As an important contribution, it's better to compare it with other other multi-shot methods, such as reference [4].  \end{quote}  \textit{We thank the reviewer to point this out, as it makes clear that we must clarify in the text that multi-shot algorithms that we are aware of (such as [4]) require a way to specify which images belong to a single person (such as a tracker or manual selection) prior to being able to analyze those images in a multi-shot fashion. No multi-shot algorithm that we are aware of does some kind of unsupervised clustering first to try and discover which images belong to a same individual, to then be able to use such data in a multi-shot fashion without a tracker or human intervention.   Therefor, we have enhanced the clarifying paragraph thusly:}