mirror of https://github.com/2martens/uni.git
[Masterproj] Added abstract to seminar paper
Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
parent
c4f088bc6f
commit
e7823fc5b3
|
@ -85,7 +85,15 @@ maxnames=2
|
|||
\maketitle
|
||||
\section*{Abstract}
|
||||
|
||||
The short abstract (100-150 words) is intended to give the reader an overview of the paper and your general opinion about the paper.
|
||||
Deep Sliding Shapes is an approach that uses 3D data in a regional proposal
|
||||
network to limit the search space before both 3D and 2D are used in an object
|
||||
recognition network to find the actual objects. In the end it produces 3D
|
||||
bounding boxes and outperforms 3D selective search and other state-of-the-art
|
||||
solutions.
|
||||
|
||||
The paper is presenting the approach in an understandable manner. But the
|
||||
reproducibility of Deep Sliding Shapes is suboptimal as key information for
|
||||
such an endeavour is missing from the paper.
|
||||
|
||||
|
||||
% Lists:
|
||||
|
@ -388,7 +396,7 @@ Furthermore the motivations for the used data sets NYUv2 and SUN RGB-D are
|
|||
not quite clear. Which data set is used for what purpose and why? The text
|
||||
mentions in one sentence that the amodal bounding boxes are obtained from
|
||||
SUN RGB-D without further explanation. It would have been advantageous
|
||||
if the actual process of this "obtaining" were explained.
|
||||
if the actual process of this "obtaining" was explained.
|
||||
|
||||
% subsection negitive (end)
|
||||
|
||||
|
|
Loading…
Reference in New Issue