Replace unnecessary non-ASCII characters with ASCII ones

Or, in the case of the quotes around "The PASCAL Visual Object Classes (VOC)
Challenge", just remove them entirely, because they aren't needed there.

demos/README.md

@@ -154,7 +154,7 @@ make
 ```
 
 For the release configuration, the demo application binaries are in `<path_to_build_directory>/intel64/Release/`;
-for the debug configuration — in `<path_to_build_directory>/intel64/Debug/`.
+for the debug configuration — in `<path_to_build_directory>/intel64/Debug/`.
 
 ### <a name="build_demos_windows"></a>Build the Demos Applications on Microsoft Windows* OS
 
@@ -163,7 +163,7 @@ The recommended Windows* build environment is the following:
 * Microsoft Visual Studio* 2015, 2017, or 2019
 * CMake* version 2.8 or higher
 
-> **NOTE**: If you want to use Microsoft Visual Studio 2019, you are required to install CMake 3.14.
+> **NOTE**: If you want to use Microsoft Visual Studio 2019, you are required to install CMake 3.14.
 
 To build the demo applications for Windows, go to the directory with the `build_demos_msvc.bat`
 batch file and run it:

models/intel/gaze-estimation-adas-0002/description/gaze-estimation-adas-0002.md

@@ -9,7 +9,7 @@ This is a custom VGG-like convolutional neural network for gaze direction estima
 
 ![](./ill_for_gaze.png)
 
-The network takes three inputs: square crop of left eye image, square crop of right eye image, and three head pose angles -- (yaw, pitch, and roll) (see figure). The network outputs 3-D vector corresponding to the direction of a person’s gaze in a Cartesian coordinate system in which z-axis is directed from person’s eyes (mid-point between left and right eyes’ centers) to the camera center, y-axis is vertical, and x-axis is orthogonal to both z,y axes so that (x,y,z) constitute a right-handed coordinate system.
+The network takes three inputs: square crop of left eye image, square crop of right eye image, and three head pose angles -- (yaw, pitch, and roll) (see figure). The network outputs 3-D vector corresponding to the direction of a person's gaze in a Cartesian coordinate system in which z-axis is directed from person's eyes (mid-point between left and right eyes' centers) to the camera center, y-axis is vertical, and x-axis is orthogonal to both z,y axes so that (x,y,z) constitute a right-handed coordinate system.
 
 ## Specification
 

models/intel/pedestrian-and-vehicle-detector-adas-0001/description/pedestrian-and-vehicle-detector-adas-0001.md

@@ -21,7 +21,7 @@ Pedestrian and vehicle detection network based on MobileNet v1.0 + SSD.
 | Source framework                | Caffe*                |
 
 Average Precision (AP) metric is described in: Mark Everingham et al.
-[“The PASCAL Visual Object Classes (VOC) Challenge”](http://host.robots.ox.ac.uk/pascal/VOC/pubs/everingham10.pdf).
+[The PASCAL Visual Object Classes (VOC) Challenge](http://host.robots.ox.ac.uk/pascal/VOC/pubs/everingham10.pdf).
 
 Tested on challenging internal datasets with 1001 pedestrian and 12585 vehicles to detect.
 

models/intel/pedestrian-detection-adas-0002/description/pedestrian-detection-adas-0002.md

@@ -20,7 +20,7 @@ Pedestrian detection network based on SSD framework with tuned MobileNet v1 as a
 | Source framework                | Caffe*                                    |
 
 Average Precision metric described in: Mark Everingham et al.
-[“The PASCAL Visual Object Classes (VOC) Challenge”](http://host.robots.ox.ac.uk/pascal/VOC/pubs/everingham10.pdf).
+[The PASCAL Visual Object Classes (VOC) Challenge](http://host.robots.ox.ac.uk/pascal/VOC/pubs/everingham10.pdf).
 
 Tested on an internal dataset with 1001 pedestrian to detect.
 

models/intel/pedestrian-detection-adas-binary-0001/description/pedestrian-detection-adas-binary-0001.md

@@ -22,7 +22,7 @@ Some layers of MobileNet v1 are binary and use I1 arithm
 | Source framework                | PyTorch*                                  |
 
 Average Precision metric described in: Mark Everingham et al.
-[“The PASCAL Visual Object Classes (VOC) Challenge”](http://host.robots.ox.ac.uk/pascal/VOC/pubs/everingham10.pdf).
+[The PASCAL Visual Object Classes (VOC) Challenge](http://host.robots.ox.ac.uk/pascal/VOC/pubs/everingham10.pdf).
 
 Tested on an internal dataset with 1001 pedestrian to detect.