Improving documentation about tracker SiamMask (#3807)

* update docs

* fix mistakes

* fix file name

* fix mistake

site/content/en/docs/manual/advanced/ai-tools.md

@@ -91,7 +91,7 @@ and where is a background. Negative points are optional.
 
 Detectors are used to automatically annotate one frame. Supported DL models are suitable only for certain labels.
 
-- Before you start, click the magic wand on the controls sidebar and select the Detectors icon tab.
+- Before you start, click the `magic wand` on the controls sidebar and select the `Detectors` tab.
   You need to match the labels of the DL model (left column) with the labels in your task (right column).
   Then click `Annotate`.
 
@@ -101,28 +101,48 @@ Detectors are used to automatically annotate one frame. Supported DL models are
   In the [Automatic annotation](/docs/manual/advanced/automatic-annotation/) section you can read
   how to make automatic annotation of all frames.
 
+### Mask RCNN
+
+The model generates polygons for each instance of an object in the image.
+
+### Faster RCNN
+
+The model generates bounding boxes for each instance of an object in the image. In this model,
+RPN and Fast R-CNN are combined into a single network.
+
 ## Trackers
 
 Trackers are used to automatically annotate an object using bounding box.
 Supported DL models are not bound to the label and can be used for any objects.
 
 - Before you start, select the `magic wand` on the controls sidebar and go to the `Trackers` tab.
-  Then select a label for the object and сlick `Track`. Then annotate the desired objects with the
+  Then select a `Label` and `Tracker` for the object and click `Track`. Then annotate the desired objects with the
   bounding box in the first frame.
 
-  ![Start tracking an object](/images/trackers_tab.png)
+  ![Start tracking an object](/images/trackers_tab.jpg)
 
 - All annotated objects will be automatically tracked when you move to the next frame.
   For tracking, use `Next` button on the top panel or the `F` button to move on to the next frame.
 
+  ![Annotation using a tracker](/images/tracker_siammask_DETRAC.gif)
+
 - You can enable/disable tracking using `tracker switcher` on sidebar.
 
   ![Tracker switcher](/images/tracker_switcher.jpg)
 
 - Trackable objects have indication on canvas with a model indication.
 
-  ![Tracker indication](/images/tracker_indication.png)
+  ![Tracker indication](/images/tracker_indication.jpg)
+
+- You can monitoring the process by the messages appearing at the top.
+  If you change one or more objects, before moving to the next frame, you will see a message that
+  the objects states initialization is taking place. The objects that you do not change are already on the server
+  and therefore do not require initialization. After the objects are initialized, tracking will occur.
+
+  ![Tracker pop-up window](/images/tracker_pop-up_window.jpg)
 
-- A pop-up window displays information about the number of tracked objects.
+### SiamMask
 
-  ![Tracker pop-up window](/images/tracker_pop-up_window.png)
+Fast online Object Tracking and Segmentation. Tracker is able to track different objects in one server request.
+Trackable object will be tracked automatically if the previous frame was
+a latest keyframe for the object. Have tracker indication on canvas. `SiamMask` tracker supported CUDA.

site/content/en/docs/manual/advanced/serverless-tutorial.md

@@ -145,14 +145,18 @@ finish the process.
 ![Create a video annotation task](/images/create_video_task.png)
 
 Open the task and use [AI tools][cvat-ai-tools-user-guide] to start tracking
-an object. Draw a bounding box around an object.
+an object. Draw a bounding box around an object, and sequentially switch
+through the frame and correct the restrictive box if necessary.
 
-![Start tracking an object](/images/start_tracking.png)
+![Start tracking an object](/images/trackers_tab.jpg)
 
-Finally you will get bounding boxes for 10 frames by default.
+Finally you will get bounding boxes.
 
 ![SiamMask results](/images/siammask_results.gif)
 
+`SiamMask` model is more optimized to work on Nvidia GPUs.
+For more information about deploying the model for the GPU, [read on](#objects-segmentation-using-mask-rcnn).
+
 ### Object detection using YOLO-v3
 
 First of all let's deploy the DL model. The deployment process is similar for

site/content/en/docs/manual/basics/vocabulary.md

@@ -42,3 +42,10 @@ Tracks are created in `Track mode`
 Can be used to reduce the annotation file and to facilitate editing polygons.
 
 ![](/images/approximation_accuracy.gif)
+
+---
+
+**Trackable** object will be tracked automatically if the previous frame was
+a latest keyframe for the object. More details in the section [trackers](/docs/manual/advanced/ai-tools/#trackers).
+
+![](/images/tracker_indication.jpg)