|
@@ -1,6 +1,7 @@
|
|
|
-Here we provide 15 360-degree equirectangular videos, togeher with eye tracking
|
|
|
-recordings of 13 subjects and a manually labelled ground-truth subset of all
|
|
|
-gaze recordings. Finally we also provide a algorithmic implemetntation of the
|
|
|
+Here we provide 15 360-degree equirectangular videos, together with the eye
|
|
|
+tracking recordings of 13 subjects and a manually labelled ground-truth subset
|
|
|
+of the gaze recordings. We also offer information about the manual labelling
|
|
|
+tool in Section 1.4. Finally we provide a algorithmic implementation of the
|
|
|
the process that was followed during manual labelling.
|
|
|
|
|
|
## 1. CONTENT
|
|
@@ -19,13 +20,13 @@ commands.
|
|
|
We used as an approximation to naturalistic stimuli 14 Youtube
|
|
|
videos from diverse contexts. The videos were published under the Creative
|
|
|
Commons license and we give attribution to the original creators by attaching
|
|
|
-the Youtude IDS at the end of each video clip.
|
|
|
+the Youtube IDs at the end of each video clip.
|
|
|
|
|
|
-A single syntetic stimulus was created by the authors and comprises of a moving
|
|
|
+A single synthetic stimulus was created by the authors and comprises of a moving
|
|
|
target, which tries to elicit many different kinds of eye motion (i.e.
|
|
|
fixations, saccade, SP, head pursuit, VOR, OKN).
|
|
|
|
|
|
-Files found in `videos`.
|
|
|
+Files found in the `videos` folder.
|
|
|
|
|
|
### 1.2 Gaze Recordings
|
|
|
|
|
@@ -33,17 +34,17 @@ In total 13 subjects participated in our study, which amounts to ca. 3.5 hours
|
|
|
of eye tracking data. Information about the participants can be found
|
|
|
[here](https://web.gin.g-node.org/ioannis.agtzidis/360_em_dataset/src/master/participant_info.csv).
|
|
|
|
|
|
-Gaze files are found in `gaze` folder.
|
|
|
+Gaze files are found in the `gaze` folder.
|
|
|
|
|
|
### 1.3 Ground Truth
|
|
|
|
|
|
-we manually labelled part of the full data set accroding to the rules presented
|
|
|
+We manually labelled part of the full data set according to the rules presented
|
|
|
in our paper. The labelled gaze recordings were split in two non overlapping
|
|
|
-(subject wise) subsets, where one can be use as training and the other as
|
|
|
-testing. In total the hand-lablled portion comprise of 2 labelled gaze files per
|
|
|
+(subject wise) subsets, where one can be used as training and the other as
|
|
|
+testing. In total the hand-labelled portion comprises of 2 labelled gaze files per
|
|
|
video stimulus and about 16 % of the data.
|
|
|
|
|
|
-Manually annotated ground-truthf files are found in `ground_truth` folder.
|
|
|
+Manually annotated ground-truth files are found in the `ground_truth` folder.
|
|
|
|
|
|
### 1.4 Manual Labelling Interface
|
|
|
|
|
@@ -53,20 +54,20 @@ The GTA-VI repository contains the extension that was developed for labelling
|
|
|
this data set and enables labelling of 360-degree equirectangular recordings with our
|
|
|
two tier method.
|
|
|
|
|
|
-### 1.5 Algorithmic Implemetation
|
|
|
+### 1.5 Algorithmic Implementation
|
|
|
|
|
|
We provide an algorithmic implementation for eye movement classification based
|
|
|
-on the definitions that we provied in our paper. The resulting eye movements
|
|
|
-adter applying our algorithms to ground truth files can be foundin the relevant
|
|
|
+on the definitions that we provide in our paper. The resulting eye movements
|
|
|
+after applying our algorithms to ground truth files can be found in the relevant
|
|
|
files.
|
|
|
|
|
|
-Algorithms and their output are found in `em_algorithms`, `output_I-S5T_combined`, `output_I-S5T_FOV`, `output_I-S5T_E+H` folders.
|
|
|
+The algorithms and their output are found in the `em_algorithms`, `output_I-S5T_combined`, `output_I-S5T_FOV`, `output_I-S5T_E+H` folders.
|
|
|
|
|
|
## 2. DATA FORMAT
|
|
|
|
|
|
-All the function use the ARFF data format for input and output to the disk. The initial
|
|
|
-ARFF format was extended as described in Agtzidis et al. (2016) and was further expanded
|
|
|
-for 360-degree gaze data.
|
|
|
+For the whole analysis we use the ARFF data format for input and output from the
|
|
|
+disk. The initial ARFF format was extended as described in Agtzidis et al.
|
|
|
+(2016) and was further expanded for 360-degree gaze data.
|
|
|
|
|
|
Here the "@RELATION" is set to gaze_360 to distinguish the recordings from
|
|
|
plain gaze recordings. We also make use of the "%@METADATA" special comments
|