Main content
Top content
Providing Video Annotations in Multimedia Containers for Visualization and Research
WACV17 - Demonstration Video and Datasets
An ever increasing amount of video data sets which comprise additional meta data, such as labelled objects, tagged events, or gaze data become avaible every day. Unfortunately, these meta data are usually stored in separate files in custom-made data formats, which reduces accessibility even for experts and makes the data effectively inaccessible for non-experts. Within our paper as well as the demonstration video and example data sets on this website as supplementary material, we want to promote the use of existing multimedia container formats to establish a standardized method of incorporating content and meta data. This will facilitate visualization in standard multimedia players, streaming via the internet, and easy use without conversion. The demonstration video below compare the current methods and our new approaches.
Source Code
VLC 3.0.0 patch
Modified version of the subsusf.c. Necessary for the playback of the USF files.
USF to ASS translation
XSL file for USF to ASS translation usf2ass.xsl.
Eye tracking data to USF converter
Currently, the eye tracking data to USF converter is only available as command line implementation. A version with a user interface is planned to release in the upcoming months. If you want to get the source code of the command line converter nevertheless, please write an email to Julius Schöning.
VLC Visual Analytics Plugins
To install the extensions under Linux, please copy the SimSub.lua and/or MergeSub.lua into ~/.local/share/vlc/lua/extensions/ for the current user or /usr/lib/vlc/lua/extensions/ for all users.
SimSub: Visualization of different eye tracking datasets in multiple windows
MergeSub: Visualization of different eye tracking datasets in a single window
Converted Data Sets with Instantaneous Visualizations
The following data sets are provided for research purposes. By using these data sets in the proposed multimedia container format, please cite [S], [S1], [S2], or [S3] and also the original dataset [A], [B], [C], [K], or [R].
- Real World Visual Processing [S3] - 1 video
- Açik et al. [A] dataset - 216 videos
- Sundberg et al. [B] dataset - 7 videos
- Coutrot & Guyader [C] dataset - 60 videos
- Kurzhals et al. [K] dataset - 11 videos
- Riche et al. [R] dataset - 24 videos
Kurzhals et al. [K]
| ID | Images | Stimulus | Setting | Task | Induced Patterns |
| K1 |  | Car Pursuit (Rectangle) ASS USF | Panning camera follows a red car while it was going through a roundabout. | Follow the red car. | Potential smooth pursuit with long time spans of attentional synchrony on the red car. |
 | Car Pursuit (Polygon) ASS USF | ||||
| K2 |  | Turning Car (Rectangle) ASS USF | Camera follows turning car. The movement of the car describes the shape of an eight. | Recognize the shape that is described by the movement of the car. | Attentional synchrony on the car with potential smooth pursuit eye movement. |
 | Turning Car (Polygon) ASS USF | ||||
| K3 |  | Dialog ASS USF | Two persons talk to each other in front of the camera. | Follow the dialog attentively. | Switching focus between the faces of both persons. Label on shirt (right person) attracts additional attention. |
| K4 |  | Thimblerig ASS USF | A thimblerig with three cups and a marble. | Find the cup with the marble. | Attentional synchrony mainly on the cup with the marble. |
| K5 |  | Memory ASS USF | A 4x4 memory game. Pairwise flipping of cards is performed until all pairs are found. | After one card is flipped, focus on the corresponding card of the pair. | Increasing attention on matching cards after several turns and switching focus during the search. |
| K6 |  | UNO ASS USF | Two persons play UNO card game until the right player wins. | For each player's turn, focus on the playable cards on the hand. | Switching focus and attention mainly distributed between both hands and the stack of played cards. |
| K7 |  | Kite ASS USF | Person on a meadow steers a kite. The kite repeatedly leaves the field of view. | Follow the flight path of the kite if possible. | Smooth pursuit if the kite is visible. Otherwise, the participants either tried to estimate the position of the kite, or focused on the person. |
| K8 |  | Case-Exchange ASS USF | Various persons crossing the field of view while a text ribbon in the lower part is showing further information. | Task is provided by the text ribbon: Look for metal case. | Attentional synchrony on the text ribbon until the metal case appears and the task is readable. |
| K9 |  | Ball Game ASS USF | Three players with orange shirts and one player with a white shirt pass a ball around. | Task group A: Count ball contacts of the white player. Task group B: Count passes between orange players. | Attentional synchrony often on the ball, independent from the task. |
| K10 |  | Bag Search ASS USF | Various persons carrying different bags are crossing the field of view. | Look for a specfic bag. Two groups: two different search targets, presented before the video started. | Switching focus on new bags in the scene. Depending on the group, the search targets attract more attention. |
| K11 |  | Person Search ASS USF | People with different clothing cross the field of view. | Task group A: Find the person with a hooded sweater. Task group B: Find the person with a red shirt and a headgear. | Switching focus on new persons. After identification, search targets become less important than new persons. |
Benchmark Data [B]
| ID | Images | Stimulus | Annotated Objects |
| B1 |  | Airplane (Rectangle) ASS USF | 6 Objects:
|
 | Airplane (Polygon) ASS USF | ||
| B2 |  | Alec Baldwin (Rectangle) ASS USF | 1 Object:
|
 | Alec Baldwin (Polygon) ASS USF | ||
| B3 |  | Arctic Kayak (Rectangle) ASS USF | 9 Objects:
|
 | Arctic Kayak (Polygon) ASS USF | ||
| B4 |  | Dominoes (Rectangle) ASS USF | 8 Objects:
|
 | Dominoes (Polygon) ASS USF | ||
| B5 |  | Avalanche (Rectangle) ASS USF | 3 Objects:
|
 | Avalanche (Polygon) ASS USF | ||
| B6 |  | Big Wheel (Rectangle) ASS USF | 3 Objects:
|
 | Big Wheel (Polygon) ASS USF | ||
| B7 |  | Campanile (Rectangle) ASS USF | 2 Objects:
|
 | Campanile (Polygon) ASS USF | ||
| B8 | ... | ... in progress | ... |
| B... | ... | ... in progress | ... |
References
| [S2] | J. Schöning, P. Faion, G. Heidemann & U. Krumnack. Providing Video Annotations in Multimedia Containers for Visualization and Research. In IEEE Winter Conference on Applications of Computer Vision (WACV) 2017. IEEE. | PDF | DOI | URL | BibTeX |
| [K] | K. Kurzhals, C.F. Bopp, J. Bässler, F. Ebinger & D. Weiskopf. Benchmark data for evaluating visualization and analysis techniques for eye tracking for video stimuli. In ACM Workshop on Beyond Time and Errors: Novel Evaluation Methods for Visualization (BELIV), pages: 54-60, 2014. ACM Press. | DOI | BibTeX |
| [B] | P. Sundberg, T. Brox, M. Maire, P. Arbelaez & J. Malik. Occlusion boundary detection and figure/ground assignment from optical flow. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages: 2233-2240, 2011. IEEE. | DOI | BibTeX |
