To submit a video for analysis the user can either provide its URL or upload a local copy of it from their machine
(please notice that the maximum permitted video size is 2GB, and duration up to 30 minutes).
The supported on-line video sources include YouTube, Facebook, Twitter, Instagram, Vimeo, DailyMotion, LiveLeak and
Dropbox (beware though that not all videos from these platforms are accessible to our service, due to platform-specific
or user-defined restrictions about the use of each specific video; moreover, the provided URL should always point to a
single video, rather than a playlist of videos). The service can handle videos in mp4, webm, avi, mov, wmv, ogv, mpg,
flv, and mkv format.
The complete service runs at high speed (i.e., it is faster than real-time video processing, though
delays may be noticed if multiple video processing jobs are in the queue).
After submitting a video, the user can monitor the progress of the analysis. The submitted video is temporarily cached
in our server to enable its processing, and it is automatically deleted from the server right after the completion of
the analysis. Subsequently, the user is shown the collection of extracted keyframes.
All video rights remain with the uploader, who is assumed to have the right to submit the video to this service for
analysis.
Any feedback you may have on the web service is most welcome; please send it to
dgalanop@iti.gr and
bmezaris@iti.gr
Acknowledgements
This service (Video Inspector) is based on a previous web-based service for video fragmentation and
reverse image search (Video Reverse Search v2.0) that was developed as part of our work in the H2020 project InVID (grant
agreement No 687786). The current version of the demo is supported by the European Media and Information Fund
Relevant Publications
If you find the technologies demonstrated through this demo interesting or useful in your work, please cite
the following papers:
E. Apostolidis, G. Balaouras, V. Mezaris, I. Patras, "Selecting a Diverse Set of Aesthetically-pleasing and Representative Video Thumbnails using Reinforcement Learning", IEEE Int. Conf. on Image Processing (ICIP 2023), Kuala Lumpur, Malaysia, Oct. 2023. DOI:10.1109/ICIP49359.2023.10222743.
E. Apostolidis, K. Apostolidis, I. Patras, V. Mezaris, "Video Fragmentation and Reverse Search on the Web", in book "Video Verification in the Fake News Era", V. Mezaris, L. Nixon, S. Papadopoulos, D. Teyssou (Eds.), pp. 53-90, Springer, 2019. DOI:10.1007/978-3-030-26752-0_3.
The full text of these and other relevant multimedia analysis papers are available at:
www.iti.gr/~bmezaris/publications.html
Contributors
Vasileios Mezaris, Senior Researcher (email: bmezaris@iti.gr)
Evlampios Apostolidis, Postdoctoral Research Associate (email: apostolid@iti.gr)
Kostas Apostolidis, Research Associate (email: kapost@iti.gr)
Damianos Galanopoulos, Research Associate (email: dgalanop@iti.gr)
Web Technologies used in this tool
Built up based in HTML5 with the help of JQuery v1.9.1.
Created using the HTML5 video tag.