Presentation of the InVID tool for video fragmentation and keyframe-based reverse video search
0 likes6,832 views
Presentation of the developed web application that allows the user to fragment a video into visually coherent parts, extract a number of representative keyframes, and apply a keyframe-based reverse search at the video-fragment level.
Presentation of the InVID tool for video fragmentation and keyframe-based reverse video search
- 1. www.invid-project.eu In Video Veritas Verification of Social Media Video Content for the News Industry Evlampios Apostolidis, CERTH-ITI Fake news based on video reuse and how to deal with it: video fragmentation and reverse image search Thessaloniki, June 2018
- 2. How does this fake work? A previously existing video is reused under a different and irrelevant context, aiming to deliberately mislead the viewers about a fact/event Fake news based on video reuse www.invid-project.eu
- 3. How does this fake work? A previously existing video is reused under a different and irrelevant context, aiming to deliberately mislead the viewers about a fact/event Fake news based on video reuse 19/3/2017; Claim: Migrant seeking free healthcare in a public hospital in France www.invid-project.eu
- 4. How does this fake work? A previously existing video is reused under a different and irrelevant context, aiming to deliberately mislead the viewers about a fact/event Fake news based on video reuse 19/3/2017; Claim: Migrant seeking free healthcare in a public hospital in France 26/2/2017; Claim: Drunk patient in a hospital in Novgorod, Russia www.invid-project.eu
- 5. How journalists deal with this kind of fake news? Try to find previous occurences of the video on the Web Dealing with this type of fakes www.invid-project.eu
- 6. How journalists deal with this kind of fake news? Try to find previous occurences of the video on the Web What processes/tools do they follow/use for performing reverse video search? Dealing with this type of fakes www.invid-project.eu
- 7. How journalists deal with this kind of fake news? Try to find previous occurences of the video on the Web What processes/tools do they follow/use for performing reverse video search? Take screenshots of the video and perform reverse search of these screenshots with the help of the Google Images engine Dealing with this type of fakes www.invid-project.eu
- 8. How journalists deal with this kind of fake news? Try to find previous occurences of the video on the Web What processes/tools do they follow/use for performing reverse video search? Use of search-engine-based web applications or plug-ins, such as TinEye1 and RevEye2 that facilitate the reverse search of images related to the video Dealing with this type of fakes www.invid-project.eu 1. https://tineye.com/ and https://goo.gl/G5Rpu9 2. https://goo.gl/ZRHTDH
- 9. How journalists deal with this kind of fake news? Try to find previous occurences of the video on the Web What processes/tools do they follow/use for performing reverse video search? Use of web applications that allow reverse search of videos based on a (limited) set of video thumbnails, such as the YouTube DataViewer1 and the Custom Reverse Image Search2 Dealing with this type of fakes www.invid-project.eu 1. https://citizenevidence.amnestyusa.org/ 2. https://inteltechniques.com/osint/reverse.video.html
- 10. How journalists deal with this kind of fake news? Try to find previous occurences of the video on the Web What processes/tools do they follow/use for performing reverse video search? Time-consuming and cumbersome processes that: either involve manual generation and uploading of video screenshots or rely on the use of a limited set of video thumbnails Dealing with this type of fakes www.invid-project.eu
- 11. Interactive tool for reverse video search on the Web Time-efficient process that requires minimum manual intervention Fine-grained search at the video-fragment-level, through: segmentation of the video into visually coherent fragments extraction of representative keyframes for each video fragment reverse search of these keyframes via the Google search engine The InVID solution www.invid-project.eu
- 12. User-generated videos (UGVs) are captured without interruption using a single camera, thus, being single-shot videos Algorithms for shot boundary detection fail to reveal information about the structure of these videos A more fine-grained segmentation into sub-shots, is needed! Video fragmentation & keyframe selection www.invid-project.eu
- 13. The InVID approach The visual content of each frame is represented with the help of a 2D Discrete Cosine Transform Video fragmentation into sub-shots is performed by assessing the visual resemblance of neighboring frames using the cosine similarity The algorithm indicates both sub-shots with minor or no activity, and sub- shots with gradually, but consistently, changing visual content Video fragmentation & keyframe selection As representative keyframe: for the former type of sub-shots the middle frame is selected for the latter type of sub-shots the frame with the most pronounced change of visual content is selected The analysis takes approx. 3% of the videos duration (being more than 30 faster than real-time processing) www.invid-project.eu
- 14. The reverse video search tool Available at: http://multimedia3.iti.gr/video_fragmentation/ service/start.html Allows the analysis of both online and locally stored videos Supported platforms: YouTube, Facebook, Twitter, Instagram, Vimeo, LiveLeak, DailyMotion and Dropbox Supported video formats: mp4, webm, avi, mov, wmv, ogv, mpg, flv, mkv www.invid-project.eu
- 15. The reverse video search tool The user can monitor the progress of the analysis, or close the browser and be notified (by e-mail) when the results are ready www.invid-project.eu
- 16. The reverse video search tool After the analysis ends, the user gets the set of extracted keyframes and can perform reverse search by left or right clicking on any of them www.invid-project.eu
- 17. Thank you for your attention! Any questions? www.invid-project.eu In Video Veritas!