SlideShare a Scribd company logo
1 of 21
Download to read offline
The InVID Plug-in: Web Video
Verification on the Browser
D. Teyssou1, J.-M. Leung1, E. Apostolidis2, K. Apostolidis2, S.
Papadopoulos2, M. Zampoglou2, O. Papadopoulou2, V. Mezaris2
1. AFP Medialab, Agence France-Presse
2. Information Technologies Institute / Centre for Research and Technology Hellas
ACM MM 2017, Mountain View, CA, USA, October 2017
Overview
• Introduction - problem formulation
• State-of-the-art on media verification
• Proposed approach: The InVID Plug-in
• Plug-in verification modules
• Case study
• Conclusions
Introduction – problem formulation
• User Generated Content (UGC): a valuable resource…
– Digital media revolution & convergence of social media with
broadband connectivity bring breaking news to online video platforms
– News organizations often rely on user-generated recordings of
breaking and developing news events shared via social media
• …but also a tricky one
– Deception facilitated by access to sophisticated editing and content
management tools
– Rapid spread of fake information in electronic networks
• Careful verification of third-party content is necessary for
reputable news outlets; at present, this manual process
– Reduces their ability to break news quickly
– Increases their costs in times of tight budgets
State-of-the-art on media verification
• Daily routine in newsrooms contains:
– Verification of images/videos posted on social networks
– Debunking fake news and hoaxes spread via social media
• Current UGC verification pipeline for journalists:
– Switch back and forth among several ever-changing tools and services
– Video verification relies on:
• Search engines, online translators, video playing and editing software,
map services, and other services (e.g. historical weather information)
– Image and video duplicate detection relies on:
• Google image search, plug-ins such as RevEye1 or TinEye2
• The YouTube DataViewer3
• The use of Google image search after taking screenshots of the video
• No integrated solution exists to address verification of UGC
1. https://goo.gl/ZRHTDH
2. https://tineye.com/
3.https://citizenevidence.amnestyusa.org/
Proposed approach
• Through design thinking methodology, observing and
understanding of journalistic workflows and of the difficulties
when verifying information, we built a browser plug-in that
works as a verification “Swiss army knife”
Proposed approach
• The plug-in provides a unified view over a number of third
party services and novel technologies, via a single GUI
• It is freely available at: http://www.invid-project.eu/verify
Plug-in verification modules
• The InVID Plug-in integrates modules for:
– Video context analysis
– Advanced Twitter search
– Video keyframe selection for reverse video search
– Visual inspection of images and keyframes through a magnifying glass
– Forensic analysis of keyframes
Plug-in verification modules
• Video context analysis: collects, extracts and presents to the
user several data and metadata related to a video
Plug-in verification modules
• Video context analysis: collects, extracts and presents to the
user several data and metadata related to a video
• Video and channel metadata contain:
– Video name and description
– Video and channel views count
– Video upload date
– Channel creation date
– Locations mentioned in the
description
Plug-in verification modules
• Video context analysis: collects, extracts and presents to the
user several data and metadata related to a video
• Comment analysis:
– Extracts comments potential related to verification based on a list of
keywords, such as “lies”, “fake”, “wrong”, and “confirm”
– Presents them in a compact form, allowing user to quickly sift through
them
Plug-in verification modules
• Video context analysis: collects, extracts and presents to the
user several data and metadata related to a video
• External search and Twitter timeline analysis:
– Performs reverse image
search using the available
video thumbnails and the
Google and Yandex engines
– Searches for video-related
posts on Twitter based on
the video URL, allowing user
to evaluate Twitter activity
around the video
Plug-in verification modules
• Advanced Twitter search: allows to query Twitter by time
interval up to the minute
• Converts regular calendar
dates into Unix timestamps
automatically
• Replaces a manual process
that uses Epoch Converter1
1. https://www.epochconverter.com
Plug-in verification modules
• Keyframe selection: segments a single-shot video into sub-
shots and selects one representative keyframe from each part
• Visual content is represented using Discrete Cosine Transform
• Each sub-shot is comprised by a set of temporally contiguous
and visually similar frames based on the cosine similarity
Plug-in verification modules
• Keyframe selection: allows user to perform keyframe-based
reverse video search on the Web
Plug-in verification modules
• Keyframe magnifier: enables deep inspection of image or
keyframe details through a digital magnifying glass
• These details might help to:
– Confirm location or identity (e.g.
car plates or signs)
– Spot pixel incoherencies that
indicate possible tampering
• Metadata reader presents
related image/video metadata
(creation / modification date,
geo-coordinates, etc.)
Plug-in verification modules
• Forensic analysis of keyframes: provides analysis tools for
tampering detection and localization in images
• Designed to cover professionals’ needs for image verification
Integrated tampering localization
algorithms
Double JPEG Quantization
JPEG Ghosts
JPEG Blocking Artifact Inconsistencies
Median Filtering Noise Residue
Discrete Wavelet High Frequency Noise
Variance
Error Level Analysis
GRIDS (JPEG Blocking Grid Inconsistencies)
Case study
• InVID Plug-in was used by several AFP and DW journalists
over the last three months, helping to:
– Debunk a fake video using the keyframe selection tool:
• Shared video allegedly on the robbery of a Manila casino on June 2017,
was an older video from a robbery in a Surinam casino on December 2011
– Debunk a fake image using the Twitter advanced search tool:
• Image shared on Twitter during the Champs Elysees failed attack, was a
re-posted image from an arrest in London after a previous terror attack
– Prove a wrong claim using the magnifier tool:
• Image of a jet allegedly used by a candidate of the French presidential
election to travel to a meeting was in fact registered in the US
Case study
• According to the analytics of the Google Chrome store the
current users of the plug-in are more than 1000
• Based on the received feedback via social media:
Case study
• According to the analytics of the Google Chrome store the
current users of the plug-in are more than 1000
• Based on the received feedback via social media:
The plug-in is currently used by journalists and experts
worldwide, effectively supporting them in their efforts to
debunk a number of fake videos!
Conclusions and next steps
• The InVID plug-in seamlessly integrates a set of SoA tools and
services for media analysis, that assist the verification of UGV
• Testing in real-life scenarios shows that it can speed up video
verification process for journalists, media scholars and NGOs
• The InVID plug-in will be updated over the next months by
enhancing the current features
• Stay tuned at: www.invid-project.eu
Questions?
More information:
http://www.iti.gr/~bmezaris
bmezaris@iti.gr

More Related Content

Viewers also liked

Viewers also liked (18)

MediaEval 2016 - TUD-MMC Predicting media Interestingness Task
MediaEval 2016 - TUD-MMC Predicting media Interestingness TaskMediaEval 2016 - TUD-MMC Predicting media Interestingness Task
MediaEval 2016 - TUD-MMC Predicting media Interestingness Task
 
MediaEval 2015 - Verifying Multimedia Use at MediaEval 2015
MediaEval 2015 - Verifying Multimedia Use at MediaEval 2015MediaEval 2015 - Verifying Multimedia Use at MediaEval 2015
MediaEval 2015 - Verifying Multimedia Use at MediaEval 2015
 
MediaEval 2016 - Placing Images with Refined Language Models and Similarity S...
MediaEval 2016 - Placing Images with Refined Language Models and Similarity S...MediaEval 2016 - Placing Images with Refined Language Models and Similarity S...
MediaEval 2016 - Placing Images with Refined Language Models and Similarity S...
 
MediaEval 2016 - COSMIR and the OpenMIC Challenge: A Plan for Sustainable Mus...
MediaEval 2016 - COSMIR and the OpenMIC Challenge: A Plan for Sustainable Mus...MediaEval 2016 - COSMIR and the OpenMIC Challenge: A Plan for Sustainable Mus...
MediaEval 2016 - COSMIR and the OpenMIC Challenge: A Plan for Sustainable Mus...
 
MediaEval 2016 - IR Evaluation: Putting the User Back in the Loop
MediaEval 2016 - IR Evaluation: Putting the User Back in the LoopMediaEval 2016 - IR Evaluation: Putting the User Back in the Loop
MediaEval 2016 - IR Evaluation: Putting the User Back in the Loop
 
MediaEval 2016 - LAPI @ 2016 Retrieving Diverse Social Images Task: A Pseudo-...
MediaEval 2016 - LAPI @ 2016 Retrieving Diverse Social Images Task: A Pseudo-...MediaEval 2016 - LAPI @ 2016 Retrieving Diverse Social Images Task: A Pseudo-...
MediaEval 2016 - LAPI @ 2016 Retrieving Diverse Social Images Task: A Pseudo-...
 
MediaEval 2016: A Multimodal System for the Verifying Multimedia Use Task
MediaEval 2016: A Multimodal System for the Verifying Multimedia Use TaskMediaEval 2016: A Multimodal System for the Verifying Multimedia Use Task
MediaEval 2016: A Multimodal System for the Verifying Multimedia Use Task
 
MediaEval 2016 - Emotion in Music Task: Lessons Learned
MediaEval 2016 - Emotion in Music Task: Lessons LearnedMediaEval 2016 - Emotion in Music Task: Lessons Learned
MediaEval 2016 - Emotion in Music Task: Lessons Learned
 
MediaEval 2015 - JRS at Synchronization of Multi-user Event Media Task
MediaEval 2015 - JRS at Synchronization of Multi-user Event Media TaskMediaEval 2015 - JRS at Synchronization of Multi-user Event Media Task
MediaEval 2015 - JRS at Synchronization of Multi-user Event Media Task
 
MediaEval 2015 - Synchronization of Multi-User Event Media at MediaEval 2015:...
MediaEval 2015 - Synchronization of Multi-User Event Media at MediaEval 2015:...MediaEval 2015 - Synchronization of Multi-User Event Media at MediaEval 2015:...
MediaEval 2015 - Synchronization of Multi-User Event Media at MediaEval 2015:...
 
MediaEval 2015 - CERTH at MediaEval 2015 Synchronization of Multi-User Event ...
MediaEval 2015 - CERTH at MediaEval 2015 Synchronization of Multi-User Event ...MediaEval 2015 - CERTH at MediaEval 2015 Synchronization of Multi-User Event ...
MediaEval 2015 - CERTH at MediaEval 2015 Synchronization of Multi-User Event ...
 
MediaEval 2015 - GTM-UVigo Systems for Person Discovery Task at MediaEval 2015
MediaEval 2015 - GTM-UVigo Systems for Person Discovery Task at MediaEval 2015MediaEval 2015 - GTM-UVigo Systems for Person Discovery Task at MediaEval 2015
MediaEval 2015 - GTM-UVigo Systems for Person Discovery Task at MediaEval 2015
 
MediaEval 2016 - Verifying Multimedia Use Task Overview
MediaEval 2016 - Verifying Multimedia Use Task OverviewMediaEval 2016 - Verifying Multimedia Use Task Overview
MediaEval 2016 - Verifying Multimedia Use Task Overview
 
MediaEval 2016 - HUCVL Predicting Interesting Key Frames with Deep Models
MediaEval 2016 - HUCVL Predicting Interesting Key Frames with Deep ModelsMediaEval 2016 - HUCVL Predicting Interesting Key Frames with Deep Models
MediaEval 2016 - HUCVL Predicting Interesting Key Frames with Deep Models
 
MediaEval 2016: LAPI at Predicting Media Interestingness Task
MediaEval 2016: LAPI at Predicting Media Interestingness TaskMediaEval 2016: LAPI at Predicting Media Interestingness Task
MediaEval 2016: LAPI at Predicting Media Interestingness Task
 
MediaEval 2016 - BUT Zero-Cost Speech Recognition
MediaEval 2016 - BUT Zero-Cost Speech RecognitionMediaEval 2016 - BUT Zero-Cost Speech Recognition
MediaEval 2016 - BUT Zero-Cost Speech Recognition
 
Media REVEALr: A social multimedia monitoring and intelligence system for Web...
Media REVEALr: A social multimedia monitoring and intelligence system for Web...Media REVEALr: A social multimedia monitoring and intelligence system for Web...
Media REVEALr: A social multimedia monitoring and intelligence system for Web...
 
MediaEval 2016 - Simula Team @ Context of Experience Task
MediaEval 2016 - Simula Team @ Context of Experience TaskMediaEval 2016 - Simula Team @ Context of Experience Task
MediaEval 2016 - Simula Team @ Context of Experience Task
 

Similar to The InVID Plug-in: Web Video Verification on the Browser

Conduit Aug 2010
Conduit Aug 2010Conduit Aug 2010
Conduit Aug 2010
Guy Malachi
 

Similar to The InVID Plug-in: Web Video Verification on the Browser (20)

Context Aggregation and Analysis: A tool for User-Generated Video Verification
Context Aggregation and Analysis: A tool for User-Generated Video VerificationContext Aggregation and Analysis: A tool for User-Generated Video Verification
Context Aggregation and Analysis: A tool for User-Generated Video Verification
 
Context Aggregation and Analysis: A Tool for User- Generated Video Verificati...
Context Aggregation and Analysis: A Tool for User- Generated Video Verificati...Context Aggregation and Analysis: A Tool for User- Generated Video Verificati...
Context Aggregation and Analysis: A Tool for User- Generated Video Verificati...
 
Presentation of the InVID verification technologies at IPTC 2018
Presentation of the InVID verification technologies at IPTC 2018Presentation of the InVID verification technologies at IPTC 2018
Presentation of the InVID verification technologies at IPTC 2018
 
Video & AI: capabilities and limitations of AI in detecting video manipulations
Video & AI: capabilities and limitations of AI in detecting video manipulationsVideo & AI: capabilities and limitations of AI in detecting video manipulations
Video & AI: capabilities and limitations of AI in detecting video manipulations
 
Aggregating and Analyzing the Context of Social Media Content
Aggregating and Analyzing the Context of Social Media ContentAggregating and Analyzing the Context of Social Media Content
Aggregating and Analyzing the Context of Social Media Content
 
A short introduction to multimedia forensics the science discovering the hist...
A short introduction to multimedia forensics the science discovering the hist...A short introduction to multimedia forensics the science discovering the hist...
A short introduction to multimedia forensics the science discovering the hist...
 
Second issue of the InVID newsletter
Second issue of the InVID newsletterSecond issue of the InVID newsletter
Second issue of the InVID newsletter
 
Model Driven Development of Social Media Environmental Monitoring Applications
Model Driven Development of Social Media Environmental Monitoring ApplicationsModel Driven Development of Social Media Environmental Monitoring Applications
Model Driven Development of Social Media Environmental Monitoring Applications
 
Welcome to the Evolution of Video Community!
Welcome to the Evolution of Video Community! Welcome to the Evolution of Video Community!
Welcome to the Evolution of Video Community!
 
Visual Information Analysis for Crisis and Natural Disasters Management and R...
Visual Information Analysis for Crisis and Natural Disasters Management and R...Visual Information Analysis for Crisis and Natural Disasters Management and R...
Visual Information Analysis for Crisis and Natural Disasters Management and R...
 
Media Fragments Indexing using Social Media
Media Fragments Indexing using Social MediaMedia Fragments Indexing using Social Media
Media Fragments Indexing using Social Media
 
NexGenTV: Providing Real-Time Insight during Political Debates in a Second Sc...
NexGenTV: Providing Real-Time Insight during Political Debates in a Second Sc...NexGenTV: Providing Real-Time Insight during Political Debates in a Second Sc...
NexGenTV: Providing Real-Time Insight during Political Debates in a Second Sc...
 
Durex - Real Feel
Durex - Real FeelDurex - Real Feel
Durex - Real Feel
 
Final Project Presentation.pptx
Final Project Presentation.pptxFinal Project Presentation.pptx
Final Project Presentation.pptx
 
Randall Helms - Video Tracking in Google Analytics: Lessons Learned and Trick...
Randall Helms - Video Tracking in Google Analytics: Lessons Learned and Trick...Randall Helms - Video Tracking in Google Analytics: Lessons Learned and Trick...
Randall Helms - Video Tracking in Google Analytics: Lessons Learned and Trick...
 
Security in Android Application
Security in Android ApplicationSecurity in Android Application
Security in Android Application
 
trust based video management framework for social multimedia networks
trust based video management framework for social multimedia networkstrust based video management framework for social multimedia networks
trust based video management framework for social multimedia networks
 
Conduit Aug 2010
Conduit Aug 2010Conduit Aug 2010
Conduit Aug 2010
 
Operation Buhtrap - AVAR 2015
Operation Buhtrap - AVAR 2015Operation Buhtrap - AVAR 2015
Operation Buhtrap - AVAR 2015
 
Multimedia development process
Multimedia development processMultimedia development process
Multimedia development process
 

More from InVID Project

More from InVID Project (15)

InVID at IFCN Global Fact V
InVID at IFCN Global Fact VInVID at IFCN Global Fact V
InVID at IFCN Global Fact V
 
Presentation of the InVID technologies for image forensics analysis
Presentation of the InVID technologies for image forensics analysisPresentation of the InVID technologies for image forensics analysis
Presentation of the InVID technologies for image forensics analysis
 
IUT-Toulouse-InVID-2018
IUT-Toulouse-InVID-2018IUT-Toulouse-InVID-2018
IUT-Toulouse-InVID-2018
 
Presentation of the InVID tool for social media verification
Presentation of the InVID tool for social media verificationPresentation of the InVID tool for social media verification
Presentation of the InVID tool for social media verification
 
Presentation of the InVID tool for video fragmentation and reverse keyframe s...
Presentation of the InVID tool for video fragmentation and reverse keyframe s...Presentation of the InVID tool for video fragmentation and reverse keyframe s...
Presentation of the InVID tool for video fragmentation and reverse keyframe s...
 
Presentation of the InVID tools for image forensics analysis
Presentation of the InVID tools for image forensics analysisPresentation of the InVID tools for image forensics analysis
Presentation of the InVID tools for image forensics analysis
 
The InVID Vefirication Plugin at #IFRAExpo #DCXExpo
The InVID Vefirication Plugin at #IFRAExpo #DCXExpoThe InVID Vefirication Plugin at #IFRAExpo #DCXExpo
The InVID Vefirication Plugin at #IFRAExpo #DCXExpo
 
The InVID Vefirication Plugin at DisinfoLab
The InVID Vefirication Plugin at DisinfoLabThe InVID Vefirication Plugin at DisinfoLab
The InVID Vefirication Plugin at DisinfoLab
 
Comparison of Fine-tuning and Extension Strategies for Deep Convolutional Neu...
Comparison of Fine-tuning and Extension Strategies for Deep Convolutional Neu...Comparison of Fine-tuning and Extension Strategies for Deep Convolutional Neu...
Comparison of Fine-tuning and Extension Strategies for Deep Convolutional Neu...
 
TRECVID 2016 Ad-hoc Video Seach task, CERTH-ITI
TRECVID 2016 Ad-hoc Video Seach task, CERTH-ITITRECVID 2016 Ad-hoc Video Seach task, CERTH-ITI
TRECVID 2016 Ad-hoc Video Seach task, CERTH-ITI
 
InVID at the IPTC Autumn Meeting 2016
InVID at the IPTC Autumn Meeting 2016InVID at the IPTC Autumn Meeting 2016
InVID at the IPTC Autumn Meeting 2016
 
ELLA LC algorithm presentation in ICIP 2016
ELLA LC algorithm presentation in ICIP 2016ELLA LC algorithm presentation in ICIP 2016
ELLA LC algorithm presentation in ICIP 2016
 
InVID verification application presentation at SMVW16
InVID verification application presentation at SMVW16InVID verification application presentation at SMVW16
InVID verification application presentation at SMVW16
 
InVID platform presentation at SMVW16
InVID platform presentation at SMVW16InVID platform presentation at SMVW16
InVID platform presentation at SMVW16
 
InVID at Computational journalism workshop in Rennes, France
InVID at Computational journalism workshop in Rennes, FranceInVID at Computational journalism workshop in Rennes, France
InVID at Computational journalism workshop in Rennes, France
 

Recently uploaded

Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Safe Software
 

Recently uploaded (20)

Exploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with MilvusExploring Multimodal Embeddings with Milvus
Exploring Multimodal Embeddings with Milvus
 
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfRising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
 
CNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In PakistanCNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In Pakistan
 
How to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected WorkerHow to Troubleshoot Apps for the Modern Connected Worker
How to Troubleshoot Apps for the Modern Connected Worker
 
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
Biography Of Angeliki Cooney | Senior Vice President Life Sciences | Albany, ...
 
[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf[BuildWithAI] Introduction to Gemini.pdf
[BuildWithAI] Introduction to Gemini.pdf
 
Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..Understanding the FAA Part 107 License ..
Understanding the FAA Part 107 License ..
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
Apidays New York 2024 - APIs in 2030: The Risk of Technological Sleepwalk by ...
 
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
Navigating the Deluge_ Dubai Floods and the Resilience of Dubai International...
 
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ..."I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
MS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectorsMS Copilot expands with MS Graph connectors
MS Copilot expands with MS Graph connectors
 
Six Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal OntologySix Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal Ontology
 
ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challenges
 
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemkeProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
ProductAnonymous-April2024-WinProductDiscovery-MelissaKlemke
 
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 AmsterdamDEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
DEV meet-up UiPath Document Understanding May 7 2024 Amsterdam
 
Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)Introduction to Multilingual Retrieval Augmented Generation (RAG)
Introduction to Multilingual Retrieval Augmented Generation (RAG)
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​Elevate Developer Efficiency & build GenAI Application with Amazon Q​
Elevate Developer Efficiency & build GenAI Application with Amazon Q​
 

The InVID Plug-in: Web Video Verification on the Browser

  • 1. The InVID Plug-in: Web Video Verification on the Browser D. Teyssou1, J.-M. Leung1, E. Apostolidis2, K. Apostolidis2, S. Papadopoulos2, M. Zampoglou2, O. Papadopoulou2, V. Mezaris2 1. AFP Medialab, Agence France-Presse 2. Information Technologies Institute / Centre for Research and Technology Hellas ACM MM 2017, Mountain View, CA, USA, October 2017
  • 2. Overview • Introduction - problem formulation • State-of-the-art on media verification • Proposed approach: The InVID Plug-in • Plug-in verification modules • Case study • Conclusions
  • 3. Introduction – problem formulation • User Generated Content (UGC): a valuable resource… – Digital media revolution & convergence of social media with broadband connectivity bring breaking news to online video platforms – News organizations often rely on user-generated recordings of breaking and developing news events shared via social media • …but also a tricky one – Deception facilitated by access to sophisticated editing and content management tools – Rapid spread of fake information in electronic networks • Careful verification of third-party content is necessary for reputable news outlets; at present, this manual process – Reduces their ability to break news quickly – Increases their costs in times of tight budgets
  • 4. State-of-the-art on media verification • Daily routine in newsrooms contains: – Verification of images/videos posted on social networks – Debunking fake news and hoaxes spread via social media • Current UGC verification pipeline for journalists: – Switch back and forth among several ever-changing tools and services – Video verification relies on: • Search engines, online translators, video playing and editing software, map services, and other services (e.g. historical weather information) – Image and video duplicate detection relies on: • Google image search, plug-ins such as RevEye1 or TinEye2 • The YouTube DataViewer3 • The use of Google image search after taking screenshots of the video • No integrated solution exists to address verification of UGC 1. https://goo.gl/ZRHTDH 2. https://tineye.com/ 3.https://citizenevidence.amnestyusa.org/
  • 5. Proposed approach • Through design thinking methodology, observing and understanding of journalistic workflows and of the difficulties when verifying information, we built a browser plug-in that works as a verification “Swiss army knife”
  • 6. Proposed approach • The plug-in provides a unified view over a number of third party services and novel technologies, via a single GUI • It is freely available at: http://www.invid-project.eu/verify
  • 7. Plug-in verification modules • The InVID Plug-in integrates modules for: – Video context analysis – Advanced Twitter search – Video keyframe selection for reverse video search – Visual inspection of images and keyframes through a magnifying glass – Forensic analysis of keyframes
  • 8. Plug-in verification modules • Video context analysis: collects, extracts and presents to the user several data and metadata related to a video
  • 9. Plug-in verification modules • Video context analysis: collects, extracts and presents to the user several data and metadata related to a video • Video and channel metadata contain: – Video name and description – Video and channel views count – Video upload date – Channel creation date – Locations mentioned in the description
  • 10. Plug-in verification modules • Video context analysis: collects, extracts and presents to the user several data and metadata related to a video • Comment analysis: – Extracts comments potential related to verification based on a list of keywords, such as “lies”, “fake”, “wrong”, and “confirm” – Presents them in a compact form, allowing user to quickly sift through them
  • 11. Plug-in verification modules • Video context analysis: collects, extracts and presents to the user several data and metadata related to a video • External search and Twitter timeline analysis: – Performs reverse image search using the available video thumbnails and the Google and Yandex engines – Searches for video-related posts on Twitter based on the video URL, allowing user to evaluate Twitter activity around the video
  • 12. Plug-in verification modules • Advanced Twitter search: allows to query Twitter by time interval up to the minute • Converts regular calendar dates into Unix timestamps automatically • Replaces a manual process that uses Epoch Converter1 1. https://www.epochconverter.com
  • 13. Plug-in verification modules • Keyframe selection: segments a single-shot video into sub- shots and selects one representative keyframe from each part • Visual content is represented using Discrete Cosine Transform • Each sub-shot is comprised by a set of temporally contiguous and visually similar frames based on the cosine similarity
  • 14. Plug-in verification modules • Keyframe selection: allows user to perform keyframe-based reverse video search on the Web
  • 15. Plug-in verification modules • Keyframe magnifier: enables deep inspection of image or keyframe details through a digital magnifying glass • These details might help to: – Confirm location or identity (e.g. car plates or signs) – Spot pixel incoherencies that indicate possible tampering • Metadata reader presents related image/video metadata (creation / modification date, geo-coordinates, etc.)
  • 16. Plug-in verification modules • Forensic analysis of keyframes: provides analysis tools for tampering detection and localization in images • Designed to cover professionals’ needs for image verification Integrated tampering localization algorithms Double JPEG Quantization JPEG Ghosts JPEG Blocking Artifact Inconsistencies Median Filtering Noise Residue Discrete Wavelet High Frequency Noise Variance Error Level Analysis GRIDS (JPEG Blocking Grid Inconsistencies)
  • 17. Case study • InVID Plug-in was used by several AFP and DW journalists over the last three months, helping to: – Debunk a fake video using the keyframe selection tool: • Shared video allegedly on the robbery of a Manila casino on June 2017, was an older video from a robbery in a Surinam casino on December 2011 – Debunk a fake image using the Twitter advanced search tool: • Image shared on Twitter during the Champs Elysees failed attack, was a re-posted image from an arrest in London after a previous terror attack – Prove a wrong claim using the magnifier tool: • Image of a jet allegedly used by a candidate of the French presidential election to travel to a meeting was in fact registered in the US
  • 18. Case study • According to the analytics of the Google Chrome store the current users of the plug-in are more than 1000 • Based on the received feedback via social media:
  • 19. Case study • According to the analytics of the Google Chrome store the current users of the plug-in are more than 1000 • Based on the received feedback via social media: The plug-in is currently used by journalists and experts worldwide, effectively supporting them in their efforts to debunk a number of fake videos!
  • 20. Conclusions and next steps • The InVID plug-in seamlessly integrates a set of SoA tools and services for media analysis, that assist the verification of UGV • Testing in real-life scenarios shows that it can speed up video verification process for journalists, media scholars and NGOs • The InVID plug-in will be updated over the next months by enhancing the current features • Stay tuned at: www.invid-project.eu