SlideShare a Scribd company logo
1 of 1
Download to read offline
Supported by:
ITI-CERTH participation in TRECVID 2018
Konstantinos Avgerinakis, Anastasia Moumtzidou, Damianos Galanopoulos, Georgios Orfanidis, Stelios Andreadis, Foteini Markatopoulou,
Elissavet Batziou, Konstantinos Ioannidis, Stefanos Vrochidis, Vasileios Mezaris, Ioannis Kompatsiaris
Ad-hoc Video Search
Activities in Extended Video
Information Technologies Institute (ITI), Centre for Research and Technology Hellas (CERTH), Thessaloniki, Greece
{koafgeri, moumtzid, dgalanop, g.orfanidis, andreadisst, markatopoulou, batziou.el, kioannid, stefanos, bmezaris, ikom} @iti.gr
Instance Search
Keyframe Representation: Keyframe
annotation using 33142 concept detectors.
• ImageNet 1000 - Late fusion of 5
different DCNNs.
• Pre-trained ResNet ImageNet DCNN;
fine-tuned on SIN 345 concepts, plus 3
additional concepts derived from SIN.
• Pre-trained DCNNs for FCVID-239,
Places-205, Places-365, Hybrid-1365 &
ImageNet 4000, 4437, 8201, 12988.
Runs:
ITI-CERTH 1: Runs 2 & 4 combination (late fusion)
ITI-CERTH 2: Approach (iii) for query representation
ITI-CERTH 3: Approach (ii) for query representation
ITI-CERTH 4: Approach (i) for query representation
Run
ITI-
CERTH 1
ITI-
CERTH 2
ITI-
CERTH 3
ITI-
CERTH 4
MXinfAP 0.043 0.047 0.040 0.034
Conclusions:
• Combination of DCNNs with traditional
approaches (HOG-HOF and SVM classification).
• Accuracy above 99% in training, indicates that the
contestants activity features are linearly separable.
Activity Recognition Pipeline:
min max min max
0.4536572 0.99807
0.5576526 0.9994005
mean 𝑃 𝑚𝑖𝑠𝑠@𝑅𝑎𝑡𝑒 𝐹𝐴=1𝐴𝐷
mean 𝑃 𝑚𝑖𝑠𝑠@𝑅𝑎𝑡𝑒 𝐹𝐴=1𝐴O𝐷
Results:
High Level Visual Concept Retrieval:
• 346 TRECVID concepts using pre-trained DCNNs
& Training with Linear SVMs.
• GoogLeNet CNN network for landscape
recognition using the Places-205 scene
categories.
Visual Similarity Search module:
• Use of pre-trained DCNN on 5055 ImageNet
categories & selection of last pooling layer for
keyframe representation.
• Nearest Neighbour search realized using
Asymmetric Distance Computation.
Face detection and Face Retrieval Module:
• Face detection: detect faces using Tiny face
detection algorithm.
• Face feature extraction: extract CNN descriptors
using VGG-Very-Deep-16 CNN architecture &
use of last FC layer as feature vector.
• Construction of an IVFADC index for fast face
retrieval.
Scene Similarity Search Module:
• Use the feature vector of the last fully
connected layer and the output of the softmax
layer of the VGG16 DCNN pre-trained on Places-
365 dataset. VERGE GUI
http://mklab-services.iti.gr/verge/trec2018
VERGE video search engine modules:
VERGE graphical user interface:
• Friendly and efficient navigation.
• Various retrieval utilities, displayed
in a sliding menu or as buttons.
• Shot-based representation of
results.
Conclusion:
• High level features are extracted
and combined.
Run ID MAP Recall
Run 1 0.114 478/11717
Semantic embeddings: Both query and keyframe concept-based
representations are transformed to semantic-embedding representations.
Query Representation: Cue extraction and
query representation as a vector of concepts.
Three approaches:
i. A variety of complex NLP rules for cue
extraction; multiple stages of matching
cues with concepts.
ii. Cue extraction by finding noun phrases;
multiple stages of cue-concept matching.
iii. Keywords are extracted by finding nouns;
the most similar concept is selected for
each noun.
• The performance of the object detection module is vital, which in our case was not
secured. For this, many activities weren’t evaluated.
• An improved object detection model, as well as, an activity filter for irrelevant activities,
will improve the performance.
Results:
Results:

More Related Content

Similar to ITI-CERTH participation in TRECVID 2018

Motion capture for Animation
Motion capture for AnimationMotion capture for Animation
Motion capture for AnimationIRJET Journal
 
Operation-wise Attention Network for Tampering Localization Fusion.
Operation-wise Attention Network for Tampering Localization Fusion.Operation-wise Attention Network for Tampering Localization Fusion.
Operation-wise Attention Network for Tampering Localization Fusion.Weverify
 
Foreground algorithms for detection and extraction of an object in multimedia...
Foreground algorithms for detection and extraction of an object in multimedia...Foreground algorithms for detection and extraction of an object in multimedia...
Foreground algorithms for detection and extraction of an object in multimedia...IJECEIAES
 
ROAD SIGN DETECTION USING CONVOLUTIONAL NEURAL NETWORK (CNN)
ROAD SIGN DETECTION USING CONVOLUTIONAL NEURAL NETWORK (CNN)ROAD SIGN DETECTION USING CONVOLUTIONAL NEURAL NETWORK (CNN)
ROAD SIGN DETECTION USING CONVOLUTIONAL NEURAL NETWORK (CNN)IRJET Journal
 
Secure IoT Systems Monitor Framework using Probabilistic Image Encryption
Secure IoT Systems Monitor Framework using Probabilistic Image EncryptionSecure IoT Systems Monitor Framework using Probabilistic Image Encryption
Secure IoT Systems Monitor Framework using Probabilistic Image EncryptionIJAEMSJORNAL
 
Content-based product image retrieval using squared-hinge loss trained convol...
Content-based product image retrieval using squared-hinge loss trained convol...Content-based product image retrieval using squared-hinge loss trained convol...
Content-based product image retrieval using squared-hinge loss trained convol...IJECEIAES
 
“How Transformers Are Changing the Nature of Deep Learning Models,” a Present...
“How Transformers Are Changing the Nature of Deep Learning Models,” a Present...“How Transformers Are Changing the Nature of Deep Learning Models,” a Present...
“How Transformers Are Changing the Nature of Deep Learning Models,” a Present...Edge AI and Vision Alliance
 
IRJET- A Deep Learning based Approach for Automatic Detection of Bike Rid...
IRJET-  	  A Deep Learning based Approach for Automatic Detection of Bike Rid...IRJET-  	  A Deep Learning based Approach for Automatic Detection of Bike Rid...
IRJET- A Deep Learning based Approach for Automatic Detection of Bike Rid...IRJET Journal
 
“COVID-19 Safe Distancing Measures in Public Spaces with Edge AI,” a Presenta...
“COVID-19 Safe Distancing Measures in Public Spaces with Edge AI,” a Presenta...“COVID-19 Safe Distancing Measures in Public Spaces with Edge AI,” a Presenta...
“COVID-19 Safe Distancing Measures in Public Spaces with Edge AI,” a Presenta...Edge AI and Vision Alliance
 
Combining textual and visual features for Ad-hoc Video Search
Combining textual and visual features for Ad-hoc Video SearchCombining textual and visual features for Ad-hoc Video Search
Combining textual and visual features for Ad-hoc Video SearchVasileiosMezaris
 
Virtual Contact Discovery using Facial Recognition
Virtual Contact Discovery using Facial RecognitionVirtual Contact Discovery using Facial Recognition
Virtual Contact Discovery using Facial RecognitionIRJET Journal
 
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 2018InVID Project
 
IRJET - 3D Virtual Dressing Room Application
IRJET -  	  3D Virtual Dressing Room ApplicationIRJET -  	  3D Virtual Dressing Room Application
IRJET - 3D Virtual Dressing Room ApplicationIRJET Journal
 
Transfer Learning Model for Image Segmentation by Integrating U-NetPlusPlus a...
Transfer Learning Model for Image Segmentation by Integrating U-NetPlusPlus a...Transfer Learning Model for Image Segmentation by Integrating U-NetPlusPlus a...
Transfer Learning Model for Image Segmentation by Integrating U-NetPlusPlus a...YutaSuzuki27
 
Siddha Ganju. Deep learning on mobile
Siddha Ganju. Deep learning on mobileSiddha Ganju. Deep learning on mobile
Siddha Ganju. Deep learning on mobileLviv Startup Club
 
Siddha Ganju, NVIDIA. Deep Learning for Mobile
Siddha Ganju, NVIDIA. Deep Learning for MobileSiddha Ganju, NVIDIA. Deep Learning for Mobile
Siddha Ganju, NVIDIA. Deep Learning for MobileIT Arena
 
Poster Competition - Hwan Lee
Poster Competition - Hwan LeePoster Competition - Hwan Lee
Poster Competition - Hwan LeeHwan Lee
 
USING IMAGE CLASSIFICATION TO INCENTIVIZE RECYCLING
USING IMAGE CLASSIFICATION TO INCENTIVIZE RECYCLINGUSING IMAGE CLASSIFICATION TO INCENTIVIZE RECYCLING
USING IMAGE CLASSIFICATION TO INCENTIVIZE RECYCLINGIRJET Journal
 
Synthesizing pseudo 2.5 d content from monocular videos for mixed reality
Synthesizing pseudo 2.5 d content from monocular videos for mixed realitySynthesizing pseudo 2.5 d content from monocular videos for mixed reality
Synthesizing pseudo 2.5 d content from monocular videos for mixed realityNAVER Engineering
 

Similar to ITI-CERTH participation in TRECVID 2018 (20)

kanimozhi2019.pdf
kanimozhi2019.pdfkanimozhi2019.pdf
kanimozhi2019.pdf
 
Motion capture for Animation
Motion capture for AnimationMotion capture for Animation
Motion capture for Animation
 
Operation-wise Attention Network for Tampering Localization Fusion.
Operation-wise Attention Network for Tampering Localization Fusion.Operation-wise Attention Network for Tampering Localization Fusion.
Operation-wise Attention Network for Tampering Localization Fusion.
 
Foreground algorithms for detection and extraction of an object in multimedia...
Foreground algorithms for detection and extraction of an object in multimedia...Foreground algorithms for detection and extraction of an object in multimedia...
Foreground algorithms for detection and extraction of an object in multimedia...
 
ROAD SIGN DETECTION USING CONVOLUTIONAL NEURAL NETWORK (CNN)
ROAD SIGN DETECTION USING CONVOLUTIONAL NEURAL NETWORK (CNN)ROAD SIGN DETECTION USING CONVOLUTIONAL NEURAL NETWORK (CNN)
ROAD SIGN DETECTION USING CONVOLUTIONAL NEURAL NETWORK (CNN)
 
Secure IoT Systems Monitor Framework using Probabilistic Image Encryption
Secure IoT Systems Monitor Framework using Probabilistic Image EncryptionSecure IoT Systems Monitor Framework using Probabilistic Image Encryption
Secure IoT Systems Monitor Framework using Probabilistic Image Encryption
 
Content-based product image retrieval using squared-hinge loss trained convol...
Content-based product image retrieval using squared-hinge loss trained convol...Content-based product image retrieval using squared-hinge loss trained convol...
Content-based product image retrieval using squared-hinge loss trained convol...
 
“How Transformers Are Changing the Nature of Deep Learning Models,” a Present...
“How Transformers Are Changing the Nature of Deep Learning Models,” a Present...“How Transformers Are Changing the Nature of Deep Learning Models,” a Present...
“How Transformers Are Changing the Nature of Deep Learning Models,” a Present...
 
IRJET- A Deep Learning based Approach for Automatic Detection of Bike Rid...
IRJET-  	  A Deep Learning based Approach for Automatic Detection of Bike Rid...IRJET-  	  A Deep Learning based Approach for Automatic Detection of Bike Rid...
IRJET- A Deep Learning based Approach for Automatic Detection of Bike Rid...
 
“COVID-19 Safe Distancing Measures in Public Spaces with Edge AI,” a Presenta...
“COVID-19 Safe Distancing Measures in Public Spaces with Edge AI,” a Presenta...“COVID-19 Safe Distancing Measures in Public Spaces with Edge AI,” a Presenta...
“COVID-19 Safe Distancing Measures in Public Spaces with Edge AI,” a Presenta...
 
Combining textual and visual features for Ad-hoc Video Search
Combining textual and visual features for Ad-hoc Video SearchCombining textual and visual features for Ad-hoc Video Search
Combining textual and visual features for Ad-hoc Video Search
 
Virtual Contact Discovery using Facial Recognition
Virtual Contact Discovery using Facial RecognitionVirtual Contact Discovery using Facial Recognition
Virtual Contact Discovery using Facial Recognition
 
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
 
IRJET - 3D Virtual Dressing Room Application
IRJET -  	  3D Virtual Dressing Room ApplicationIRJET -  	  3D Virtual Dressing Room Application
IRJET - 3D Virtual Dressing Room Application
 
Transfer Learning Model for Image Segmentation by Integrating U-NetPlusPlus a...
Transfer Learning Model for Image Segmentation by Integrating U-NetPlusPlus a...Transfer Learning Model for Image Segmentation by Integrating U-NetPlusPlus a...
Transfer Learning Model for Image Segmentation by Integrating U-NetPlusPlus a...
 
Siddha Ganju. Deep learning on mobile
Siddha Ganju. Deep learning on mobileSiddha Ganju. Deep learning on mobile
Siddha Ganju. Deep learning on mobile
 
Siddha Ganju, NVIDIA. Deep Learning for Mobile
Siddha Ganju, NVIDIA. Deep Learning for MobileSiddha Ganju, NVIDIA. Deep Learning for Mobile
Siddha Ganju, NVIDIA. Deep Learning for Mobile
 
Poster Competition - Hwan Lee
Poster Competition - Hwan LeePoster Competition - Hwan Lee
Poster Competition - Hwan Lee
 
USING IMAGE CLASSIFICATION TO INCENTIVIZE RECYCLING
USING IMAGE CLASSIFICATION TO INCENTIVIZE RECYCLINGUSING IMAGE CLASSIFICATION TO INCENTIVIZE RECYCLING
USING IMAGE CLASSIFICATION TO INCENTIVIZE RECYCLING
 
Synthesizing pseudo 2.5 d content from monocular videos for mixed reality
Synthesizing pseudo 2.5 d content from monocular videos for mixed realitySynthesizing pseudo 2.5 d content from monocular videos for mixed reality
Synthesizing pseudo 2.5 d content from monocular videos for mixed reality
 

More from MOVING Project

Opening up education through digitization. Remarks on recent developments in ...
Opening up education through digitization. Remarks on recent developments in ...Opening up education through digitization. Remarks on recent developments in ...
Opening up education through digitization. Remarks on recent developments in ...MOVING Project
 
MOVING: Applying digital science methodology for TVET
MOVING: Applying digital science methodology for TVETMOVING: Applying digital science methodology for TVET
MOVING: Applying digital science methodology for TVETMOVING Project
 
Learning analytics for reflective learning
Learning analytics for reflective learningLearning analytics for reflective learning
Learning analytics for reflective learningMOVING Project
 
Challenges in Developing Automatic Learning Guidance in Relation to an Inform...
Challenges in Developing Automatic Learning Guidance in Relation to an Inform...Challenges in Developing Automatic Learning Guidance in Relation to an Inform...
Challenges in Developing Automatic Learning Guidance in Relation to an Inform...MOVING Project
 
Unesco mobileweek 2019_frontier_tech_oer-final
Unesco mobileweek 2019_frontier_tech_oer-finalUnesco mobileweek 2019_frontier_tech_oer-final
Unesco mobileweek 2019_frontier_tech_oer-finalMOVING Project
 
Inferring knowledge acquisition through Web navigation behaviour
Inferring knowledge acquisition through Web navigation behaviourInferring knowledge acquisition through Web navigation behaviour
Inferring knowledge acquisition through Web navigation behaviourMOVING Project
 
Wissenschaft 2.0 und offene Forschungsmethoden vermitteln– Der MOOC "Science ...
Wissenschaft 2.0 und offene Forschungsmethoden vermitteln– Der MOOC "Science ...Wissenschaft 2.0 und offene Forschungsmethoden vermitteln– Der MOOC "Science ...
Wissenschaft 2.0 und offene Forschungsmethoden vermitteln– Der MOOC "Science ...MOVING Project
 
Wissenschaft 2.0 und offene Forschungsmethoden vermitteln: Der MOOC Science 2...
Wissenschaft 2.0 und offene Forschungsmethoden vermitteln: Der MOOC Science 2...Wissenschaft 2.0 und offene Forschungsmethoden vermitteln: Der MOOC Science 2...
Wissenschaft 2.0 und offene Forschungsmethoden vermitteln: Der MOOC Science 2...MOVING Project
 
VERGE: A Multimodal Interactive Search Engine for Video Browsing and Retrieval
VERGE: A Multimodal Interactive Search Engine for Video Browsing and RetrievalVERGE: A Multimodal Interactive Search Engine for Video Browsing and Retrieval
VERGE: A Multimodal Interactive Search Engine for Video Browsing and RetrievalMOVING Project
 
Temporal Lecture Video Fragmentation using Word Embeddings
Temporal Lecture Video Fragmentation using Word EmbeddingsTemporal Lecture Video Fragmentation using Word Embeddings
Temporal Lecture Video Fragmentation using Word EmbeddingsMOVING Project
 
The Impact of Blocking and Name-Matching on Author Disambiguation.
The Impact of Blocking and Name-Matching on Author Disambiguation.The Impact of Blocking and Name-Matching on Author Disambiguation.
The Impact of Blocking and Name-Matching on Author Disambiguation.MOVING Project
 
Effective Unsupervised Author Disambiguation with Relative Frequencies
Effective Unsupervised Author Disambiguation with Relative FrequenciesEffective Unsupervised Author Disambiguation with Relative Frequencies
Effective Unsupervised Author Disambiguation with Relative FrequenciesMOVING Project
 
What to read next? Challenges and Preliminary Results in Selecting Represen...
What to read next? Challenges and  Preliminary Results in Selecting  Represen...What to read next? Challenges and  Preliminary Results in Selecting  Represen...
What to read next? Challenges and Preliminary Results in Selecting Represen...MOVING Project
 
Qualitative Analysis of Vocabulary Evolution on the Linked Open Data Cloud
Qualitative Analysis of Vocabulary Evolution on the Linked Open Data CloudQualitative Analysis of Vocabulary Evolution on the Linked Open Data Cloud
Qualitative Analysis of Vocabulary Evolution on the Linked Open Data CloudMOVING Project
 
Analyzing the Evolution of Vocabulary Terms and Their Impact on the LOD Cloud
Analyzing the Evolution of Vocabulary Terms and Their Impact on the LOD CloudAnalyzing the Evolution of Vocabulary Terms and Their Impact on the LOD Cloud
Analyzing the Evolution of Vocabulary Terms and Their Impact on the LOD CloudMOVING Project
 
Keeping Linked Open Data Caches Up-to-date by Predicting the Life-time of RDF...
Keeping Linked Open Data Caches Up-to-date by Predicting the Life-time of RDF...Keeping Linked Open Data Caches Up-to-date by Predicting the Life-time of RDF...
Keeping Linked Open Data Caches Up-to-date by Predicting the Life-time of RDF...MOVING Project
 
Deep Multi-task Learning with Label Correlation Constraint for Video Concept ...
Deep Multi-task Learning with Label Correlation Constraint for Video Concept ...Deep Multi-task Learning with Label Correlation Constraint for Video Concept ...
Deep Multi-task Learning with Label Correlation Constraint for Video Concept ...MOVING Project
 
Generic to Specific Recognition Models for Membership Analysis in Group Videos
Generic to Specific Recognition Models for Membership Analysis in Group VideosGeneric to Specific Recognition Models for Membership Analysis in Group Videos
Generic to Specific Recognition Models for Membership Analysis in Group VideosMOVING Project
 
MOVING the Industry 4.0
MOVING the Industry 4.0MOVING the Industry 4.0
MOVING the Industry 4.0MOVING Project
 
MOVING presentation at JSI
MOVING presentation at JSIMOVING presentation at JSI
MOVING presentation at JSIMOVING Project
 

More from MOVING Project (20)

Opening up education through digitization. Remarks on recent developments in ...
Opening up education through digitization. Remarks on recent developments in ...Opening up education through digitization. Remarks on recent developments in ...
Opening up education through digitization. Remarks on recent developments in ...
 
MOVING: Applying digital science methodology for TVET
MOVING: Applying digital science methodology for TVETMOVING: Applying digital science methodology for TVET
MOVING: Applying digital science methodology for TVET
 
Learning analytics for reflective learning
Learning analytics for reflective learningLearning analytics for reflective learning
Learning analytics for reflective learning
 
Challenges in Developing Automatic Learning Guidance in Relation to an Inform...
Challenges in Developing Automatic Learning Guidance in Relation to an Inform...Challenges in Developing Automatic Learning Guidance in Relation to an Inform...
Challenges in Developing Automatic Learning Guidance in Relation to an Inform...
 
Unesco mobileweek 2019_frontier_tech_oer-final
Unesco mobileweek 2019_frontier_tech_oer-finalUnesco mobileweek 2019_frontier_tech_oer-final
Unesco mobileweek 2019_frontier_tech_oer-final
 
Inferring knowledge acquisition through Web navigation behaviour
Inferring knowledge acquisition through Web navigation behaviourInferring knowledge acquisition through Web navigation behaviour
Inferring knowledge acquisition through Web navigation behaviour
 
Wissenschaft 2.0 und offene Forschungsmethoden vermitteln– Der MOOC "Science ...
Wissenschaft 2.0 und offene Forschungsmethoden vermitteln– Der MOOC "Science ...Wissenschaft 2.0 und offene Forschungsmethoden vermitteln– Der MOOC "Science ...
Wissenschaft 2.0 und offene Forschungsmethoden vermitteln– Der MOOC "Science ...
 
Wissenschaft 2.0 und offene Forschungsmethoden vermitteln: Der MOOC Science 2...
Wissenschaft 2.0 und offene Forschungsmethoden vermitteln: Der MOOC Science 2...Wissenschaft 2.0 und offene Forschungsmethoden vermitteln: Der MOOC Science 2...
Wissenschaft 2.0 und offene Forschungsmethoden vermitteln: Der MOOC Science 2...
 
VERGE: A Multimodal Interactive Search Engine for Video Browsing and Retrieval
VERGE: A Multimodal Interactive Search Engine for Video Browsing and RetrievalVERGE: A Multimodal Interactive Search Engine for Video Browsing and Retrieval
VERGE: A Multimodal Interactive Search Engine for Video Browsing and Retrieval
 
Temporal Lecture Video Fragmentation using Word Embeddings
Temporal Lecture Video Fragmentation using Word EmbeddingsTemporal Lecture Video Fragmentation using Word Embeddings
Temporal Lecture Video Fragmentation using Word Embeddings
 
The Impact of Blocking and Name-Matching on Author Disambiguation.
The Impact of Blocking and Name-Matching on Author Disambiguation.The Impact of Blocking and Name-Matching on Author Disambiguation.
The Impact of Blocking and Name-Matching on Author Disambiguation.
 
Effective Unsupervised Author Disambiguation with Relative Frequencies
Effective Unsupervised Author Disambiguation with Relative FrequenciesEffective Unsupervised Author Disambiguation with Relative Frequencies
Effective Unsupervised Author Disambiguation with Relative Frequencies
 
What to read next? Challenges and Preliminary Results in Selecting Represen...
What to read next? Challenges and  Preliminary Results in Selecting  Represen...What to read next? Challenges and  Preliminary Results in Selecting  Represen...
What to read next? Challenges and Preliminary Results in Selecting Represen...
 
Qualitative Analysis of Vocabulary Evolution on the Linked Open Data Cloud
Qualitative Analysis of Vocabulary Evolution on the Linked Open Data CloudQualitative Analysis of Vocabulary Evolution on the Linked Open Data Cloud
Qualitative Analysis of Vocabulary Evolution on the Linked Open Data Cloud
 
Analyzing the Evolution of Vocabulary Terms and Their Impact on the LOD Cloud
Analyzing the Evolution of Vocabulary Terms and Their Impact on the LOD CloudAnalyzing the Evolution of Vocabulary Terms and Their Impact on the LOD Cloud
Analyzing the Evolution of Vocabulary Terms and Their Impact on the LOD Cloud
 
Keeping Linked Open Data Caches Up-to-date by Predicting the Life-time of RDF...
Keeping Linked Open Data Caches Up-to-date by Predicting the Life-time of RDF...Keeping Linked Open Data Caches Up-to-date by Predicting the Life-time of RDF...
Keeping Linked Open Data Caches Up-to-date by Predicting the Life-time of RDF...
 
Deep Multi-task Learning with Label Correlation Constraint for Video Concept ...
Deep Multi-task Learning with Label Correlation Constraint for Video Concept ...Deep Multi-task Learning with Label Correlation Constraint for Video Concept ...
Deep Multi-task Learning with Label Correlation Constraint for Video Concept ...
 
Generic to Specific Recognition Models for Membership Analysis in Group Videos
Generic to Specific Recognition Models for Membership Analysis in Group VideosGeneric to Specific Recognition Models for Membership Analysis in Group Videos
Generic to Specific Recognition Models for Membership Analysis in Group Videos
 
MOVING the Industry 4.0
MOVING the Industry 4.0MOVING the Industry 4.0
MOVING the Industry 4.0
 
MOVING presentation at JSI
MOVING presentation at JSIMOVING presentation at JSI
MOVING presentation at JSI
 

Recently uploaded

Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Paola De la Torre
 
Developing An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilDeveloping An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilV3cube
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Igalia
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking MenDelhi Call girls
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Miguel Araújo
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...Neo4j
 
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 WorkerThousandEyes
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...Martijn de Jong
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slidevu2urc
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationSafe Software
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Enterprise Knowledge
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Servicegiselly40
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024The Digital Insurer
 
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxMalak Abu Hammad
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxKatpro Technologies
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking MenDelhi Call girls
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfEnterprise Knowledge
 

Recently uploaded (20)

Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101Salesforce Community Group Quito, Salesforce 101
Salesforce Community Group Quito, Salesforce 101
 
Developing An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilDeveloping An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of Brazil
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
 
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men08448380779 Call Girls In Greater Kailash - I Women Seeking Men
08448380779 Call Girls In Greater Kailash - I Women Seeking Men
 
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
Mastering MySQL Database Architecture: Deep Dive into MySQL Shell and MySQL R...
 
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...Workshop - Best of Both Worlds_ Combine  KG and Vector search for  enhanced R...
Workshop - Best of Both Worlds_ Combine KG and Vector search for enhanced R...
 
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
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
Histor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slideHistor y of HAM Radio presentation slide
Histor y of HAM Radio presentation slide
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time AutomationFrom Event to Action: Accelerate Your Decision Making with Real-Time Automation
From Event to Action: Accelerate Your Decision Making with Real-Time Automation
 
Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...Driving Behavioral Change for Information Management through Data-Driven Gree...
Driving Behavioral Change for Information Management through Data-Driven Gree...
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 
Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
Neo4j - How KGs are shaping the future of Generative AI at AWS Summit London ...
 
The Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptxThe Codex of Business Writing Software for Real-World Solutions 2.pptx
The Codex of Business Writing Software for Real-World Solutions 2.pptx
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
 
08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men08448380779 Call Girls In Friends Colony Women Seeking Men
08448380779 Call Girls In Friends Colony Women Seeking Men
 
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdfThe Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
The Role of Taxonomy and Ontology in Semantic Layers - Heather Hedden.pdf
 

ITI-CERTH participation in TRECVID 2018

  • 1. Supported by: ITI-CERTH participation in TRECVID 2018 Konstantinos Avgerinakis, Anastasia Moumtzidou, Damianos Galanopoulos, Georgios Orfanidis, Stelios Andreadis, Foteini Markatopoulou, Elissavet Batziou, Konstantinos Ioannidis, Stefanos Vrochidis, Vasileios Mezaris, Ioannis Kompatsiaris Ad-hoc Video Search Activities in Extended Video Information Technologies Institute (ITI), Centre for Research and Technology Hellas (CERTH), Thessaloniki, Greece {koafgeri, moumtzid, dgalanop, g.orfanidis, andreadisst, markatopoulou, batziou.el, kioannid, stefanos, bmezaris, ikom} @iti.gr Instance Search Keyframe Representation: Keyframe annotation using 33142 concept detectors. • ImageNet 1000 - Late fusion of 5 different DCNNs. • Pre-trained ResNet ImageNet DCNN; fine-tuned on SIN 345 concepts, plus 3 additional concepts derived from SIN. • Pre-trained DCNNs for FCVID-239, Places-205, Places-365, Hybrid-1365 & ImageNet 4000, 4437, 8201, 12988. Runs: ITI-CERTH 1: Runs 2 & 4 combination (late fusion) ITI-CERTH 2: Approach (iii) for query representation ITI-CERTH 3: Approach (ii) for query representation ITI-CERTH 4: Approach (i) for query representation Run ITI- CERTH 1 ITI- CERTH 2 ITI- CERTH 3 ITI- CERTH 4 MXinfAP 0.043 0.047 0.040 0.034 Conclusions: • Combination of DCNNs with traditional approaches (HOG-HOF and SVM classification). • Accuracy above 99% in training, indicates that the contestants activity features are linearly separable. Activity Recognition Pipeline: min max min max 0.4536572 0.99807 0.5576526 0.9994005 mean 𝑃 𝑚𝑖𝑠𝑠@𝑅𝑎𝑡𝑒 𝐹𝐴=1𝐴𝐷 mean 𝑃 𝑚𝑖𝑠𝑠@𝑅𝑎𝑡𝑒 𝐹𝐴=1𝐴O𝐷 Results: High Level Visual Concept Retrieval: • 346 TRECVID concepts using pre-trained DCNNs & Training with Linear SVMs. • GoogLeNet CNN network for landscape recognition using the Places-205 scene categories. Visual Similarity Search module: • Use of pre-trained DCNN on 5055 ImageNet categories & selection of last pooling layer for keyframe representation. • Nearest Neighbour search realized using Asymmetric Distance Computation. Face detection and Face Retrieval Module: • Face detection: detect faces using Tiny face detection algorithm. • Face feature extraction: extract CNN descriptors using VGG-Very-Deep-16 CNN architecture & use of last FC layer as feature vector. • Construction of an IVFADC index for fast face retrieval. Scene Similarity Search Module: • Use the feature vector of the last fully connected layer and the output of the softmax layer of the VGG16 DCNN pre-trained on Places- 365 dataset. VERGE GUI http://mklab-services.iti.gr/verge/trec2018 VERGE video search engine modules: VERGE graphical user interface: • Friendly and efficient navigation. • Various retrieval utilities, displayed in a sliding menu or as buttons. • Shot-based representation of results. Conclusion: • High level features are extracted and combined. Run ID MAP Recall Run 1 0.114 478/11717 Semantic embeddings: Both query and keyframe concept-based representations are transformed to semantic-embedding representations. Query Representation: Cue extraction and query representation as a vector of concepts. Three approaches: i. A variety of complex NLP rules for cue extraction; multiple stages of matching cues with concepts. ii. Cue extraction by finding noun phrases; multiple stages of cue-concept matching. iii. Keywords are extracted by finding nouns; the most similar concept is selected for each noun. • The performance of the object detection module is vital, which in our case was not secured. For this, many activities weren’t evaluated. • An improved object detection model, as well as, an activity filter for irrelevant activities, will improve the performance. Results: Results: