SlideShare a Scribd company logo
EURECOM @MediaEval 2017:
Media Genre Inference for
Predicting Media Interestingness
O. Ben-Ahmed, J. Wacker, A. Gaballo, B. Huet
EURECOM
Sophia Antipolis, France
Introduction
 Predicting Media Interestingness (PMI)
 automatically analyze media data
 identify the most attractive content
 Content based approaches
 gap between low-level features
and high-level human perception
 Our proposal
 Address PMI in association with
Media Genre
13/09/2017 MediaEval2017 Dublin - B. HUET, EURECOM - p 2
http://www.dailyherald.com/article/20110627/entlife/706279989/
Why Genre Inference for PMI
 Motivation
 Interestingness is highly correlated with data emotional content
 Affective representation of data content
 Hypothesis
 Emotional impact of movie genre can be a factor for interestingness
of a video fragment
 Method
 Mid-level representation based on media genre prediction for PMI
– Represent each video fragment/image as a distribution of genres
13/09/2017 MediaEval2017 Dublin - B. HUET, EURECOM - p 3
Our Framework
13/09/2017 MediaEval2017 Dublin - B. HUET, EURECOM - p 4
Media Genre Prediction
 Visual Branch
 Middle frame selection
 Deep CNN for features extraction
 DNN classifier
 Audio Branch
 Audio extraction : OpenSmile
 Deep features extraction : Soundnet
 SVM classifier
VGG Architecture
13/09/2017 MediaEval2017 Dublin - B. HUET, EURECOM - p 5
| X
| X
Media Genre Prediction Example
Visual Audio Audio-Visual
Action
Drama
Horror
Romance
Sci-fi
13/09/2017 MediaEval2017 Dublin - B. HUET, EURECOM - p 6
Media Genre Prediction Example
Visual Audio Audio-Visual
Action
Drama
Horror
Romance
Sci-fi
2.5% 33,34% 17.92%
0% 17,78% 8.89%
0.37% 2.61% 1.49%
0% 3.87% 1.93%
97.12% 42,40% 69,76%
13/09/2017 MediaEval2017 Dublin - B. HUET, EURECOM - p 7
Media Genre Prediction Example
Visual Audio Audio-Visual
Action
Drama
Horror
Romance
Sci-fi
Interestingness : 1
Rank : 1
2.5% 33,34% 17.92%
0% 17,78% 8.89%
0.37% 2.61% 1.49%
0% 3.87% 1.93%
97.12% 42,40% 69,76%
13/09/2017 MediaEval2017 Dublin - B. HUET, EURECOM - p 8
Interestingness Classification
 Features vectors
 probability vector for the genre distribution for the video/image
 Classifier
 Binary SVM,
 Taking into account the confidence score in training
 Image subtask
 Visual genre vector
 Video subtask
 Visual genre vector
 Audio-Visual genre vector
– Mean of visual- and audio-based genre vectors probabilities
13/09/2017 MediaEval2017 Dublin - B. HUET, EURECOM - p 9
Experiments and Results
TASK RUN SVM CLASSIFIER MAP MAP@10
IMAGE 1 Sigmoid kernel 0.2029 0.0587
2 Linear kernel 0.2016 0.0579
VIDEO 1 Sigmoid kernel gamma=0.5, C=100 0.2034 0.0717
2 Polynomial kernel degree=3 0.1960 0.0732
3 Polynomial kernel degree=2 0.1964 0.0640
4 Sigmoid kernel gamma=0.2, C=100 0.2094 0.0827
5 Sigmoid kernel gamma=0.3 , C=100 0.2002 0.0774
13/09/2017 MediaEval2017 Dublin - B. HUET, EURECOM - p 10
Experiments and Results
TASK RUN SVM CLASSIFIER MAP MAP@10
IMAGE 1 Sigmoid kernel 0.2029 0.0587
2 Linear kernel 0.2016 0.0579
VIDEO 1 Sigmoid kernel gamma=0.5, C=100 0.2034 0.0717
2 Polynomial kernel degree=3 0.1960 0.0732
3 Polynomial kernel degree=2 0.1964 0.0640
4 Sigmoid kernel gamma=0.2, C=100 0.2094 0.0827
5 Sigmoid kernel gamma=0.3 , C=100 0.2002 0.0774
13/09/2017 MediaEval2017 Dublin - B. HUET, EURECOM - p 11
Conclusions and Future Work
 We proposed a Genre Recognition System as a mid-
level representation for Predicting Media
Interestingness
 Deep Audio and Visual Features for Genre Recognition
 SVM Classifier for Predicting Media Interestingness
 Best Results:
 20,29 MAP for Image and 20,94 MAP for Video (on test set).
 Audio brings limited additional information for PMI
13/09/2017 MediaEval2017 Dublin - B. HUET, EURECOM - p 12
Conclusions and Future Work
 We proposed a Genre Recognition System as a mid-
level representation for Predicting Media
Interestingness
 Deep Audio and Visual Features for Genre Recognition
 SVM Classifier for Predicting Media Interestingness
 Best Results:
 20,29 MAP for Image and 20,94 MAP for Video (on test set).
 Audio brings limited additional information for PMI
 Joint learning of audio-visual features
 Integration of temporal information
13/09/2017 MediaEval2017 Dublin - B. HUET, EURECOM - p 13
Questions?
Benoit Huet.
MediaEval2017 Dublin - B. HUET, EURECOM - p 1413/09/2017
Media Genre Inference for
Predicting Media Interestingness
@
2017
Thank you,

More Related Content

Similar to Media Genre Inference for Predicting Media Interestingness

How to prepare a perfect video abstract for your research paper – Pubrica.pptx
How to prepare a perfect video abstract for your research paper – Pubrica.pptxHow to prepare a perfect video abstract for your research paper – Pubrica.pptx
How to prepare a perfect video abstract for your research paper – Pubrica.pptx
Pubrica
 
KIT at MediaEval 2012 – Content–based Genre Classification with Visual Cues
KIT at MediaEval 2012 – Content–based Genre Classification with Visual CuesKIT at MediaEval 2012 – Content–based Genre Classification with Visual Cues
KIT at MediaEval 2012 – Content–based Genre Classification with Visual CuesMediaEval2012
 
3-D Video Formats and Coding- A review
3-D Video Formats and Coding- A review3-D Video Formats and Coding- A review
3-D Video Formats and Coding- A review
inventionjournals
 
3-D Video Formats and Coding- A review
3-D Video Formats and Coding- A review3-D Video Formats and Coding- A review
3-D Video Formats and Coding- A review
inventionjournals
 
2009.06.09 chris poppe - public PhD defense
2009.06.09   chris poppe - public PhD defense2009.06.09   chris poppe - public PhD defense
2009.06.09 chris poppe - public PhD defense
Chris Poppe
 
Design and Analysis of Quantization Based Low Bit Rate Encoding System
Design and Analysis of Quantization Based Low Bit Rate Encoding SystemDesign and Analysis of Quantization Based Low Bit Rate Encoding System
Design and Analysis of Quantization Based Low Bit Rate Encoding System
ijtsrd
 
SceneBoundaryDetection (1)
SceneBoundaryDetection (1)SceneBoundaryDetection (1)
SceneBoundaryDetection (1)Devon Bates
 
3 d video coding & streaming real time of hd
3 d video coding & streaming real time of hd3 d video coding & streaming real time of hd
3 d video coding & streaming real time of hd
Empirix
 
3 d video coding & streaming real time of hd
3 d video coding & streaming real time of hd3 d video coding & streaming real time of hd
3 d video coding & streaming real time of hdEmpirix
 
Call for papers - 9th International Conference on Signal, Image Processing an...
Call for papers - 9th International Conference on Signal, Image Processing an...Call for papers - 9th International Conference on Signal, Image Processing an...
Call for papers - 9th International Conference on Signal, Image Processing an...
sipij
 
Video Coding Enhancements for HTTP Adaptive Streaming
Video Coding Enhancements for HTTP Adaptive StreamingVideo Coding Enhancements for HTTP Adaptive Streaming
Video Coding Enhancements for HTTP Adaptive Streaming
Alpen-Adria-Universität
 
Research@Lunch_Presentation.pdf
Research@Lunch_Presentation.pdfResearch@Lunch_Presentation.pdf
Research@Lunch_Presentation.pdf
Vignesh V Menon
 
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
multimediaeval
 
GAN-based video summarization
GAN-based video summarizationGAN-based video summarization
GAN-based video summarization
VasileiosMezaris
 
DIGITAL VIDEO SOURCE IDENTIFICATION BASED ON GREEN-CHANNEL PHOTO RESPONSE NON...
DIGITAL VIDEO SOURCE IDENTIFICATION BASED ON GREEN-CHANNEL PHOTO RESPONSE NON...DIGITAL VIDEO SOURCE IDENTIFICATION BASED ON GREEN-CHANNEL PHOTO RESPONSE NON...
DIGITAL VIDEO SOURCE IDENTIFICATION BASED ON GREEN-CHANNEL PHOTO RESPONSE NON...
csandit
 
76201950
7620195076201950
76201950
IJRAT
 
Comparison of compression efficiency between HEVC and VP9 based on subjective...
Comparison of compression efficiency between HEVC and VP9 based on subjective...Comparison of compression efficiency between HEVC and VP9 based on subjective...
Comparison of compression efficiency between HEVC and VP9 based on subjective...
Touradj Ebrahimi
 
Extract the Audio from Video by using python
Extract the Audio from Video by using pythonExtract the Audio from Video by using python
Extract the Audio from Video by using python
IRJET Journal
 
MediaEval 2018: Fine grained sport action recognition: Application to table t...
MediaEval 2018: Fine grained sport action recognition: Application to table t...MediaEval 2018: Fine grained sport action recognition: Application to table t...
MediaEval 2018: Fine grained sport action recognition: Application to table t...
multimediaeval
 
OPTE: Online Per-title Encoding for Live Video Streaming
OPTE: Online Per-title Encoding for Live Video StreamingOPTE: Online Per-title Encoding for Live Video Streaming
OPTE: Online Per-title Encoding for Live Video Streaming
Alpen-Adria-Universität
 

Similar to Media Genre Inference for Predicting Media Interestingness (20)

How to prepare a perfect video abstract for your research paper – Pubrica.pptx
How to prepare a perfect video abstract for your research paper – Pubrica.pptxHow to prepare a perfect video abstract for your research paper – Pubrica.pptx
How to prepare a perfect video abstract for your research paper – Pubrica.pptx
 
KIT at MediaEval 2012 – Content–based Genre Classification with Visual Cues
KIT at MediaEval 2012 – Content–based Genre Classification with Visual CuesKIT at MediaEval 2012 – Content–based Genre Classification with Visual Cues
KIT at MediaEval 2012 – Content–based Genre Classification with Visual Cues
 
3-D Video Formats and Coding- A review
3-D Video Formats and Coding- A review3-D Video Formats and Coding- A review
3-D Video Formats and Coding- A review
 
3-D Video Formats and Coding- A review
3-D Video Formats and Coding- A review3-D Video Formats and Coding- A review
3-D Video Formats and Coding- A review
 
2009.06.09 chris poppe - public PhD defense
2009.06.09   chris poppe - public PhD defense2009.06.09   chris poppe - public PhD defense
2009.06.09 chris poppe - public PhD defense
 
Design and Analysis of Quantization Based Low Bit Rate Encoding System
Design and Analysis of Quantization Based Low Bit Rate Encoding SystemDesign and Analysis of Quantization Based Low Bit Rate Encoding System
Design and Analysis of Quantization Based Low Bit Rate Encoding System
 
SceneBoundaryDetection (1)
SceneBoundaryDetection (1)SceneBoundaryDetection (1)
SceneBoundaryDetection (1)
 
3 d video coding & streaming real time of hd
3 d video coding & streaming real time of hd3 d video coding & streaming real time of hd
3 d video coding & streaming real time of hd
 
3 d video coding & streaming real time of hd
3 d video coding & streaming real time of hd3 d video coding & streaming real time of hd
3 d video coding & streaming real time of hd
 
Call for papers - 9th International Conference on Signal, Image Processing an...
Call for papers - 9th International Conference on Signal, Image Processing an...Call for papers - 9th International Conference on Signal, Image Processing an...
Call for papers - 9th International Conference on Signal, Image Processing an...
 
Video Coding Enhancements for HTTP Adaptive Streaming
Video Coding Enhancements for HTTP Adaptive StreamingVideo Coding Enhancements for HTTP Adaptive Streaming
Video Coding Enhancements for HTTP Adaptive Streaming
 
Research@Lunch_Presentation.pdf
Research@Lunch_Presentation.pdfResearch@Lunch_Presentation.pdf
Research@Lunch_Presentation.pdf
 
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
 
GAN-based video summarization
GAN-based video summarizationGAN-based video summarization
GAN-based video summarization
 
DIGITAL VIDEO SOURCE IDENTIFICATION BASED ON GREEN-CHANNEL PHOTO RESPONSE NON...
DIGITAL VIDEO SOURCE IDENTIFICATION BASED ON GREEN-CHANNEL PHOTO RESPONSE NON...DIGITAL VIDEO SOURCE IDENTIFICATION BASED ON GREEN-CHANNEL PHOTO RESPONSE NON...
DIGITAL VIDEO SOURCE IDENTIFICATION BASED ON GREEN-CHANNEL PHOTO RESPONSE NON...
 
76201950
7620195076201950
76201950
 
Comparison of compression efficiency between HEVC and VP9 based on subjective...
Comparison of compression efficiency between HEVC and VP9 based on subjective...Comparison of compression efficiency between HEVC and VP9 based on subjective...
Comparison of compression efficiency between HEVC and VP9 based on subjective...
 
Extract the Audio from Video by using python
Extract the Audio from Video by using pythonExtract the Audio from Video by using python
Extract the Audio from Video by using python
 
MediaEval 2018: Fine grained sport action recognition: Application to table t...
MediaEval 2018: Fine grained sport action recognition: Application to table t...MediaEval 2018: Fine grained sport action recognition: Application to table t...
MediaEval 2018: Fine grained sport action recognition: Application to table t...
 
OPTE: Online Per-title Encoding for Live Video Streaming
OPTE: Online Per-title Encoding for Live Video StreamingOPTE: Online Per-title Encoding for Live Video Streaming
OPTE: Online Per-title Encoding for Live Video Streaming
 

More from Benoit HUET

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...
Benoit HUET
 
Event-based MultiMedia Search and Retrieval for Question Answering
Event-based MultiMedia Search and Retrieval for Question AnsweringEvent-based MultiMedia Search and Retrieval for Question Answering
Event-based MultiMedia Search and Retrieval for Question Answering
Benoit HUET
 
Convenient Discovery of Archived Video Using Audiovisual Hyperlinking
Convenient Discovery of Archived Video Using Audiovisual HyperlinkingConvenient Discovery of Archived Video Using Audiovisual Hyperlinking
Convenient Discovery of Archived Video Using Audiovisual Hyperlinking
Benoit HUET
 
Hyper Video Browser Search and Hyperlinking in Broadcast Media
Hyper Video Browser Search and Hyperlinking in Broadcast MediaHyper Video Browser Search and Hyperlinking in Broadcast Media
Hyper Video Browser Search and Hyperlinking in Broadcast Media
Benoit HUET
 
Multimedia Content Understanding: Bringing Context to Content
Multimedia Content Understanding: Bringing Context to ContentMultimedia Content Understanding: Bringing Context to Content
Multimedia Content Understanding: Bringing Context to Content
Benoit HUET
 
Mining the Web for Multimedia-based Enriching - Multimedia Hyperlinking and ...
Mining the Web for Multimedia-based Enriching - Multimedia Hyperlinking and ...Mining the Web for Multimedia-based Enriching - Multimedia Hyperlinking and ...
Mining the Web for Multimedia-based Enriching - Multimedia Hyperlinking and ...
Benoit HUET
 
LinkedTV @ MediaEval 2013 Search and Hyperlinking Task
LinkedTV @ MediaEval 2013 Search and Hyperlinking TaskLinkedTV @ MediaEval 2013 Search and Hyperlinking Task
LinkedTV @ MediaEval 2013 Search and Hyperlinking Task
Benoit HUET
 
Multimedia Data Collection using Social Media Analysis
Multimedia Data Collection using Social Media Analysis Multimedia Data Collection using Social Media Analysis
Multimedia Data Collection using Social Media Analysis
Benoit HUET
 
Wsm2011
Wsm2011Wsm2011
Wsm2011
Benoit HUET
 

More from Benoit HUET (9)

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...
 
Event-based MultiMedia Search and Retrieval for Question Answering
Event-based MultiMedia Search and Retrieval for Question AnsweringEvent-based MultiMedia Search and Retrieval for Question Answering
Event-based MultiMedia Search and Retrieval for Question Answering
 
Convenient Discovery of Archived Video Using Audiovisual Hyperlinking
Convenient Discovery of Archived Video Using Audiovisual HyperlinkingConvenient Discovery of Archived Video Using Audiovisual Hyperlinking
Convenient Discovery of Archived Video Using Audiovisual Hyperlinking
 
Hyper Video Browser Search and Hyperlinking in Broadcast Media
Hyper Video Browser Search and Hyperlinking in Broadcast MediaHyper Video Browser Search and Hyperlinking in Broadcast Media
Hyper Video Browser Search and Hyperlinking in Broadcast Media
 
Multimedia Content Understanding: Bringing Context to Content
Multimedia Content Understanding: Bringing Context to ContentMultimedia Content Understanding: Bringing Context to Content
Multimedia Content Understanding: Bringing Context to Content
 
Mining the Web for Multimedia-based Enriching - Multimedia Hyperlinking and ...
Mining the Web for Multimedia-based Enriching - Multimedia Hyperlinking and ...Mining the Web for Multimedia-based Enriching - Multimedia Hyperlinking and ...
Mining the Web for Multimedia-based Enriching - Multimedia Hyperlinking and ...
 
LinkedTV @ MediaEval 2013 Search and Hyperlinking Task
LinkedTV @ MediaEval 2013 Search and Hyperlinking TaskLinkedTV @ MediaEval 2013 Search and Hyperlinking Task
LinkedTV @ MediaEval 2013 Search and Hyperlinking Task
 
Multimedia Data Collection using Social Media Analysis
Multimedia Data Collection using Social Media Analysis Multimedia Data Collection using Social Media Analysis
Multimedia Data Collection using Social Media Analysis
 
Wsm2011
Wsm2011Wsm2011
Wsm2011
 

Recently uploaded

3D Hybrid PIC simulation of the plasma expansion (ISSS-14)
3D Hybrid PIC simulation of the plasma expansion (ISSS-14)3D Hybrid PIC simulation of the plasma expansion (ISSS-14)
3D Hybrid PIC simulation of the plasma expansion (ISSS-14)
David Osipyan
 
Nucleic Acid-its structural and functional complexity.
Nucleic Acid-its structural and functional complexity.Nucleic Acid-its structural and functional complexity.
Nucleic Acid-its structural and functional complexity.
Nistarini College, Purulia (W.B) India
 
Unveiling the Energy Potential of Marshmallow Deposits.pdf
Unveiling the Energy Potential of Marshmallow Deposits.pdfUnveiling the Energy Potential of Marshmallow Deposits.pdf
Unveiling the Energy Potential of Marshmallow Deposits.pdf
Erdal Coalmaker
 
GBSN- Microbiology (Lab 3) Gram Staining
GBSN- Microbiology (Lab 3) Gram StainingGBSN- Microbiology (Lab 3) Gram Staining
GBSN- Microbiology (Lab 3) Gram Staining
Areesha Ahmad
 
role of pramana in research.pptx in science
role of pramana in research.pptx in sciencerole of pramana in research.pptx in science
role of pramana in research.pptx in science
sonaliswain16
 
BLOOD AND BLOOD COMPONENT- introduction to blood physiology
BLOOD AND BLOOD COMPONENT- introduction to blood physiologyBLOOD AND BLOOD COMPONENT- introduction to blood physiology
BLOOD AND BLOOD COMPONENT- introduction to blood physiology
NoelManyise1
 
Deep Behavioral Phenotyping in Systems Neuroscience for Functional Atlasing a...
Deep Behavioral Phenotyping in Systems Neuroscience for Functional Atlasing a...Deep Behavioral Phenotyping in Systems Neuroscience for Functional Atlasing a...
Deep Behavioral Phenotyping in Systems Neuroscience for Functional Atlasing a...
Ana Luísa Pinho
 
Comparing Evolved Extractive Text Summary Scores of Bidirectional Encoder Rep...
Comparing Evolved Extractive Text Summary Scores of Bidirectional Encoder Rep...Comparing Evolved Extractive Text Summary Scores of Bidirectional Encoder Rep...
Comparing Evolved Extractive Text Summary Scores of Bidirectional Encoder Rep...
University of Maribor
 
S.1 chemistry scheme term 2 for ordinary level
S.1 chemistry scheme term 2 for ordinary levelS.1 chemistry scheme term 2 for ordinary level
S.1 chemistry scheme term 2 for ordinary level
ronaldlakony0
 
Richard's aventures in two entangled wonderlands
Richard's aventures in two entangled wonderlandsRichard's aventures in two entangled wonderlands
Richard's aventures in two entangled wonderlands
Richard Gill
 
如何办理(uvic毕业证书)维多利亚大学毕业证本科学位证书原版一模一样
如何办理(uvic毕业证书)维多利亚大学毕业证本科学位证书原版一模一样如何办理(uvic毕业证书)维多利亚大学毕业证本科学位证书原版一模一样
如何办理(uvic毕业证书)维多利亚大学毕业证本科学位证书原版一模一样
yqqaatn0
 
Orion Air Quality Monitoring Systems - CWS
Orion Air Quality Monitoring Systems - CWSOrion Air Quality Monitoring Systems - CWS
Orion Air Quality Monitoring Systems - CWS
Columbia Weather Systems
 
Introduction to Mean Field Theory(MFT).pptx
Introduction to Mean Field Theory(MFT).pptxIntroduction to Mean Field Theory(MFT).pptx
Introduction to Mean Field Theory(MFT).pptx
zeex60
 
Seminar of U.V. Spectroscopy by SAMIR PANDA
 Seminar of U.V. Spectroscopy by SAMIR PANDA Seminar of U.V. Spectroscopy by SAMIR PANDA
Seminar of U.V. Spectroscopy by SAMIR PANDA
SAMIR PANDA
 
Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...
Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...
Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...
Sérgio Sacani
 
What is greenhouse gasses and how many gasses are there to affect the Earth.
What is greenhouse gasses and how many gasses are there to affect the Earth.What is greenhouse gasses and how many gasses are there to affect the Earth.
What is greenhouse gasses and how many gasses are there to affect the Earth.
moosaasad1975
 
DERIVATION OF MODIFIED BERNOULLI EQUATION WITH VISCOUS EFFECTS AND TERMINAL V...
DERIVATION OF MODIFIED BERNOULLI EQUATION WITH VISCOUS EFFECTS AND TERMINAL V...DERIVATION OF MODIFIED BERNOULLI EQUATION WITH VISCOUS EFFECTS AND TERMINAL V...
DERIVATION OF MODIFIED BERNOULLI EQUATION WITH VISCOUS EFFECTS AND TERMINAL V...
Wasswaderrick3
 
platelets_clotting_biogenesis.clot retractionpptx
platelets_clotting_biogenesis.clot retractionpptxplatelets_clotting_biogenesis.clot retractionpptx
platelets_clotting_biogenesis.clot retractionpptx
muralinath2
 
GBSN - Microbiology (Lab 4) Culture Media
GBSN - Microbiology (Lab 4) Culture MediaGBSN - Microbiology (Lab 4) Culture Media
GBSN - Microbiology (Lab 4) Culture Media
Areesha Ahmad
 
原版制作(carleton毕业证书)卡尔顿大学毕业证硕士文凭原版一模一样
原版制作(carleton毕业证书)卡尔顿大学毕业证硕士文凭原版一模一样原版制作(carleton毕业证书)卡尔顿大学毕业证硕士文凭原版一模一样
原版制作(carleton毕业证书)卡尔顿大学毕业证硕士文凭原版一模一样
yqqaatn0
 

Recently uploaded (20)

3D Hybrid PIC simulation of the plasma expansion (ISSS-14)
3D Hybrid PIC simulation of the plasma expansion (ISSS-14)3D Hybrid PIC simulation of the plasma expansion (ISSS-14)
3D Hybrid PIC simulation of the plasma expansion (ISSS-14)
 
Nucleic Acid-its structural and functional complexity.
Nucleic Acid-its structural and functional complexity.Nucleic Acid-its structural and functional complexity.
Nucleic Acid-its structural and functional complexity.
 
Unveiling the Energy Potential of Marshmallow Deposits.pdf
Unveiling the Energy Potential of Marshmallow Deposits.pdfUnveiling the Energy Potential of Marshmallow Deposits.pdf
Unveiling the Energy Potential of Marshmallow Deposits.pdf
 
GBSN- Microbiology (Lab 3) Gram Staining
GBSN- Microbiology (Lab 3) Gram StainingGBSN- Microbiology (Lab 3) Gram Staining
GBSN- Microbiology (Lab 3) Gram Staining
 
role of pramana in research.pptx in science
role of pramana in research.pptx in sciencerole of pramana in research.pptx in science
role of pramana in research.pptx in science
 
BLOOD AND BLOOD COMPONENT- introduction to blood physiology
BLOOD AND BLOOD COMPONENT- introduction to blood physiologyBLOOD AND BLOOD COMPONENT- introduction to blood physiology
BLOOD AND BLOOD COMPONENT- introduction to blood physiology
 
Deep Behavioral Phenotyping in Systems Neuroscience for Functional Atlasing a...
Deep Behavioral Phenotyping in Systems Neuroscience for Functional Atlasing a...Deep Behavioral Phenotyping in Systems Neuroscience for Functional Atlasing a...
Deep Behavioral Phenotyping in Systems Neuroscience for Functional Atlasing a...
 
Comparing Evolved Extractive Text Summary Scores of Bidirectional Encoder Rep...
Comparing Evolved Extractive Text Summary Scores of Bidirectional Encoder Rep...Comparing Evolved Extractive Text Summary Scores of Bidirectional Encoder Rep...
Comparing Evolved Extractive Text Summary Scores of Bidirectional Encoder Rep...
 
S.1 chemistry scheme term 2 for ordinary level
S.1 chemistry scheme term 2 for ordinary levelS.1 chemistry scheme term 2 for ordinary level
S.1 chemistry scheme term 2 for ordinary level
 
Richard's aventures in two entangled wonderlands
Richard's aventures in two entangled wonderlandsRichard's aventures in two entangled wonderlands
Richard's aventures in two entangled wonderlands
 
如何办理(uvic毕业证书)维多利亚大学毕业证本科学位证书原版一模一样
如何办理(uvic毕业证书)维多利亚大学毕业证本科学位证书原版一模一样如何办理(uvic毕业证书)维多利亚大学毕业证本科学位证书原版一模一样
如何办理(uvic毕业证书)维多利亚大学毕业证本科学位证书原版一模一样
 
Orion Air Quality Monitoring Systems - CWS
Orion Air Quality Monitoring Systems - CWSOrion Air Quality Monitoring Systems - CWS
Orion Air Quality Monitoring Systems - CWS
 
Introduction to Mean Field Theory(MFT).pptx
Introduction to Mean Field Theory(MFT).pptxIntroduction to Mean Field Theory(MFT).pptx
Introduction to Mean Field Theory(MFT).pptx
 
Seminar of U.V. Spectroscopy by SAMIR PANDA
 Seminar of U.V. Spectroscopy by SAMIR PANDA Seminar of U.V. Spectroscopy by SAMIR PANDA
Seminar of U.V. Spectroscopy by SAMIR PANDA
 
Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...
Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...
Earliest Galaxies in the JADES Origins Field: Luminosity Function and Cosmic ...
 
What is greenhouse gasses and how many gasses are there to affect the Earth.
What is greenhouse gasses and how many gasses are there to affect the Earth.What is greenhouse gasses and how many gasses are there to affect the Earth.
What is greenhouse gasses and how many gasses are there to affect the Earth.
 
DERIVATION OF MODIFIED BERNOULLI EQUATION WITH VISCOUS EFFECTS AND TERMINAL V...
DERIVATION OF MODIFIED BERNOULLI EQUATION WITH VISCOUS EFFECTS AND TERMINAL V...DERIVATION OF MODIFIED BERNOULLI EQUATION WITH VISCOUS EFFECTS AND TERMINAL V...
DERIVATION OF MODIFIED BERNOULLI EQUATION WITH VISCOUS EFFECTS AND TERMINAL V...
 
platelets_clotting_biogenesis.clot retractionpptx
platelets_clotting_biogenesis.clot retractionpptxplatelets_clotting_biogenesis.clot retractionpptx
platelets_clotting_biogenesis.clot retractionpptx
 
GBSN - Microbiology (Lab 4) Culture Media
GBSN - Microbiology (Lab 4) Culture MediaGBSN - Microbiology (Lab 4) Culture Media
GBSN - Microbiology (Lab 4) Culture Media
 
原版制作(carleton毕业证书)卡尔顿大学毕业证硕士文凭原版一模一样
原版制作(carleton毕业证书)卡尔顿大学毕业证硕士文凭原版一模一样原版制作(carleton毕业证书)卡尔顿大学毕业证硕士文凭原版一模一样
原版制作(carleton毕业证书)卡尔顿大学毕业证硕士文凭原版一模一样
 

Media Genre Inference for Predicting Media Interestingness

  • 1. EURECOM @MediaEval 2017: Media Genre Inference for Predicting Media Interestingness O. Ben-Ahmed, J. Wacker, A. Gaballo, B. Huet EURECOM Sophia Antipolis, France
  • 2. Introduction  Predicting Media Interestingness (PMI)  automatically analyze media data  identify the most attractive content  Content based approaches  gap between low-level features and high-level human perception  Our proposal  Address PMI in association with Media Genre 13/09/2017 MediaEval2017 Dublin - B. HUET, EURECOM - p 2 http://www.dailyherald.com/article/20110627/entlife/706279989/
  • 3. Why Genre Inference for PMI  Motivation  Interestingness is highly correlated with data emotional content  Affective representation of data content  Hypothesis  Emotional impact of movie genre can be a factor for interestingness of a video fragment  Method  Mid-level representation based on media genre prediction for PMI – Represent each video fragment/image as a distribution of genres 13/09/2017 MediaEval2017 Dublin - B. HUET, EURECOM - p 3
  • 4. Our Framework 13/09/2017 MediaEval2017 Dublin - B. HUET, EURECOM - p 4
  • 5. Media Genre Prediction  Visual Branch  Middle frame selection  Deep CNN for features extraction  DNN classifier  Audio Branch  Audio extraction : OpenSmile  Deep features extraction : Soundnet  SVM classifier VGG Architecture 13/09/2017 MediaEval2017 Dublin - B. HUET, EURECOM - p 5 | X | X
  • 6. Media Genre Prediction Example Visual Audio Audio-Visual Action Drama Horror Romance Sci-fi 13/09/2017 MediaEval2017 Dublin - B. HUET, EURECOM - p 6
  • 7. Media Genre Prediction Example Visual Audio Audio-Visual Action Drama Horror Romance Sci-fi 2.5% 33,34% 17.92% 0% 17,78% 8.89% 0.37% 2.61% 1.49% 0% 3.87% 1.93% 97.12% 42,40% 69,76% 13/09/2017 MediaEval2017 Dublin - B. HUET, EURECOM - p 7
  • 8. Media Genre Prediction Example Visual Audio Audio-Visual Action Drama Horror Romance Sci-fi Interestingness : 1 Rank : 1 2.5% 33,34% 17.92% 0% 17,78% 8.89% 0.37% 2.61% 1.49% 0% 3.87% 1.93% 97.12% 42,40% 69,76% 13/09/2017 MediaEval2017 Dublin - B. HUET, EURECOM - p 8
  • 9. Interestingness Classification  Features vectors  probability vector for the genre distribution for the video/image  Classifier  Binary SVM,  Taking into account the confidence score in training  Image subtask  Visual genre vector  Video subtask  Visual genre vector  Audio-Visual genre vector – Mean of visual- and audio-based genre vectors probabilities 13/09/2017 MediaEval2017 Dublin - B. HUET, EURECOM - p 9
  • 10. Experiments and Results TASK RUN SVM CLASSIFIER MAP MAP@10 IMAGE 1 Sigmoid kernel 0.2029 0.0587 2 Linear kernel 0.2016 0.0579 VIDEO 1 Sigmoid kernel gamma=0.5, C=100 0.2034 0.0717 2 Polynomial kernel degree=3 0.1960 0.0732 3 Polynomial kernel degree=2 0.1964 0.0640 4 Sigmoid kernel gamma=0.2, C=100 0.2094 0.0827 5 Sigmoid kernel gamma=0.3 , C=100 0.2002 0.0774 13/09/2017 MediaEval2017 Dublin - B. HUET, EURECOM - p 10
  • 11. Experiments and Results TASK RUN SVM CLASSIFIER MAP MAP@10 IMAGE 1 Sigmoid kernel 0.2029 0.0587 2 Linear kernel 0.2016 0.0579 VIDEO 1 Sigmoid kernel gamma=0.5, C=100 0.2034 0.0717 2 Polynomial kernel degree=3 0.1960 0.0732 3 Polynomial kernel degree=2 0.1964 0.0640 4 Sigmoid kernel gamma=0.2, C=100 0.2094 0.0827 5 Sigmoid kernel gamma=0.3 , C=100 0.2002 0.0774 13/09/2017 MediaEval2017 Dublin - B. HUET, EURECOM - p 11
  • 12. Conclusions and Future Work  We proposed a Genre Recognition System as a mid- level representation for Predicting Media Interestingness  Deep Audio and Visual Features for Genre Recognition  SVM Classifier for Predicting Media Interestingness  Best Results:  20,29 MAP for Image and 20,94 MAP for Video (on test set).  Audio brings limited additional information for PMI 13/09/2017 MediaEval2017 Dublin - B. HUET, EURECOM - p 12
  • 13. Conclusions and Future Work  We proposed a Genre Recognition System as a mid- level representation for Predicting Media Interestingness  Deep Audio and Visual Features for Genre Recognition  SVM Classifier for Predicting Media Interestingness  Best Results:  20,29 MAP for Image and 20,94 MAP for Video (on test set).  Audio brings limited additional information for PMI  Joint learning of audio-visual features  Integration of temporal information 13/09/2017 MediaEval2017 Dublin - B. HUET, EURECOM - p 13
  • 14. Questions? Benoit Huet. MediaEval2017 Dublin - B. HUET, EURECOM - p 1413/09/2017 Media Genre Inference for Predicting Media Interestingness @ 2017 Thank you,