The opening keynote of VIGTA 2012 – First International Workshop on Visual Interfaces for Ground Truth Collection in Computer Vision Applications
In conjunction with the Advanced Visual Interfaces International Working Conference in Capri Italy, May 21-25, 2012
A Different Perspective on Business with Social DataTzar Umang
Do business the intelligent way with Social Data and Analytics, harness the power Social Media and Sentiments and use it to improve your brand and or your current campaign,
Recent years have seen an increased use of social media data as a cheaper alternative to more traditional methods of market research. Social media services generate a large quantity of data every day and some of the data is available through their Application Programming Interfaces (APIs). This presentation outlines some of the research work carried out as part of the Uncertainty of Identity (http://www.uncertaintyofidentity.com) project. In particular, the use of social media data for activity pattern analysis and demographic profiling is explored.
Social Media in Australia: The Case of TwitterAxel Bruns
Professor Axel Bruns at Queensland University of Technology leads research tracking social media use in Australia, particularly Twitter. His team has identified over 2.8 million active Australian Twitter accounts through 2013. They map these accounts' follower/followee networks and track hashtags, links shared, and other activities to understand how public discourse and information spread occurs online. Their goal is developing a comprehensive model of Australia's online public sphere through large-scale, data-driven analysis of social media over time.
Telecom Data Analysis Using Social Media FeedsJuhi Srivastava
This document discusses using social media data and text analysis techniques to gain business insights. It covers extracting data from social media, preprocessing the text, performing sentiment analysis and classification using Naive Bayes and other algorithms, analyzing word frequencies and associations through word clouds and clustering, and segmenting customers for cross-sell/upsell opportunities based on spending and sentiment. Potential applications discussed include customer churn prediction, sarcasm detection, and building unique models of customer behavior over time.
www.its.leeds.ac.uk/people/c.calastri
Social networks, i.e. the circles of people we are socially connected to, have been recognised to play a role in shaping our travel and activity behaviour. This not only has to do with socialisation being the purpose of travel, but also with enabling mobility and other activities through the so-called social capital. Another theme in the literature connecting social environment and travel behaviour is social influence, i.e. the investigation of how travel behaviour can be affected by observation or comparison with other people. Research about the impact of social influence on travel choices is still at its infancy. In this talk, I will give an overview of how choice modelling can be used to investigate the relationships between social networks, travel and activities. I will touch upon work that I have done so far, in particular I will describe my applications of the Multiple Discrete-Continuous Extreme Value (MDCEV) model to frequency of social interactions as well as to allocation of time to different activities, taking the social dimension into account. In these studies, I make use of social network and travel data collected in places as diverse as Switzerland and Chile. I will also discuss ongoing work making use of longitudinal life-course data to model the impact of family of origin and the “mobility environment” people grew up in on travel decision of adults. Finally, I will outline future plans about modelling behavioural changes due to social influence using the smartphone app travel data that are being collected in Leeds within the “Choices and consumption: modelling long and short term decisions in a changing world” (“DECISIONS”) project.
The document analyzes social media activity for BJP, Congress, and AAP from August 1, 2014 to December 9, 2014. It finds that BJP has the highest share of voice (SOV) at 51%. BJP receives the most positive commentary while Congress receives the most negative commentary. Videos generate the most mentions, with Congress enjoying the maximum share for videos.
Friendship and mobility user movement in location based social networksFread Mzee
This document summarizes a study on how friendship and social networks influence human mobility patterns based on location-based social network and mobile phone data. The study found that short-range daily travel exhibits strong periodic patterns and is not influenced by social ties, while long-distance travel is more influenced by social networks. It also found that social relationships can explain 10-30% of human movement, with periodic behavior explaining 50-70%. Based on these findings, the study developed a human mobility model combining periodic short-range movements with social network-influenced travel, which better predicted future location dynamics.
Spatio-temporal demographic classification of the Twitter usersDr Muhammad Adnan
Use of social media continues to increase day by day, with implications for the creation of ‘big’ data – Twitter alone was forecast to have created 1.8 zettabytes of data in 2011. This talk presents an initial work towards the creation of geo-temporal geodemgoraphic classifications by using the Twitter social media data. London was chosen as the study area because of its high incidence of users and the consequent expectation that higher penetration might be associated with lower demographic bias.
A Different Perspective on Business with Social DataTzar Umang
Do business the intelligent way with Social Data and Analytics, harness the power Social Media and Sentiments and use it to improve your brand and or your current campaign,
Recent years have seen an increased use of social media data as a cheaper alternative to more traditional methods of market research. Social media services generate a large quantity of data every day and some of the data is available through their Application Programming Interfaces (APIs). This presentation outlines some of the research work carried out as part of the Uncertainty of Identity (http://www.uncertaintyofidentity.com) project. In particular, the use of social media data for activity pattern analysis and demographic profiling is explored.
Social Media in Australia: The Case of TwitterAxel Bruns
Professor Axel Bruns at Queensland University of Technology leads research tracking social media use in Australia, particularly Twitter. His team has identified over 2.8 million active Australian Twitter accounts through 2013. They map these accounts' follower/followee networks and track hashtags, links shared, and other activities to understand how public discourse and information spread occurs online. Their goal is developing a comprehensive model of Australia's online public sphere through large-scale, data-driven analysis of social media over time.
Telecom Data Analysis Using Social Media FeedsJuhi Srivastava
This document discusses using social media data and text analysis techniques to gain business insights. It covers extracting data from social media, preprocessing the text, performing sentiment analysis and classification using Naive Bayes and other algorithms, analyzing word frequencies and associations through word clouds and clustering, and segmenting customers for cross-sell/upsell opportunities based on spending and sentiment. Potential applications discussed include customer churn prediction, sarcasm detection, and building unique models of customer behavior over time.
www.its.leeds.ac.uk/people/c.calastri
Social networks, i.e. the circles of people we are socially connected to, have been recognised to play a role in shaping our travel and activity behaviour. This not only has to do with socialisation being the purpose of travel, but also with enabling mobility and other activities through the so-called social capital. Another theme in the literature connecting social environment and travel behaviour is social influence, i.e. the investigation of how travel behaviour can be affected by observation or comparison with other people. Research about the impact of social influence on travel choices is still at its infancy. In this talk, I will give an overview of how choice modelling can be used to investigate the relationships between social networks, travel and activities. I will touch upon work that I have done so far, in particular I will describe my applications of the Multiple Discrete-Continuous Extreme Value (MDCEV) model to frequency of social interactions as well as to allocation of time to different activities, taking the social dimension into account. In these studies, I make use of social network and travel data collected in places as diverse as Switzerland and Chile. I will also discuss ongoing work making use of longitudinal life-course data to model the impact of family of origin and the “mobility environment” people grew up in on travel decision of adults. Finally, I will outline future plans about modelling behavioural changes due to social influence using the smartphone app travel data that are being collected in Leeds within the “Choices and consumption: modelling long and short term decisions in a changing world” (“DECISIONS”) project.
The document analyzes social media activity for BJP, Congress, and AAP from August 1, 2014 to December 9, 2014. It finds that BJP has the highest share of voice (SOV) at 51%. BJP receives the most positive commentary while Congress receives the most negative commentary. Videos generate the most mentions, with Congress enjoying the maximum share for videos.
Friendship and mobility user movement in location based social networksFread Mzee
This document summarizes a study on how friendship and social networks influence human mobility patterns based on location-based social network and mobile phone data. The study found that short-range daily travel exhibits strong periodic patterns and is not influenced by social ties, while long-distance travel is more influenced by social networks. It also found that social relationships can explain 10-30% of human movement, with periodic behavior explaining 50-70%. Based on these findings, the study developed a human mobility model combining periodic short-range movements with social network-influenced travel, which better predicted future location dynamics.
Spatio-temporal demographic classification of the Twitter usersDr Muhammad Adnan
Use of social media continues to increase day by day, with implications for the creation of ‘big’ data – Twitter alone was forecast to have created 1.8 zettabytes of data in 2011. This talk presents an initial work towards the creation of geo-temporal geodemgoraphic classifications by using the Twitter social media data. London was chosen as the study area because of its high incidence of users and the consequent expectation that higher penetration might be associated with lower demographic bias.
Statistical analytical programming for social media analysis .Felicita Florence
This document discusses using SAS programming to analyze social media recruitment data. It includes importing data files, merging files, conducting frequency analysis, means analysis, ANOVA, correlation, regression, and creating graphs and charts like bar charts, pie charts, and scatterplots. SAS code is provided for merging data, conducting statistical tests, and creating various graphs and visualizations to analyze the social media recruitment data.
A guide to realistic social media and measurementAdam Vincenzini
Social media measurement and performance analysis is one of the most debated topics in the current marketing environment.
Recently I hosted a workshop for the PRIA which attempted to put social media measurement in perspective, especially when linking it to tangible business objectives.
This is not an exhaustive presentation, nor will it answer every question linked to social media measurement, but it will hopefully give you a useful resource to refer to.
Usage and consumption pattern of Social Media- Girish.HavaleGirish Havale
"Social Media becoming New trend for the marketers, marketing in such case will increase marketers strength and easier to track customers. Here the research focus on usage and consumption pattern of elements on Facebook, which helps for building strategies and calculation models of ROI of SMM."
RSC: Mining and Modeling Temporal Activity in Social MediaAlceu Ferraz Costa
Presentation of the KDD 2015 paper describing the RSC model:
RSC: Mining and Modeling Temporal Activity in Social Media
Alceu Ferraz Costa, Yuto Yamaguchi, Agma Juci Machado Traina, Caetano Traina Jr., and Christos Faloutsos
The 21st SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2015
The document discusses various tools and methods for collecting data, including keyboards, mice, graphics tablets, biometric devices, barcode readers, smart cards, phones, optical mark sensing, magnetic ink character recognition, and radio frequency identification. It covers the technologies, advantages, and disadvantages of each method. Key details like data format, encoding, and transmission are explained for different input and collection mechanisms.
Picturing the Social: Talk for Transforming Digital Methods Winter SchoolFarida Vis
This talk highlights the work of the Visual Social Media Lab and the Picturing the Social project. It summarises the key research questions and aims of the project. It highlights the value of interdisciplinarity and working closely with industry in this area. It also focuses on the way in which me might study different types of structures involved in the circulation and the scopic regimes that make social media images more or less visible. It also tries to unpack how we can start to think about APIs as 'method' and looks at the different ways in which we can get access to different kinds of social media image data. Both through public ('free') APIs and ('pay for') firehose data.
Researching Social Media – Big Data and Social Media AnalysisFarida Vis
Researching Social Media – Big Data and Social Media Analysis, presentation for the Social Media for Researchers: A Sheffield Universities Social Media Symposium, 23 September 2014
7 Hot Location-Based Apps You Should Know AboutShauna Causey
1) The document reviews 7 top location-based apps: Foursquare, Gowalla, Yelp, Starbucks, CauseWorld, Whrrl.
2) It highlights key features of each app such as checking in locations, collecting points/badges, finding nearby places/friends, and special features like cause marketing or custom drink orders.
3) The review finds that Foursquare and Yelp have the most comprehensive information on locations while Gowalla and Starbucks focus more on gaming and loyalty features respectively.
Human mobility,urban structure analysis,and spatial community detection from ...Song Gao
1) The document summarizes Song Gao's research interests in human mobility patterns, urban structure analysis, and spatial community detection using mobile phone data.
2) Key research questions include how human mobility and physical movements are impacted by distance and information communication technologies.
3) The document outlines methods for analyzing individual and aggregate mobility patterns, dynamic urban landscapes, and detecting spatial communities in interaction networks.
4) Preliminary results suggest distance still constrains human interactions and mobility, and that a relationship exists between communication technologies and physical movements.
This document provides an overview of social media and big data analytics. It discusses key concepts like Web 2.0, social media platforms, big data characteristics involving volume, velocity, variety, veracity and value. The document also discusses how social media data can be extracted and analyzed using big data tools like Hadoop and techniques like social network analysis and sentiment analysis. It provides examples of analyzing social media data at scale to gain insights and make informed decisions.
Jump start into 2013 by exploring how Big Data can transform your business. Listen to Infochimps Director of Product, Tim Gasper, cover the leading use cases for 2013, sharing where the data comes from, how the systems are architected and most importantly, how they drive business insights for data-driven decisions.
Social network analysis & Big Data - Telecommunications and moreWael Elrifai
Social Network Analysis: Practical Uses and Implementation is a presentation that discusses social network analysis and its uses. It covers key topics such as defining social networks and social network analysis, why social network analysis is important, identifying influencers in social networks, roles in social networks, graph theory concepts used in social network analysis, calculating metrics from social networks, and recommended approaches to social network analysis. The presentation provides an overview of social network analysis concepts and their practical applications.
This document discusses location-based services (LBS) and evaluates different positioning techniques used in LBS. It begins by introducing common LBS applications and services. It then examines the components and architecture of LBS systems, including LBS middleware and location tracking. Privacy concerns with LBS are also addressed. The document evaluates and compares several positioning systems used in LBS, including satellite-based GPS, network-based methods like GSM, and indoor positioning techniques. It concludes by discussing limitations and opportunities for future work improving LBS positioning accuracy and privacy.
Continuing our series of studies into Digital, Social and Mobile use around the world, this report explores the connected landscape in China in August 2015. It shares the latest active user figures for fixed and mobile internet; shares details of the most active social media platforms, and outlines user behaviour across mobile devices and e-commerce. For more info, please visit http://bit.ly/DSMCN15
Big Data Analytics : A Social Network ApproachAndry Alamsyah
This document discusses using social network analysis approaches for big data analytics. It begins by introducing social network metrics like centrality and modularity that can be applied to large social network datasets. It then provides examples of how social network analysis has been used to detect terrorist cells and identify research communities. Finally, it outlines the author's research interests and publications in areas like sentiment analysis on social media and using social networks to analyze industries.
Affective Multimodal Analysis for the Media IndustryBenoit HUET
The media industry is constantly making use of affective signals whether in text, sound, image or moving images with the aim of attracting our attention and conveying a message or a story. In this presentation we will look at the analysis of audio-visual content for understanding its affective properties. We will start with proposing a semi supervised approach for identifying the genre of a media (action, drama, horror, etc..). We will then show how the genre of video segments can be used to determine its interestingness. There are many usage scenarios where such information about the content has value for the media editors and archivists. Beyond genre and interestingness, emotion recognition in videos in another important cue when understanding the content of audio-visual documents. For this a deep model combining three key component for recognizing human expression of emotions has been devised. It includes static as well as dynamic facial features and audio information. The approach was shown to perform well on the Emotion Recognition in the Wild 2017 challenge. Applications to past and ongoing research and industry projects will be used throughout to illustrate the presentation.
NexGenTV: Providing Real-Time Insight during Political Debates in a Second Sc...Benoit HUET
Second screen applications are becoming key for broadcasters exploiting the convergence of TV and Internet. Authoring such applications however remains costly. In this paper, we present a second screen authoring application that leverages multimedia content analytics and social media monitoring. A back-office is dedicated to easy and fast content ingestion, segmentation, description and enrichment with links to entities and related content. From the back-end, broadcasters can push enriched content to front-end applications providing customers with highlights, entity and content links, overviews of social network, etc. The demonstration operates on political debates ingested during the 2017 French presidential election, enabling insights on the debates.
Media Genre Inference for Predicting Media InterestingnessBenoit HUET
In this presentation, we present EURECOM's approach to address the MediaEval 2017 Predicting Media Interestingness Task.
We developed models for both the image and video subtasks. In particular, we investigate the usage of media genre information (i.e., drama, horror, etc.) to predict interestingness. Our approach is related to the affective impact of media content and is shown to be effective in predicting interestingness for both video shots and key-frames.
This approach obtained the best performance on the video task (in terms of MAP and MAP@10).
Event-based MultiMedia Search and Retrieval for Question AnsweringBenoit HUET
The document describes a framework for event-based multimedia search and retrieval for question answering. It discusses parsing user queries to extract semantic entities like location and time. Events are collected from news sources and clustered. Textual and visual media are gathered from social media to summarize events. Visual concepts are mapped to queries to enrich text-based search. Experimental results show combining textual and visual scores using concept mapping improves search performance. The optimal approach weights textual scores higher than visual scores.
Convenient Discovery of Archived Video Using Audiovisual HyperlinkingBenoit HUET
This paper overviews ongoing work that aims to support
end-users in conveniently exploring and exploiting large audiovisual archives by deploying multiple multimodal linking
approaches. We present ongoing work on multimodal video
hyperlinking, from a perspective of unconstrained link anchor identification and based on the identification of named
entities, and recent attempts to implement and validate the
concept of outside-in linking that relates current events to
archive content. Although these concepts are not new, current work is revealing novel insights, more mature technology, development of benchmark evaluations and emergence
of dedicated workshops which are opening many interesting research questions on various levels that require closer
collaboration between research communities.
Statistical analytical programming for social media analysis .Felicita Florence
This document discusses using SAS programming to analyze social media recruitment data. It includes importing data files, merging files, conducting frequency analysis, means analysis, ANOVA, correlation, regression, and creating graphs and charts like bar charts, pie charts, and scatterplots. SAS code is provided for merging data, conducting statistical tests, and creating various graphs and visualizations to analyze the social media recruitment data.
A guide to realistic social media and measurementAdam Vincenzini
Social media measurement and performance analysis is one of the most debated topics in the current marketing environment.
Recently I hosted a workshop for the PRIA which attempted to put social media measurement in perspective, especially when linking it to tangible business objectives.
This is not an exhaustive presentation, nor will it answer every question linked to social media measurement, but it will hopefully give you a useful resource to refer to.
Usage and consumption pattern of Social Media- Girish.HavaleGirish Havale
"Social Media becoming New trend for the marketers, marketing in such case will increase marketers strength and easier to track customers. Here the research focus on usage and consumption pattern of elements on Facebook, which helps for building strategies and calculation models of ROI of SMM."
RSC: Mining and Modeling Temporal Activity in Social MediaAlceu Ferraz Costa
Presentation of the KDD 2015 paper describing the RSC model:
RSC: Mining and Modeling Temporal Activity in Social Media
Alceu Ferraz Costa, Yuto Yamaguchi, Agma Juci Machado Traina, Caetano Traina Jr., and Christos Faloutsos
The 21st SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2015
The document discusses various tools and methods for collecting data, including keyboards, mice, graphics tablets, biometric devices, barcode readers, smart cards, phones, optical mark sensing, magnetic ink character recognition, and radio frequency identification. It covers the technologies, advantages, and disadvantages of each method. Key details like data format, encoding, and transmission are explained for different input and collection mechanisms.
Picturing the Social: Talk for Transforming Digital Methods Winter SchoolFarida Vis
This talk highlights the work of the Visual Social Media Lab and the Picturing the Social project. It summarises the key research questions and aims of the project. It highlights the value of interdisciplinarity and working closely with industry in this area. It also focuses on the way in which me might study different types of structures involved in the circulation and the scopic regimes that make social media images more or less visible. It also tries to unpack how we can start to think about APIs as 'method' and looks at the different ways in which we can get access to different kinds of social media image data. Both through public ('free') APIs and ('pay for') firehose data.
Researching Social Media – Big Data and Social Media AnalysisFarida Vis
Researching Social Media – Big Data and Social Media Analysis, presentation for the Social Media for Researchers: A Sheffield Universities Social Media Symposium, 23 September 2014
7 Hot Location-Based Apps You Should Know AboutShauna Causey
1) The document reviews 7 top location-based apps: Foursquare, Gowalla, Yelp, Starbucks, CauseWorld, Whrrl.
2) It highlights key features of each app such as checking in locations, collecting points/badges, finding nearby places/friends, and special features like cause marketing or custom drink orders.
3) The review finds that Foursquare and Yelp have the most comprehensive information on locations while Gowalla and Starbucks focus more on gaming and loyalty features respectively.
Human mobility,urban structure analysis,and spatial community detection from ...Song Gao
1) The document summarizes Song Gao's research interests in human mobility patterns, urban structure analysis, and spatial community detection using mobile phone data.
2) Key research questions include how human mobility and physical movements are impacted by distance and information communication technologies.
3) The document outlines methods for analyzing individual and aggregate mobility patterns, dynamic urban landscapes, and detecting spatial communities in interaction networks.
4) Preliminary results suggest distance still constrains human interactions and mobility, and that a relationship exists between communication technologies and physical movements.
This document provides an overview of social media and big data analytics. It discusses key concepts like Web 2.0, social media platforms, big data characteristics involving volume, velocity, variety, veracity and value. The document also discusses how social media data can be extracted and analyzed using big data tools like Hadoop and techniques like social network analysis and sentiment analysis. It provides examples of analyzing social media data at scale to gain insights and make informed decisions.
Jump start into 2013 by exploring how Big Data can transform your business. Listen to Infochimps Director of Product, Tim Gasper, cover the leading use cases for 2013, sharing where the data comes from, how the systems are architected and most importantly, how they drive business insights for data-driven decisions.
Social network analysis & Big Data - Telecommunications and moreWael Elrifai
Social Network Analysis: Practical Uses and Implementation is a presentation that discusses social network analysis and its uses. It covers key topics such as defining social networks and social network analysis, why social network analysis is important, identifying influencers in social networks, roles in social networks, graph theory concepts used in social network analysis, calculating metrics from social networks, and recommended approaches to social network analysis. The presentation provides an overview of social network analysis concepts and their practical applications.
This document discusses location-based services (LBS) and evaluates different positioning techniques used in LBS. It begins by introducing common LBS applications and services. It then examines the components and architecture of LBS systems, including LBS middleware and location tracking. Privacy concerns with LBS are also addressed. The document evaluates and compares several positioning systems used in LBS, including satellite-based GPS, network-based methods like GSM, and indoor positioning techniques. It concludes by discussing limitations and opportunities for future work improving LBS positioning accuracy and privacy.
Continuing our series of studies into Digital, Social and Mobile use around the world, this report explores the connected landscape in China in August 2015. It shares the latest active user figures for fixed and mobile internet; shares details of the most active social media platforms, and outlines user behaviour across mobile devices and e-commerce. For more info, please visit http://bit.ly/DSMCN15
Big Data Analytics : A Social Network ApproachAndry Alamsyah
This document discusses using social network analysis approaches for big data analytics. It begins by introducing social network metrics like centrality and modularity that can be applied to large social network datasets. It then provides examples of how social network analysis has been used to detect terrorist cells and identify research communities. Finally, it outlines the author's research interests and publications in areas like sentiment analysis on social media and using social networks to analyze industries.
Affective Multimodal Analysis for the Media IndustryBenoit HUET
The media industry is constantly making use of affective signals whether in text, sound, image or moving images with the aim of attracting our attention and conveying a message or a story. In this presentation we will look at the analysis of audio-visual content for understanding its affective properties. We will start with proposing a semi supervised approach for identifying the genre of a media (action, drama, horror, etc..). We will then show how the genre of video segments can be used to determine its interestingness. There are many usage scenarios where such information about the content has value for the media editors and archivists. Beyond genre and interestingness, emotion recognition in videos in another important cue when understanding the content of audio-visual documents. For this a deep model combining three key component for recognizing human expression of emotions has been devised. It includes static as well as dynamic facial features and audio information. The approach was shown to perform well on the Emotion Recognition in the Wild 2017 challenge. Applications to past and ongoing research and industry projects will be used throughout to illustrate the presentation.
NexGenTV: Providing Real-Time Insight during Political Debates in a Second Sc...Benoit HUET
Second screen applications are becoming key for broadcasters exploiting the convergence of TV and Internet. Authoring such applications however remains costly. In this paper, we present a second screen authoring application that leverages multimedia content analytics and social media monitoring. A back-office is dedicated to easy and fast content ingestion, segmentation, description and enrichment with links to entities and related content. From the back-end, broadcasters can push enriched content to front-end applications providing customers with highlights, entity and content links, overviews of social network, etc. The demonstration operates on political debates ingested during the 2017 French presidential election, enabling insights on the debates.
Media Genre Inference for Predicting Media InterestingnessBenoit HUET
In this presentation, we present EURECOM's approach to address the MediaEval 2017 Predicting Media Interestingness Task.
We developed models for both the image and video subtasks. In particular, we investigate the usage of media genre information (i.e., drama, horror, etc.) to predict interestingness. Our approach is related to the affective impact of media content and is shown to be effective in predicting interestingness for both video shots and key-frames.
This approach obtained the best performance on the video task (in terms of MAP and MAP@10).
Event-based MultiMedia Search and Retrieval for Question AnsweringBenoit HUET
The document describes a framework for event-based multimedia search and retrieval for question answering. It discusses parsing user queries to extract semantic entities like location and time. Events are collected from news sources and clustered. Textual and visual media are gathered from social media to summarize events. Visual concepts are mapped to queries to enrich text-based search. Experimental results show combining textual and visual scores using concept mapping improves search performance. The optimal approach weights textual scores higher than visual scores.
Convenient Discovery of Archived Video Using Audiovisual HyperlinkingBenoit HUET
This paper overviews ongoing work that aims to support
end-users in conveniently exploring and exploiting large audiovisual archives by deploying multiple multimodal linking
approaches. We present ongoing work on multimodal video
hyperlinking, from a perspective of unconstrained link anchor identification and based on the identification of named
entities, and recent attempts to implement and validate the
concept of outside-in linking that relates current events to
archive content. Although these concepts are not new, current work is revealing novel insights, more mature technology, development of benchmark evaluations and emergence
of dedicated workshops which are opening many interesting research questions on various levels that require closer
collaboration between research communities.
Hyper Video Browser Search and Hyperlinking in Broadcast MediaBenoit HUET
Massive amounts of digital media is being produced and consumed daily on the Internet. Efficient access to relevant information is of key importance in contemporary society. The Hyper Video Browser provides multiple navigation means within the content of a media repository. Our system utilizes the state of the art multimodal content analysis and indexing techniques, at multiple temporal granularity, in order to satisfy the user need by suggesting relevant material.
We integrate two intuitive interfaces: for search and browsing through the video archive, and for further hyperlinking to the related content while enjoying some video content. The novelty of this work includes a multi-faceted search and browsing interface for navigating in video collections and the dynamic suggestion of hyperlinks related to a media fragment content, rather than the entire video, being viewed.
The approach was evaluated on the MediaEval Search and Hyperlinking task, demonstrating its effectiveness at locating accurately relevant content in a big media archive.
When textual and visual information join forces for multimedia retrievalBenoit HUET
Currently, popular search engines retrieve documents on the basis of text information. However, integrating the visual information with the text-based search for video and image retrieval is still a hot research topic. In this paper, we propose and evaluate a video search framework based on using visual information to enrich the classic text-based search for video retrieval. The framework extends conventional text-based search by fusing together text and visual scores, obtained from video subtitles (or automatic speech recognition) and visual concept detectors respectively. We attempt to overcome the so called problem of semantic gap by automatically mapping query text to semantic concepts. With the proposed framework, we endeavor to show experimentally, on a set of real world scenarios, that visual cues can effectively contribute to the quality improvement of video retrieval. Experimental results show that mapping text-based queries to visual concepts improves the performance of the search system.
Moreover, when appropriately selecting the relevant visual concepts for a query, a very significant improvement of the system's performance is achieved.
Multimedia Content Understanding: Bringing Context to ContentBenoit HUET
There is a digital revolution happening right before our eyes, the way we communicate is rapidly changing dues to rapid technological advances. Pencil and paper communication is drastically reducing and being replaced with newer communication medium ranging from emails to sms/mms and other instant messaging services. Information/news used to be broadcasted only through official and dedicated channels such as television, radio or newspapers. The technology available today allows every single one of us to be individual information broadcasters whether through text, image or video using our personal connected mobile device. In effect, the current trend shows that video will soon become the most important media on the Internet. While the amount of multimedia content continuously increases there is still progress to be done for automatically understanding multimedia documents in order to provide means to index, search and browse them more effectively. The objectives of this chapter are three-fold. First, we will motivate multimedia content modeling research in the current technological context. Secondly, a broad state of the art will provide the reader with a brief overview of the methodological trends of the field. Thirdly, a bird eye view of the various research themes I have supervised and/or conducted will be presented and will expose how contextual information has become an important additional source of information for multimedia content understanding.
Mining the Web for Multimedia-based Enriching - Multimedia Hyperlinking and ...Benoit HUET
As the amount of social media shared on the Internet grows increasingly, it becomes possible to explore a topic with a novel, people based viewpoint. We aim at performing topic enriching using media items mined from social media sharing platforms. Nevertheless, such data
collected from the Web is likely to contain noise, hence the need to further process collected documents to ensure relevance. To this end, we designed an approach to automatically propose a cleaned set of media items related to events mined from search trends. Events are described using word tags and a pool of videos is linked to each event in order to propose relevant content. This pool has previously been filtered out from non-relevant data using information retrieval techniques. We report the
results of our approach by automatically illustrating the popular moments of four celebrities.
LinkedTV @ MediaEval 2013 Search and Hyperlinking TaskBenoit HUET
This paper aims at presenting the results of LinkedTV's rst
participation to the Search and Hyperlinking task at Medi-
aEval challenge 2013. We used textual information, tran-
scripts, subtitles and metadata, and we tested their combi-
nation with automatically detected visual concepts. Hence,
we submitted various runs to compare diverse approaches
and see the improvement when adding visual information.
Essentials of Automations: Exploring Attributes & Automation ParametersSafe Software
Building automations in FME Flow can save time, money, and help businesses scale by eliminating data silos and providing data to stakeholders in real-time. One essential component to orchestrating complex automations is the use of attributes & automation parameters (both formerly known as “keys”). In fact, it’s unlikely you’ll ever build an Automation without using these components, but what exactly are they?
Attributes & automation parameters enable the automation author to pass data values from one automation component to the next. During this webinar, our FME Flow Specialists will cover leveraging the three types of these output attributes & parameters in FME Flow: Event, Custom, and Automation. As a bonus, they’ll also be making use of the Split-Merge Block functionality.
You’ll leave this webinar with a better understanding of how to maximize the potential of automations by making use of attributes & automation parameters, with the ultimate goal of setting your enterprise integration workflows up on autopilot.
Programming Foundation Models with DSPy - Meetup SlidesZilliz
Prompting language models is hard, while programming language models is easy. In this talk, I will discuss the state-of-the-art framework DSPy for programming foundation models with its powerful optimizers and runtime constraint system.
Fueling AI with Great Data with Airbyte WebinarZilliz
This talk will focus on how to collect data from a variety of sources, leveraging this data for RAG and other GenAI use cases, and finally charting your course to productionalization.
The Microsoft 365 Migration Tutorial For Beginner.pptxoperationspcvita
This presentation will help you understand the power of Microsoft 365. However, we have mentioned every productivity app included in Office 365. Additionally, we have suggested the migration situation related to Office 365 and how we can help you.
You can also read: https://www.systoolsgroup.com/updates/office-365-tenant-to-tenant-migration-step-by-step-complete-guide/
Northern Engraving | Nameplate Manufacturing Process - 2024Northern Engraving
Manufacturing custom quality metal nameplates and badges involves several standard operations. Processes include sheet prep, lithography, screening, coating, punch press and inspection. All decoration is completed in the flat sheet with adhesive and tooling operations following. The possibilities for creating unique durable nameplates are endless. How will you create your brand identity? We can help!
Introduction of Cybersecurity with OSS at Code Europe 2024Hiroshi SHIBATA
I develop the Ruby programming language, RubyGems, and Bundler, which are package managers for Ruby. Today, I will introduce how to enhance the security of your application using open-source software (OSS) examples from Ruby and RubyGems.
The first topic is CVE (Common Vulnerabilities and Exposures). I have published CVEs many times. But what exactly is a CVE? I'll provide a basic understanding of CVEs and explain how to detect and handle vulnerabilities in OSS.
Next, let's discuss package managers. Package managers play a critical role in the OSS ecosystem. I'll explain how to manage library dependencies in your application.
I'll share insights into how the Ruby and RubyGems core team works to keep our ecosystem safe. By the end of this talk, you'll have a better understanding of how to safeguard your code.
Ivanti’s Patch Tuesday breakdown goes beyond patching your applications and brings you the intelligence and guidance needed to prioritize where to focus your attention first. Catch early analysis on our Ivanti blog, then join industry expert Chris Goettl for the Patch Tuesday Webinar Event. There we’ll do a deep dive into each of the bulletins and give guidance on the risks associated with the newly-identified vulnerabilities.
In the realm of cybersecurity, offensive security practices act as a critical shield. By simulating real-world attacks in a controlled environment, these techniques expose vulnerabilities before malicious actors can exploit them. This proactive approach allows manufacturers to identify and fix weaknesses, significantly enhancing system security.
This presentation delves into the development of a system designed to mimic Galileo's Open Service signal using software-defined radio (SDR) technology. We'll begin with a foundational overview of both Global Navigation Satellite Systems (GNSS) and the intricacies of digital signal processing.
The presentation culminates in a live demonstration. We'll showcase the manipulation of Galileo's Open Service pilot signal, simulating an attack on various software and hardware systems. This practical demonstration serves to highlight the potential consequences of unaddressed vulnerabilities, emphasizing the importance of offensive security practices in safeguarding critical infrastructure.
Discover top-tier mobile app development services, offering innovative solutions for iOS and Android. Enhance your business with custom, user-friendly mobile applications.
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2024/06/temporal-event-neural-networks-a-more-efficient-alternative-to-the-transformer-a-presentation-from-brainchip/
Chris Jones, Director of Product Management at BrainChip , presents the “Temporal Event Neural Networks: A More Efficient Alternative to the Transformer” tutorial at the May 2024 Embedded Vision Summit.
The expansion of AI services necessitates enhanced computational capabilities on edge devices. Temporal Event Neural Networks (TENNs), developed by BrainChip, represent a novel and highly efficient state-space network. TENNs demonstrate exceptional proficiency in handling multi-dimensional streaming data, facilitating advancements in object detection, action recognition, speech enhancement and language model/sequence generation. Through the utilization of polynomial-based continuous convolutions, TENNs streamline models, expedite training processes and significantly diminish memory requirements, achieving notable reductions of up to 50x in parameters and 5,000x in energy consumption compared to prevailing methodologies like transformers.
Integration with BrainChip’s Akida neuromorphic hardware IP further enhances TENNs’ capabilities, enabling the realization of highly capable, portable and passively cooled edge devices. This presentation delves into the technical innovations underlying TENNs, presents real-world benchmarks, and elucidates how this cutting-edge approach is positioned to revolutionize edge AI across diverse applications.
Conversational agents, or chatbots, are increasingly used to access all sorts of services using natural language. While open-domain chatbots - like ChatGPT - can converse on any topic, task-oriented chatbots - the focus of this paper - are designed for specific tasks, like booking a flight, obtaining customer support, or setting an appointment. Like any other software, task-oriented chatbots need to be properly tested, usually by defining and executing test scenarios (i.e., sequences of user-chatbot interactions). However, there is currently a lack of methods to quantify the completeness and strength of such test scenarios, which can lead to low-quality tests, and hence to buggy chatbots.
To fill this gap, we propose adapting mutation testing (MuT) for task-oriented chatbots. To this end, we introduce a set of mutation operators that emulate faults in chatbot designs, an architecture that enables MuT on chatbots built using heterogeneous technologies, and a practical realisation as an Eclipse plugin. Moreover, we evaluate the applicability, effectiveness and efficiency of our approach on open-source chatbots, with promising results.
Monitoring and Managing Anomaly Detection on OpenShift.pdfTosin Akinosho
Monitoring and Managing Anomaly Detection on OpenShift
Overview
Dive into the world of anomaly detection on edge devices with our comprehensive hands-on tutorial. This SlideShare presentation will guide you through the entire process, from data collection and model training to edge deployment and real-time monitoring. Perfect for those looking to implement robust anomaly detection systems on resource-constrained IoT/edge devices.
Key Topics Covered
1. Introduction to Anomaly Detection
- Understand the fundamentals of anomaly detection and its importance in identifying unusual behavior or failures in systems.
2. Understanding Edge (IoT)
- Learn about edge computing and IoT, and how they enable real-time data processing and decision-making at the source.
3. What is ArgoCD?
- Discover ArgoCD, a declarative, GitOps continuous delivery tool for Kubernetes, and its role in deploying applications on edge devices.
4. Deployment Using ArgoCD for Edge Devices
- Step-by-step guide on deploying anomaly detection models on edge devices using ArgoCD.
5. Introduction to Apache Kafka and S3
- Explore Apache Kafka for real-time data streaming and Amazon S3 for scalable storage solutions.
6. Viewing Kafka Messages in the Data Lake
- Learn how to view and analyze Kafka messages stored in a data lake for better insights.
7. What is Prometheus?
- Get to know Prometheus, an open-source monitoring and alerting toolkit, and its application in monitoring edge devices.
8. Monitoring Application Metrics with Prometheus
- Detailed instructions on setting up Prometheus to monitor the performance and health of your anomaly detection system.
9. What is Camel K?
- Introduction to Camel K, a lightweight integration framework built on Apache Camel, designed for Kubernetes.
10. Configuring Camel K Integrations for Data Pipelines
- Learn how to configure Camel K for seamless data pipeline integrations in your anomaly detection workflow.
11. What is a Jupyter Notebook?
- Overview of Jupyter Notebooks, an open-source web application for creating and sharing documents with live code, equations, visualizations, and narrative text.
12. Jupyter Notebooks with Code Examples
- Hands-on examples and code snippets in Jupyter Notebooks to help you implement and test anomaly detection models.
2. Visual Data in the 90’s
Huet & Hancock [WACV’96]
Digital Map Corresponding aerial images
Ground Truth taken at different aircraft altitudes
21/05/2012 B. HUET - VIGTA'12 Keynote -2
3. Large Scale in the 90’
Huet & Hancock [IEEE PAMI’99]
Cartographic Database
22 original images
Aerial scenes
Main features: roads
100-1000 lines per image
Trademarks and logos Database [Flickner et al. ’95]
Over 1000 original images
Scanned data
B&W, Various resolution
10-5000 lines per image
21/05/2012 B. HUET - VIGTA'12 Keynote -3
4. The TRECVID years (2001- to date)
2001: 11 hrs from BBC & OpenVideo Project
2003 first collaborative ground truth annotation
2005-2006: 170 hrs (Nov.’04 news in Arabic,
Chinese, and English)
High-level feature extraction (10)
2007-2009: 100hrs from the Netherlands Institute
for Sound and Vision (news magazine, science news, news
reports, documentaries, educational programming, and archival video)
2010-2011: 600hrs of MPEG-4 Creative Commons
Videos
High-level feature extraction (light=50 full=364)
21/05/2012 B. HUET - VIGTA'12 Keynote -4
5. The Trend:
Datasets are going Large-Scale (Web-Scale)
...slowly...
Multimedia / Computer Vision researchers
are tackling and experimenting
with Large-Scale data
Issue:
1 research objective <-> 1 data corpus
Annotation -> expensive and demanding process
21/05/2012 B. HUET - VIGTA'12 Keynote -5
6. Talk Outline
The scene / motivation
Social Events and Big Data
Using social platforms for creating a corpus automatically
Social Event Detection
Using social media for detecting events
Social Event Media Mining
Enriching Event‟s Illustrations through Web Mining
Conclusions
21/05/2012 B. HUET - VIGTA'12 Keynote -6
7. What’s a Social Event?
21/05/2012 B. HUET - VIGTA'12 Keynote -7
8. What’s a Social Event?
VIGTA
2012
Capri
Italy
21/05/2012 B. HUET - VIGTA'12 Keynote -8
9. Big Data!
21/05/2012 B. HUET - VIGTA'12 Keynote -9
15. REST API for query
21/05/2012 B. HUET - VIGTA'12 Keynote - 15
16. Conclusion
The medias and events can be linked via
machine tag.
The relations provided by machine tags can be
taken as ground truth.
Thanks to the REST API, Events and Media
information can be retrieved effectively.
21/05/2012 B. HUET - VIGTA'12 Keynote - 16
18. Event Detection - Related Work
EventBurn.com
Create summaries about given events (searching
Twitter, Facebook, and Flickr)
Firan et al. (CIKM’10)
Event categorization from social media data
Gao et al. (WWW’11)
Employing Twitter data to enrich event information
Liu et al. (ICMR’11)
Finding media illustrating events
21/05/2012 B. HUET - VIGTA'12 Keynote - 18
19. How to mine events from PhotoSet…
Events ??
21/05/2012 B. HUET - VIGTA'12 Keynote - 19
20. Observation
Media are captured during events and shared
Capture Time, Geo-localization
User Tags (Annotations)
Machine-Tag (lastfm:event=1337426)
21/05/2012 B. HUET - VIGTA'12 Keynote - 20
21. How fast media are uploaded?
21/05/2012 B. HUET - VIGTA'12 Keynote - 21
22. Experiment Data
9 Attractive Venues WorldWide
Venue Name NbEvents NbPhotos NbUsers
Melkweg 352 6912 266
Koko 151 3546 155
HMV Forum 106 2650 130
111 Minna Gallery 24 1369 105
HMV Hammersmith Apollo 79 2124 96
Circolo degli Artisti 148 2571 86
Circolo Magnolia 79 2190 76
Ancienne Belgique 212 7831 56
Rotown 204 3623 49
Event Ground Truth obtained from the official agendas
available from individual venue websites.
21/05/2012 B. HUET - VIGTA'12 Keynote - 22
23. Detecting and Identifying Events
Our solution consists of 3 steps:
Location Monitoring: finding the bounding-box of venues.
Temporal Analysis: detecting events by analyzing the
uploading behavior along time.
Event Topic Identification: identifying detected events’ topics
through tag analysis.
14
12
10
8
6
4
2
0
10/05/01 10/05/06 10/05/11 10/05/16 10/05/21 10/05/26 10/05/31
Location Temporal Event Topic
Results
Monitoring Analysis Identification
21/05/2012 B. HUET - VIGTA'12 Keynote - 23
25. Venue Bounding Box Estimation
1 : INPUT : VenueName
2 : OUTPUT : BoundingBox
3 : PhotoSet []
4 : Center GetInfo(
VenueName)
5 : EventSet GetPastEvents(VenueName)
6 : foreach event in EventSet do
7: photos GetFlickrPhoto(event)
8: PhotoSet.append ( photos)
9 : end
10 : GeoSet GetGeoInfo( PhotoSet)
11 : Filter (GeoSet, Center, threshold 1km)
12 : RETURN MinRect(GeoSet)
21/05/2012 B. HUET - VIGTA'12 Keynote - 25
26. Venue Bounding Boxes (a selection)
Paradiso HMV Hammersmith Apollo
Megwelk KoKo
21/05/2012 B. HUET - VIGTA'12 Keynote - 26
27. Analyzing the number of Photos
L
o
c
a
t
i
o
n
Megwelk
D
a
t
REST
e
Query
21/05/2012 B. HUET - VIGTA'12 Keynote - 27
28. Our Media DataSet
Flickr Photos
Taken in May 2010
In either one of the 9 selected locations:
Number of Photos
Name Overlap Total
Geo-tagged Venue Name tagged
Koko 372 2040 3 2409
Rotown 90 273 1 362
Melkweg 363 700 8 1055
HMV Forum 184 412 0 596
111 Minna Gallery 937 3 0 940
Ancienne Belgique 2206 288 2 2492
Circolo degli Artisti 70 553 1 622
Circolo Magnolia 95 236 0 331
Hammersmith Apollo 287 84 0 371
Total : 4604 4589 15 9178
Photos rarely have both geo-tag and venue name tag!
21/05/2012 B. HUET - VIGTA'12 Keynote - 28
29. Analyzing the number of Photos
250
200
Events ??
150
100
50
0
10/05/01 10/05/06 10/05/11 10/05/16 10/05/21 10/05/26 10/05/31
Number of Photos taken in Melkweg (NL) in May 2010
21/05/2012 B. HUET - VIGTA'12 Keynote - 29
30. Analyzing the number of Photos Owners
14
12
Events ??
10
8
6
4
2
0
10/05/01 10/05/06 10/05/11 10/05/16 10/05/21 10/05/26 10/05/31
Number of Photo Owners in Melkweg in May 2010
21/05/2012 B. HUET - VIGTA'12 Keynote - 30
31. Event Detection Approach
Based on media upload activity
At a given time
At a given location
Events can be detected by:
et arg(ti T)
i
Where
ti N photos * N owners
T : Threshold
Venue/Event popularity
Adaptive thresholding
21/05/2012 B. HUET - VIGTA'12 Keynote - 31
32. Event Topics Mining
Keep the top N most frequent tags
Result:
melkweg anouk amsterdam jemaine 2010 european flight flightoftheconchords
conchords fotc mckenzie clement tour bret evelyn
21/05/2012 B. HUET - VIGTA'12 Keynote - 32
33. Event Detection Example
Melkweg in May 2010
Number of photos * Number of photo owners
21/05/2012 B. HUET - VIGTA'12 Keynote - 33
34. Event Detection Example
111 Minna Gallery in May 2010
Number of photos * Number of photo owners
21/05/2012 B. HUET - VIGTA'12 Keynote - 34
35. Event Detection Results
Detection results on different conditions
Source Threshold True Predict False Predict F1
mean 43 21 0.211
Image
median 64 51 0.279
mean 56 56 0.246
Owner
median 58 62 0.251
mean 34 18 0.172
Image*Owner
median 67 53 0.289
21/05/2012 B. HUET - VIGTA'12 Keynote - 35
36. Event Detection Results
Event Detection Statistics
Our Method
Venues Ground Truth LastFM
Detect Matched Precision Recall
Melkweg 69 15 12 0.800 0.174 44
Koko 20 15 8 0.533 0.400 0
HMV Forum 14 12 9 0.750 0.643 14
111 Minna
Gallery 23 15 2 0.133 0.087 0
Ancienne
Belgique 38 15 9 0.600 0.237 28
Rotown 16 15 8 0.533 0.500 13
Circolo degli
Artisti 22 15 8 0.533 0.364 12
Circolo
Magnolia 25 3 1 0.333 0.040 11
Hammersmith
Apollo 15 15 10 0.667 0.667 14
In total 242 120 67 0.558 0.277 136
21/05/2012 B. HUET - VIGTA'12 Keynote - 36
37. Events Detection at Melkweg
Detection Results Ground Truth LastFM
Venue
Date Tags Date Title LastFM Title
Parkway Drive / Despised Icon /
parkwaydrive drive
melkweg 03/05/2010 03/05/2010 Winds Of Plague / The Warriors / 50 1336473 Parkway Drive
parkway
Lions
flight
Flight Of The Conchords - Flight of the
melkweg 02/05/2010 flightoftheconchords 02/05/2010 1439320
UITVERKOCHT Conchords
conchords
Flight Of The Conchords - Flight of the
melkweg 04/05/2010 flightoftheconchords 04/05/2010 1439407
UITVERKOCHT Conchords
Mayer
mayerhawtorne mayer
melkweg 05/05/2010 05/05/2010 Mayer Hawthorne & The County 1416229 Hawthorne &
hawthorne
The County
melkweg 11/05/2010 bonobo 11/05/2010 Bonobo - UITVERKOCHT 1398102 Bonobo
melkweg 14/05/2010 paulweller paul 14/05/2010 Paul Weller - UITVERKOCHT 1406677 Paul Weller
Broken Social
melkweg 18/05/2010 brokensocialscene 18/05/2010 Broken Social Scene - UITVERKOCHT 1334429
Scene
Mike Stern band with special guest
Richard
melkweg 19/05/2010 mikestern richardbona 19/05/2010
Bona featuring Dave Weckl & Bob
Malach
melkweg 25/05/2010 beattimemelkweg 24/05/2010 Beattime - The Kika Edition
melkweg 26/05/2010 beattime 24/05/2010 Beattime - The Kika Edition
Off Centre - day 3 - night met Kode 9 /
melkweg 28/05/2010 offcentre 28/05/2010
Falty DL / Gold Panda / Kelpe
melkweg 30/05/2010 joannanewsom 30/05/2010 Joanna Newsom 1425481 Joanna Newsom
21/05/2012 B. HUET - VIGTA'12 Keynote - 37
39. Conclusions on Event Detection
A novel approach for automatically detecting
social events is presented
The key idea consists in temporally monitoring
media shared on social web sites at a specific
location (Geo Localized Photo)
Automatic Efficient Social Event Detection and
Identification can be achieved
21/05/2012 B. HUET - VIGTA'12 Keynote - 39
41. Objective
Automatically collect training data to build
event visual appearance models
Model training requires both positive and
negative examples/samples
21/05/2012 B. HUET - VIGTA'12 Keynote - 41
42. Our proposed Automated FrameWork
Positive
Sample
Event
tag1 Pic1
tags tag2 Event Model
Top N Pic2 Top M Negative
tags Photos Sample
tag3 Pic3
tagN ………. PicM ……
Rank tags Rank Photos
by frequency by distance to tags
21/05/2012 B. HUET - VIGTA'12 Keynote - 42
43. Positive Samples Collection
Machine Tag
Abbreviation of events name
For example “ACMMM12” is the tag to query photos from
“ACM Multimedia 2012”
21/05/2012 B. HUET - VIGTA'12 Keynote - 43
44. Negative Samples Collection
Photos which do not originate from the event.
Assumption: Photos taken near the location of
the event offer better discriminating power than
random photos.
Collecting Approach
Collect the data taken near the event„s location and time
Extract tag from the collection, and rank them according
to appearance frequency.
Keep the top tags as common tags and use them to rank
photos by similarity
21/05/2012 B. HUET - VIGTA'12 Keynote - 44
47. Event Model Training
Feature:
400D Bag of Words from SIFT features.
Model:
SVM implemented with libSVM
RBF kernel
Cross validation is used to
optimize the parameters
21/05/2012 B. HUET - VIGTA'12 Keynote - 47
48. The (Negative Samples) Model Parameters
R: the location distance between photo taken
and event venue
D: the time-span between photo taken and
event taken time
-An example on event: lastfm:804783
Conclusion:
Use loose parameters
for both time interval
and location distance
21/05/2012 B. HUET - VIGTA'12 Keynote - 48
51. Conclusions
Event-based approach for users to explore,
annotate and share media
Improving user experience
Outstanding challenges in interlinking and curating the
data
Device and User Metadata provide interesting
and valuable clues
Detecting Events from social media activity
Visual Event Media Enrichment
21/05/2012 B. HUET - VIGTA'12 Keynote - 51
52. Conclusions and Future Work
Combine multiple information sources
(Tweets, Social Graph, etc…) to detect and
media enrich events.
Meta-Objective: Social Event analysis based on
connections between events, media and participants
Can the approach be extended to private
events?...
MediaEval: Social Event Detection Task
www.mediaeval.org
21/05/2012 B. HUET - VIGTA'12 Keynote - 52
53. Questions?
IEEE Multimedia Special Issue on
Large-Scale Multimedia Data Collection
(to appear in summer 2012)
Thank you for your attention.
21/05/2012 B. HUET - VIGTA'12 Keynote - 53
Editor's Notes
State of the art
83 ????
More place
More place
Red box is the intersection with the ground truth!