SlideShare uma empresa Scribd logo
1 de 28
QMUL @ MediaEval 2012:
Social Event Detection in
Collaborative Photo Collections
Markus Brenner, Prof. Ebroul Izquierdo




Multimedia and Vision Research Group
Queen Mary University of London, UK
OBJECTIVE


In Collaborative Photo Collection …


1. Find and detect social events
2. Retrieve photos associated with the events


… with the help of additional, external information
INTRODUCTION AND
BACKGROUND

 Internet enables people to host, access and share their
  photos online; for example, through websites like Flickr
  and Facebook
 Collaborative annotations and tags as well as public
  comments are commonplace
 Information people assign varies greatly but often seems
  to include some sort of references to what happened
  where and who was involved
   observed experiences or occurrences
   simply referred to as events
INTRODUCTION AND
BACKGROUND


 Easier to search through photo collections if photos are
  grouped into events
 Link events in photo collections to public social media
  like online news feeds
 Automatically link news with corresponding photos
 Provide additional information that might be relevant to
  users to facilitate their search, like the date and location
  of an event
OVERVIEW OF FRAMEWORK

                                      Query                                                     Preprocessing

                                                                                                     Matching
                                                                                                                     Composing Textual     Extracting Visual
                                                                                                    Geographic
                                                                                                                        Features               Features
                 Gathering External Data                                                             Locations


                   General

                                                                               Detecting Events                        Limiting Search Space
                                              Looking up
                    Translating Terms         Geographic            Google
   Google
                                               Locations           Geocoding
Translate API
                                                                      API        By Date/Time     By Date and
                                                                                                                        By Date and Time      By Location
                                                                                  and Topic        Location
                                          Compiling Names
                      Expanding the
                                           of Geographic
  WordNet                Topic                                     GeoNames
                                              Locations

                                                                                Detected        Retrieving Photos
                                                                                 Events
   DBpedia
(via SPARQL)       Topic-Specific                                                                 Textual Features
                                                                                Retrieved
                                                                                 Photos
                                                                                                     Expanding                              Visual Pruning
                     Soccer Matches*                                                                                   Classification
                                                                                                   Feature Space                            (Classification)



                * Example. Framework extendable to other topics.
GATHERING EXTERNAL DATA




 Expanding the topic
 Handling geographic locations
  (e.g. compiling names of locations)
Expanding the Topic


 Social events often revolve around a topic
  Examples: Festivals, sport events, …
 Problem: Users to no adhere to a controlled vocabulary
 Idea: Expand textual representation of a given topic
  Example: Expand the term concert by relating terms like
  festival, gig, band, sound, etc.
 Accomplish through combination of WordNet, DBpedia
  and some initial evidence
Handling Geographic Locations


 Venue location of a social event is an important cue
 Interested in gaining a more complete understanding
  such as of the city and country a event takes place to
  expand the query
 Beneficial as users often refer to a different geographical
  hierarchy, e.g. foreigner to a country but local to a city
 Also consider geographic coordinates to later match
  geo-tagged photos
 Use Google Geocoding API
Compiling Names of Locations



 Identify and understand any textual annotations in
  photos that refer to geographic locations
 Used in retrieval process to isolate photos that do not
  likely correspond to the venue of a queried event
 Extract all countries and larger cities from the
  GeoNames dataset
Topic-Specific: Soccer Matches




Use DBpedia (SPARQL) to find all soccer clubs and
associated stadiums for a given city in the query
PREPROCESSING




 Matching geographic locations
 Translating terms and stop-words
 Composing textual features
Matching Geographic Locations



 Geo-tagged photos are becoming more and more
  popular
 Identify photos as belonging and not belonging to a
  venue (and an event when also considering the time)
 For each venue compile two sets of photos
  (within/outside its bounds)
Translating Terms and Stop-words


 Photos get annotated and tagged in many different
  languages
 Translate topic-related terms and stop-words into other
  languages
 Limit to languages prevailing in the countries in which
  the query venues are located
 Use Google Translate API
Composing Textual Features

 Concatenate all information into a combined textual
  representation (title, description, keywords, username, …)
 Also include information obtained from external sources
 Use Roman preprocessor to converts text into lower
  case, strip punctuation as well as whitespaces and remove
  accents from Unicode characters
 Eliminates common stop-words, numbers and terms
  commonly associated with photography
 Apply language-agnostic character-based tokenizer
 Convert tokens into a matrix of occurrences (TF/IDF)
RETRIEVING PHOTOS OF AN EVENT


In the most basic case, we (already) know about a specific
event, and we wish to simply retrieve all photos associated
with it


 Classification-based approach
 Limiting search space
 Expanding feature space
 Visual pruning
Classification-based Approach: I



 Treat each event independently (we instantiate a
  separate classifier for each event for a series of events)
 Train classifier on the textual features we compose
  beforehand according to each event
 No separate training dataset required
Classification-based Approach: II



 Binary classification, but also introduce a third class that
  reflects events of the same topic to improve results
 Possible to include features of another query
 Two different fusing strategies implemented
 Experiment with multiple classifiers (Linear SVC, SGD, …)
 Use spare data representation and sparse-adjusted classifier
Limiting Search Space

 Generally, the date and time a photo was captured are
  effective cues to bound the search space
 For each event’s prediction step, we consider only those
  photos that lie within the event’s temporal search
  window
    Specified by the query (e.g. New Year’s Eve)
    Retrieved by the framework through external topic-specific
     sources (e.g. the specific days of a concert tour)
    Roughly estimated (based on a clustering scheme) in the
     forthcoming event detection method
 Exclude photos not matching geographic location
Expanding Feature Space

 Expand feature space based on query information and
  photo collection itself
 Helpful when “training” information is sparse
  (the case when there are few geo-tagged photos)
 Iterative two-step process:
   1. Train initial classifier on the few query terms available
   2. Then compile new list of textual terms based on the
      predicted outcome over all applicable photos
   3. Finally, used gained terms to refine initial query terms
 Example: Photos related to a specific music venue
  contain terms of the playing band or artist
Visual Pruning

 Mixing textual and visual features is not straightforward
 Employ a cascade of two separate classifiers, each
  separately adjusted to its feature space and data
  representation
 First fast textual classification, then visual binary
  pruning on few remaining photos
 Utilize MPEG-7 color and texture features
 Experiment with several classifiers (Random
  Forrest, SVC with RBF kernel, Linear SVC)
DETECTING EVENTS

Two proposals:
 If the date but not time of day is known, apply a
  clustering method on all candidates of a given day
   largest clusters then reflect events
 Otherwise: Expand approach by performing a prediction
  step for any day instead of just selected days conforming
  to the events  will inadvertently grow the search space
 In both cases apply a threshold (number of photos
  relating to potential event) prior considering a new event
EXPERIMENTS




 Dataset
 Implementation details and setup
 Results
Dataset


 2012 MediaEval SED Dataset – Challenge II
 167.332 photos collected from Flickr
 Metadata: unique Flickr ID, capture
  timestamp, username, title, description, keywords and
  partial geographic coordinates (in about a fifth of the
  cases:)
 Ground truth in the form of event clusters (specifying
  associated photos) for two topics/challenges
 “Training set”: 2011 MediaEval SED Dataset
Implementation Details and
Setup

 Define event as a distinct combination of location and
  date (one event per day at the same location)
 Use English names of locations only
 Bounding threshold of 500 meter
 Default: Linear SVC, no feature expansion, no visual
  pruning
 Evaluation measures: Precision (P), Recall (R),
  F-score, Normalized Mutual Information (NMI)
Dataset Setup


 Focus on Challenge II
 Challenge I/III: Current approach has limitation
    No event/venue detection through social media websites
     like Twitter
    Only basic venue/location detection/clustering
      issue when the destination covers a large area
     (e.g. entire country)
Results: Challenge II

 Detected: 32 events


 Identified several thousand photos not belonging
  to any relevant venue
   substantial reduction of candidates
   large amount of training samples

                             P      R      F     NMI
   Default configuration    79.0   67.1   72.6   0.65
   Basic event detection    56.0   69.6   62.0   0.53    worse
   With visual pruning      83.2   61.9   71.0   0.63
   With feature expansion   79.0   66.9   72.5   0.65
CONCLUSION


 External information, e.g. about a venue, helpful for
  both event detection and retrieval of associated photos
 Finding and linking external data in a uniform way
  still challenging
 Visual information does not improve results much
 Future considerations:
    Social media websites like Facebook and Twitter
    Improved venue/location detection/clustering
Thank you!
    Questions?

Mais conteúdo relacionado

Destaque

Week 2 discussion 2
Week 2 discussion 2Week 2 discussion 2
Week 2 discussion 2LILBIT2012
 
CERTH @ MediaEval 2012 Social Event Detection Task
CERTH @ MediaEval 2012 Social Event Detection TaskCERTH @ MediaEval 2012 Social Event Detection Task
CERTH @ MediaEval 2012 Social Event Detection TaskMediaEval2012
 
The Watershed-based Social Events Detection Method with Support from External...
The Watershed-based Social Events Detection Method with Support from External...The Watershed-based Social Events Detection Method with Support from External...
The Watershed-based Social Events Detection Method with Support from External...MediaEval2012
 
The Deck by Phil Polstra GrrCON2012
The Deck by Phil Polstra GrrCON2012The Deck by Phil Polstra GrrCON2012
The Deck by Phil Polstra GrrCON2012Philip Polstra
 
Idea or opportunity?
Idea or opportunity?Idea or opportunity?
Idea or opportunity?Grow America
 
MediaEval 2012 Visual Privacy Task: Privacy and Intelligibility through Pixel...
MediaEval 2012 Visual Privacy Task: Privacy and Intelligibility through Pixel...MediaEval 2012 Visual Privacy Task: Privacy and Intelligibility through Pixel...
MediaEval 2012 Visual Privacy Task: Privacy and Intelligibility through Pixel...MediaEval2012
 
When Ideas and Opportunities Collide
When Ideas and Opportunities CollideWhen Ideas and Opportunities Collide
When Ideas and Opportunities CollideGrow America
 
The MediaEval 2012 Affect Task: Violent Scenes Detectio
The MediaEval 2012 Affect Task: Violent Scenes DetectioThe MediaEval 2012 Affect Task: Violent Scenes Detectio
The MediaEval 2012 Affect Task: Violent Scenes DetectioMediaEval2012
 
LIG at MediaEval 2012 affect task: use of a generic method
LIG at MediaEval 2012 affect task: use of a generic methodLIG at MediaEval 2012 affect task: use of a generic method
LIG at MediaEval 2012 affect task: use of a generic methodMediaEval2012
 
Telefonica Research System for the Spoken Web Search task at Mediaeval 2012
Telefonica Research System for the Spoken Web Search task at Mediaeval 2012Telefonica Research System for the Spoken Web Search task at Mediaeval 2012
Telefonica Research System for the Spoken Web Search task at Mediaeval 2012MediaEval2012
 
תחרות אלוף הידע
תחרות אלוף הידעתחרות אלוף הידע
תחרות אלוף הידעsabal1
 
John Richards: My Life Lessons As An Entrepreneur
John Richards: My Life Lessons As An EntrepreneurJohn Richards: My Life Lessons As An Entrepreneur
John Richards: My Life Lessons As An EntrepreneurGrow America
 

Destaque (14)

Week 2 discussion 2
Week 2 discussion 2Week 2 discussion 2
Week 2 discussion 2
 
Live pitch event
Live pitch eventLive pitch event
Live pitch event
 
CERTH @ MediaEval 2012 Social Event Detection Task
CERTH @ MediaEval 2012 Social Event Detection TaskCERTH @ MediaEval 2012 Social Event Detection Task
CERTH @ MediaEval 2012 Social Event Detection Task
 
The Watershed-based Social Events Detection Method with Support from External...
The Watershed-based Social Events Detection Method with Support from External...The Watershed-based Social Events Detection Method with Support from External...
The Watershed-based Social Events Detection Method with Support from External...
 
The Deck by Phil Polstra GrrCON2012
The Deck by Phil Polstra GrrCON2012The Deck by Phil Polstra GrrCON2012
The Deck by Phil Polstra GrrCON2012
 
Idea or opportunity?
Idea or opportunity?Idea or opportunity?
Idea or opportunity?
 
MediaEval 2012 Visual Privacy Task: Privacy and Intelligibility through Pixel...
MediaEval 2012 Visual Privacy Task: Privacy and Intelligibility through Pixel...MediaEval 2012 Visual Privacy Task: Privacy and Intelligibility through Pixel...
MediaEval 2012 Visual Privacy Task: Privacy and Intelligibility through Pixel...
 
Thotcon2013
Thotcon2013Thotcon2013
Thotcon2013
 
When Ideas and Opportunities Collide
When Ideas and Opportunities CollideWhen Ideas and Opportunities Collide
When Ideas and Opportunities Collide
 
The MediaEval 2012 Affect Task: Violent Scenes Detectio
The MediaEval 2012 Affect Task: Violent Scenes DetectioThe MediaEval 2012 Affect Task: Violent Scenes Detectio
The MediaEval 2012 Affect Task: Violent Scenes Detectio
 
LIG at MediaEval 2012 affect task: use of a generic method
LIG at MediaEval 2012 affect task: use of a generic methodLIG at MediaEval 2012 affect task: use of a generic method
LIG at MediaEval 2012 affect task: use of a generic method
 
Telefonica Research System for the Spoken Web Search task at Mediaeval 2012
Telefonica Research System for the Spoken Web Search task at Mediaeval 2012Telefonica Research System for the Spoken Web Search task at Mediaeval 2012
Telefonica Research System for the Spoken Web Search task at Mediaeval 2012
 
תחרות אלוף הידע
תחרות אלוף הידעתחרות אלוף הידע
תחרות אלוף הידע
 
John Richards: My Life Lessons As An Entrepreneur
John Richards: My Life Lessons As An EntrepreneurJohn Richards: My Life Lessons As An Entrepreneur
John Richards: My Life Lessons As An Entrepreneur
 

Semelhante a QMUL @ MediaEval 2012: Social Event Detection in Collaborative Photo Collections

duy_bien_ism2014_paper
duy_bien_ism2014_paperduy_bien_ism2014_paper
duy_bien_ism2014_paperDuy Phạm
 
UCT GIS Labs
UCT GIS LabsUCT GIS Labs
UCT GIS Labspvhead123
 
Extracting event and place semantics from Flickr tags
Extracting event and place semantics from Flickr tagsExtracting event and place semantics from Flickr tags
Extracting event and place semantics from Flickr tagsmor
 
1 presentation idea_bank
1 presentation idea_bank1 presentation idea_bank
1 presentation idea_bankmskmoorthy
 
Strathclyde University Geospatial Metadata Workshop 20110531
Strathclyde University Geospatial Metadata Workshop 20110531Strathclyde University Geospatial Metadata Workshop 20110531
Strathclyde University Geospatial Metadata Workshop 20110531EDINA, University of Edinburgh
 
Performing Fast Spatial Query Search by Using Ultimate Code Words
Performing Fast Spatial Query Search by Using Ultimate Code WordsPerforming Fast Spatial Query Search by Using Ultimate Code Words
Performing Fast Spatial Query Search by Using Ultimate Code WordsBRNSSPublicationHubI
 
Semantic Search tutorial at SemTech 2012
Semantic Search tutorial at SemTech 2012Semantic Search tutorial at SemTech 2012
Semantic Search tutorial at SemTech 2012Peter Mika
 
AddressingHistory - Crowdsourcing the Past - Stuart Macdonald
AddressingHistory - Crowdsourcing the Past - Stuart MacdonaldAddressingHistory - Crowdsourcing the Past - Stuart Macdonald
AddressingHistory - Crowdsourcing the Past - Stuart MacdonaldJISC GECO
 
Geosolutions FOSS4g 2009 Redux
Geosolutions FOSS4g 2009 ReduxGeosolutions FOSS4g 2009 Redux
Geosolutions FOSS4g 2009 ReduxGeoSolutions
 
Geospatial metadata and spatial data workshop: 19 June 2014
Geospatial metadata and spatial data workshop: 19 June 2014Geospatial metadata and spatial data workshop: 19 June 2014
Geospatial metadata and spatial data workshop: 19 June 2014EDINA, University of Edinburgh
 
Scalable Keyword Cover Search using Keyword NNE and Inverted Indexing
Scalable Keyword Cover Search using Keyword NNE and Inverted IndexingScalable Keyword Cover Search using Keyword NNE and Inverted Indexing
Scalable Keyword Cover Search using Keyword NNE and Inverted IndexingIRJET Journal
 
Functional and Architectural Requirements for Metadata: Supporting Discovery...
Functional and Architectural Requirements for Metadata: Supporting Discovery...Functional and Architectural Requirements for Metadata: Supporting Discovery...
Functional and Architectural Requirements for Metadata: Supporting Discovery...Jian Qin
 
Leeds University Geospatial Metadata Workshop 20110617
Leeds University Geospatial Metadata Workshop 20110617Leeds University Geospatial Metadata Workshop 20110617
Leeds University Geospatial Metadata Workshop 20110617EDINA, University of Edinburgh
 
Real World Application Performance with MongoDB
Real World Application Performance with MongoDBReal World Application Performance with MongoDB
Real World Application Performance with MongoDBMongoDB
 

Semelhante a QMUL @ MediaEval 2012: Social Event Detection in Collaborative Photo Collections (19)

No(Geo)SQL
No(Geo)SQLNo(Geo)SQL
No(Geo)SQL
 
duy_bien_ism2014_paper
duy_bien_ism2014_paperduy_bien_ism2014_paper
duy_bien_ism2014_paper
 
UCT GIS Labs
UCT GIS LabsUCT GIS Labs
UCT GIS Labs
 
Extracting event and place semantics from Flickr tags
Extracting event and place semantics from Flickr tagsExtracting event and place semantics from Flickr tags
Extracting event and place semantics from Flickr tags
 
1 presentation idea_bank
1 presentation idea_bank1 presentation idea_bank
1 presentation idea_bank
 
Strathclyde University Geospatial Metadata Workshop 20110531
Strathclyde University Geospatial Metadata Workshop 20110531Strathclyde University Geospatial Metadata Workshop 20110531
Strathclyde University Geospatial Metadata Workshop 20110531
 
Performing Fast Spatial Query Search by Using Ultimate Code Words
Performing Fast Spatial Query Search by Using Ultimate Code WordsPerforming Fast Spatial Query Search by Using Ultimate Code Words
Performing Fast Spatial Query Search by Using Ultimate Code Words
 
AddressingHistory: Lessons and Messages
AddressingHistory:  Lessons and MessagesAddressingHistory:  Lessons and Messages
AddressingHistory: Lessons and Messages
 
Semantic Search tutorial at SemTech 2012
Semantic Search tutorial at SemTech 2012Semantic Search tutorial at SemTech 2012
Semantic Search tutorial at SemTech 2012
 
AddressingHistory - Crowdsourcing the Past - Stuart Macdonald
AddressingHistory - Crowdsourcing the Past - Stuart MacdonaldAddressingHistory - Crowdsourcing the Past - Stuart Macdonald
AddressingHistory - Crowdsourcing the Past - Stuart Macdonald
 
Geosolutions FOSS4g 2009 Redux
Geosolutions FOSS4g 2009 ReduxGeosolutions FOSS4g 2009 Redux
Geosolutions FOSS4g 2009 Redux
 
Bn32416419
Bn32416419Bn32416419
Bn32416419
 
Crowdsourcing the Past with AddressingHistory
Crowdsourcing the Past with AddressingHistory Crowdsourcing the Past with AddressingHistory
Crowdsourcing the Past with AddressingHistory
 
Geospatial metadata and spatial data workshop: 19 June 2014
Geospatial metadata and spatial data workshop: 19 June 2014Geospatial metadata and spatial data workshop: 19 June 2014
Geospatial metadata and spatial data workshop: 19 June 2014
 
DBpedia mobile
DBpedia mobileDBpedia mobile
DBpedia mobile
 
Scalable Keyword Cover Search using Keyword NNE and Inverted Indexing
Scalable Keyword Cover Search using Keyword NNE and Inverted IndexingScalable Keyword Cover Search using Keyword NNE and Inverted Indexing
Scalable Keyword Cover Search using Keyword NNE and Inverted Indexing
 
Functional and Architectural Requirements for Metadata: Supporting Discovery...
Functional and Architectural Requirements for Metadata: Supporting Discovery...Functional and Architectural Requirements for Metadata: Supporting Discovery...
Functional and Architectural Requirements for Metadata: Supporting Discovery...
 
Leeds University Geospatial Metadata Workshop 20110617
Leeds University Geospatial Metadata Workshop 20110617Leeds University Geospatial Metadata Workshop 20110617
Leeds University Geospatial Metadata Workshop 20110617
 
Real World Application Performance with MongoDB
Real World Application Performance with MongoDBReal World Application Performance with MongoDB
Real World Application Performance with MongoDB
 

Mais de MediaEval2012

MediaEval 2012 Opening
MediaEval 2012 OpeningMediaEval 2012 Opening
MediaEval 2012 OpeningMediaEval2012
 
A Multimodal Approach for Video Geocoding
A Multimodal Approach for   Video Geocoding A Multimodal Approach for   Video Geocoding
A Multimodal Approach for Video Geocoding MediaEval2012
 
Brave New Task: Musiclef Multimodal Music Tagging
Brave New Task: Musiclef Multimodal Music TaggingBrave New Task: Musiclef Multimodal Music Tagging
Brave New Task: Musiclef Multimodal Music TaggingMediaEval2012
 
Search and Hyperlinking Task at MediaEval 2012
Search and Hyperlinking Task at MediaEval 2012Search and Hyperlinking Task at MediaEval 2012
Search and Hyperlinking Task at MediaEval 2012MediaEval2012
 
CUNI at MediaEval 2012: Search and Hyperlinking Task
CUNI at MediaEval 2012: Search and Hyperlinking TaskCUNI at MediaEval 2012: Search and Hyperlinking Task
CUNI at MediaEval 2012: Search and Hyperlinking TaskMediaEval2012
 
DCU Search Runs at MediaEval 2012: Search and Hyperlinking Task
DCU Search Runs at MediaEval 2012: Search and Hyperlinking TaskDCU Search Runs at MediaEval 2012: Search and Hyperlinking Task
DCU Search Runs at MediaEval 2012: Search and Hyperlinking TaskMediaEval2012
 
Ghent University-IBBT at MediaEval 2012 Search and Hyperlinking: Semantic Sim...
Ghent University-IBBT at MediaEval 2012 Search and Hyperlinking: Semantic Sim...Ghent University-IBBT at MediaEval 2012 Search and Hyperlinking: Semantic Sim...
Ghent University-IBBT at MediaEval 2012 Search and Hyperlinking: Semantic Sim...MediaEval2012
 
Brave New Task: User Account Matching
Brave New Task: User Account MatchingBrave New Task: User Account Matching
Brave New Task: User Account MatchingMediaEval2012
 
The CLEF Initiative From 2010 to 2012 and Onwards
The CLEF Initiative From 2010 to 2012 and OnwardsThe CLEF Initiative From 2010 to 2012 and Onwards
The CLEF Initiative From 2010 to 2012 and OnwardsMediaEval2012
 
Overview of MediaEval 2012 Visual Privacy Task
Overview of MediaEval 2012 Visual Privacy TaskOverview of MediaEval 2012 Visual Privacy Task
Overview of MediaEval 2012 Visual Privacy TaskMediaEval2012
 
MediaEval 2012 Visual Privacy Task: Applying Transform-domain Scrambling to A...
MediaEval 2012 Visual Privacy Task: Applying Transform-domain Scrambling to A...MediaEval 2012 Visual Privacy Task: Applying Transform-domain Scrambling to A...
MediaEval 2012 Visual Privacy Task: Applying Transform-domain Scrambling to A...MediaEval2012
 
Violent Scenes Detection with Large, Brute-forced Acoustic and Visual Feature...
Violent Scenes Detection with Large, Brute-forced Acoustic and Visual Feature...Violent Scenes Detection with Large, Brute-forced Acoustic and Visual Feature...
Violent Scenes Detection with Large, Brute-forced Acoustic and Visual Feature...MediaEval2012
 
Technicolor/INRIA/Imperial College London at the MediaEval 2012 Violent Scene...
Technicolor/INRIA/Imperial College London at the MediaEval 2012 Violent Scene...Technicolor/INRIA/Imperial College London at the MediaEval 2012 Violent Scene...
Technicolor/INRIA/Imperial College London at the MediaEval 2012 Violent Scene...MediaEval2012
 
NII, Japan at MediaEval 2012 Violent Scenes Detection Affect Task
NII, Japan at MediaEval 2012 Violent Scenes Detection Affect TaskNII, Japan at MediaEval 2012 Violent Scenes Detection Affect Task
NII, Japan at MediaEval 2012 Violent Scenes Detection Affect TaskMediaEval2012
 
Violence Detection in Video by Large Scale Multi-Scale Local Binary Pattern D...
Violence Detection in Video by Large Scale Multi-Scale Local Binary Pattern D...Violence Detection in Video by Large Scale Multi-Scale Local Binary Pattern D...
Violence Detection in Video by Large Scale Multi-Scale Local Binary Pattern D...MediaEval2012
 
ARF @ MediaEval 2012: An Uninformed Approach to Violence Detection in Hollywo...
ARF @ MediaEval 2012: An Uninformed Approach to Violence Detection in Hollywo...ARF @ MediaEval 2012: An Uninformed Approach to Violence Detection in Hollywo...
ARF @ MediaEval 2012: An Uninformed Approach to Violence Detection in Hollywo...MediaEval2012
 
The Shanghai-Hongkong Team at MediaEval2012: Violent Scene Detection Using Tr...
The Shanghai-Hongkong Team at MediaEval2012: Violent Scene Detection Using Tr...The Shanghai-Hongkong Team at MediaEval2012: Violent Scene Detection Using Tr...
The Shanghai-Hongkong Team at MediaEval2012: Violent Scene Detection Using Tr...MediaEval2012
 
UNICAMP-UFMG at MediaEval 2012: Genre Tagging Task
UNICAMP-UFMG at MediaEval 2012: Genre Tagging TaskUNICAMP-UFMG at MediaEval 2012: Genre Tagging Task
UNICAMP-UFMG at MediaEval 2012: Genre Tagging TaskMediaEval2012
 
TUD at MediaEval 2012 genre tagging task: Multi-modality video categorization...
TUD at MediaEval 2012 genre tagging task: Multi-modality video categorization...TUD at MediaEval 2012 genre tagging task: Multi-modality video categorization...
TUD at MediaEval 2012 genre tagging task: Multi-modality video categorization...MediaEval2012
 

Mais de MediaEval2012 (20)

MediaEval 2012 Opening
MediaEval 2012 OpeningMediaEval 2012 Opening
MediaEval 2012 Opening
 
A Multimodal Approach for Video Geocoding
A Multimodal Approach for   Video Geocoding A Multimodal Approach for   Video Geocoding
A Multimodal Approach for Video Geocoding
 
Brave New Task: Musiclef Multimodal Music Tagging
Brave New Task: Musiclef Multimodal Music TaggingBrave New Task: Musiclef Multimodal Music Tagging
Brave New Task: Musiclef Multimodal Music Tagging
 
Search and Hyperlinking Task at MediaEval 2012
Search and Hyperlinking Task at MediaEval 2012Search and Hyperlinking Task at MediaEval 2012
Search and Hyperlinking Task at MediaEval 2012
 
CUNI at MediaEval 2012: Search and Hyperlinking Task
CUNI at MediaEval 2012: Search and Hyperlinking TaskCUNI at MediaEval 2012: Search and Hyperlinking Task
CUNI at MediaEval 2012: Search and Hyperlinking Task
 
DCU Search Runs at MediaEval 2012: Search and Hyperlinking Task
DCU Search Runs at MediaEval 2012: Search and Hyperlinking TaskDCU Search Runs at MediaEval 2012: Search and Hyperlinking Task
DCU Search Runs at MediaEval 2012: Search and Hyperlinking Task
 
Ghent University-IBBT at MediaEval 2012 Search and Hyperlinking: Semantic Sim...
Ghent University-IBBT at MediaEval 2012 Search and Hyperlinking: Semantic Sim...Ghent University-IBBT at MediaEval 2012 Search and Hyperlinking: Semantic Sim...
Ghent University-IBBT at MediaEval 2012 Search and Hyperlinking: Semantic Sim...
 
Brave New Task: User Account Matching
Brave New Task: User Account MatchingBrave New Task: User Account Matching
Brave New Task: User Account Matching
 
The CLEF Initiative From 2010 to 2012 and Onwards
The CLEF Initiative From 2010 to 2012 and OnwardsThe CLEF Initiative From 2010 to 2012 and Onwards
The CLEF Initiative From 2010 to 2012 and Onwards
 
Overview of MediaEval 2012 Visual Privacy Task
Overview of MediaEval 2012 Visual Privacy TaskOverview of MediaEval 2012 Visual Privacy Task
Overview of MediaEval 2012 Visual Privacy Task
 
MediaEval 2012 Visual Privacy Task: Applying Transform-domain Scrambling to A...
MediaEval 2012 Visual Privacy Task: Applying Transform-domain Scrambling to A...MediaEval 2012 Visual Privacy Task: Applying Transform-domain Scrambling to A...
MediaEval 2012 Visual Privacy Task: Applying Transform-domain Scrambling to A...
 
Violent Scenes Detection with Large, Brute-forced Acoustic and Visual Feature...
Violent Scenes Detection with Large, Brute-forced Acoustic and Visual Feature...Violent Scenes Detection with Large, Brute-forced Acoustic and Visual Feature...
Violent Scenes Detection with Large, Brute-forced Acoustic and Visual Feature...
 
mevd2012 esra_
 mevd2012 esra_ mevd2012 esra_
mevd2012 esra_
 
Technicolor/INRIA/Imperial College London at the MediaEval 2012 Violent Scene...
Technicolor/INRIA/Imperial College London at the MediaEval 2012 Violent Scene...Technicolor/INRIA/Imperial College London at the MediaEval 2012 Violent Scene...
Technicolor/INRIA/Imperial College London at the MediaEval 2012 Violent Scene...
 
NII, Japan at MediaEval 2012 Violent Scenes Detection Affect Task
NII, Japan at MediaEval 2012 Violent Scenes Detection Affect TaskNII, Japan at MediaEval 2012 Violent Scenes Detection Affect Task
NII, Japan at MediaEval 2012 Violent Scenes Detection Affect Task
 
Violence Detection in Video by Large Scale Multi-Scale Local Binary Pattern D...
Violence Detection in Video by Large Scale Multi-Scale Local Binary Pattern D...Violence Detection in Video by Large Scale Multi-Scale Local Binary Pattern D...
Violence Detection in Video by Large Scale Multi-Scale Local Binary Pattern D...
 
ARF @ MediaEval 2012: An Uninformed Approach to Violence Detection in Hollywo...
ARF @ MediaEval 2012: An Uninformed Approach to Violence Detection in Hollywo...ARF @ MediaEval 2012: An Uninformed Approach to Violence Detection in Hollywo...
ARF @ MediaEval 2012: An Uninformed Approach to Violence Detection in Hollywo...
 
The Shanghai-Hongkong Team at MediaEval2012: Violent Scene Detection Using Tr...
The Shanghai-Hongkong Team at MediaEval2012: Violent Scene Detection Using Tr...The Shanghai-Hongkong Team at MediaEval2012: Violent Scene Detection Using Tr...
The Shanghai-Hongkong Team at MediaEval2012: Violent Scene Detection Using Tr...
 
UNICAMP-UFMG at MediaEval 2012: Genre Tagging Task
UNICAMP-UFMG at MediaEval 2012: Genre Tagging TaskUNICAMP-UFMG at MediaEval 2012: Genre Tagging Task
UNICAMP-UFMG at MediaEval 2012: Genre Tagging Task
 
TUD at MediaEval 2012 genre tagging task: Multi-modality video categorization...
TUD at MediaEval 2012 genre tagging task: Multi-modality video categorization...TUD at MediaEval 2012 genre tagging task: Multi-modality video categorization...
TUD at MediaEval 2012 genre tagging task: Multi-modality video categorization...
 

Último

New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationSlibray Presentation
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Commit University
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfAlex Barbosa Coqueiro
 
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxDigital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxLoriGlavin3
 
unit 4 immunoblotting technique complete.pptx
unit 4 immunoblotting technique complete.pptxunit 4 immunoblotting technique complete.pptx
unit 4 immunoblotting technique complete.pptxBkGupta21
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxNavinnSomaal
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupFlorian Wilhelm
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr BaganFwdays
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
A Deep Dive on Passkeys: FIDO Paris Seminar.pptx
A Deep Dive on Passkeys: FIDO Paris Seminar.pptxA Deep Dive on Passkeys: FIDO Paris Seminar.pptx
A Deep Dive on Passkeys: FIDO Paris Seminar.pptxLoriGlavin3
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Mattias Andersson
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii SoldatenkoFwdays
 
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdfHyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdfPrecisely
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfAddepto
 
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024BookNet Canada
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteDianaGray10
 
The State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptxThe State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptxLoriGlavin3
 
TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024Lonnie McRorey
 

Último (20)

New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
Connect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck PresentationConnect Wave/ connectwave Pitch Deck Presentation
Connect Wave/ connectwave Pitch Deck Presentation
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdf
 
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptxDigital Identity is Under Attack: FIDO Paris Seminar.pptx
Digital Identity is Under Attack: FIDO Paris Seminar.pptx
 
unit 4 immunoblotting technique complete.pptx
unit 4 immunoblotting technique complete.pptxunit 4 immunoblotting technique complete.pptx
unit 4 immunoblotting technique complete.pptx
 
SAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptxSAP Build Work Zone - Overview L2-L3.pptx
SAP Build Work Zone - Overview L2-L3.pptx
 
Streamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project SetupStreamlining Python Development: A Guide to a Modern Project Setup
Streamlining Python Development: A Guide to a Modern Project Setup
 
"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan
 
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
Transcript: New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
A Deep Dive on Passkeys: FIDO Paris Seminar.pptx
A Deep Dive on Passkeys: FIDO Paris Seminar.pptxA Deep Dive on Passkeys: FIDO Paris Seminar.pptx
A Deep Dive on Passkeys: FIDO Paris Seminar.pptx
 
Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?Are Multi-Cloud and Serverless Good or Bad?
Are Multi-Cloud and Serverless Good or Bad?
 
"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko"Debugging python applications inside k8s environment", Andrii Soldatenko
"Debugging python applications inside k8s environment", Andrii Soldatenko
 
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdfHyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
Hyperautomation and AI/ML: A Strategy for Digital Transformation Success.pdf
 
DMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special EditionDMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special Edition
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdf
 
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
New from BookNet Canada for 2024: Loan Stars - Tech Forum 2024
 
Take control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test SuiteTake control of your SAP testing with UiPath Test Suite
Take control of your SAP testing with UiPath Test Suite
 
The State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptxThe State of Passkeys with FIDO Alliance.pptx
The State of Passkeys with FIDO Alliance.pptx
 
TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024TeamStation AI System Report LATAM IT Salaries 2024
TeamStation AI System Report LATAM IT Salaries 2024
 

QMUL @ MediaEval 2012: Social Event Detection in Collaborative Photo Collections

  • 1. QMUL @ MediaEval 2012: Social Event Detection in Collaborative Photo Collections Markus Brenner, Prof. Ebroul Izquierdo Multimedia and Vision Research Group Queen Mary University of London, UK
  • 2. OBJECTIVE In Collaborative Photo Collection … 1. Find and detect social events 2. Retrieve photos associated with the events … with the help of additional, external information
  • 3. INTRODUCTION AND BACKGROUND  Internet enables people to host, access and share their photos online; for example, through websites like Flickr and Facebook  Collaborative annotations and tags as well as public comments are commonplace  Information people assign varies greatly but often seems to include some sort of references to what happened where and who was involved  observed experiences or occurrences  simply referred to as events
  • 4. INTRODUCTION AND BACKGROUND  Easier to search through photo collections if photos are grouped into events  Link events in photo collections to public social media like online news feeds  Automatically link news with corresponding photos  Provide additional information that might be relevant to users to facilitate their search, like the date and location of an event
  • 5. OVERVIEW OF FRAMEWORK Query Preprocessing Matching Composing Textual Extracting Visual Geographic Features Features Gathering External Data Locations General Detecting Events Limiting Search Space Looking up Translating Terms Geographic Google Google Locations Geocoding Translate API API By Date/Time By Date and By Date and Time By Location and Topic Location Compiling Names Expanding the of Geographic WordNet Topic GeoNames Locations Detected Retrieving Photos Events DBpedia (via SPARQL) Topic-Specific Textual Features Retrieved Photos Expanding Visual Pruning Soccer Matches* Classification Feature Space (Classification) * Example. Framework extendable to other topics.
  • 6. GATHERING EXTERNAL DATA  Expanding the topic  Handling geographic locations (e.g. compiling names of locations)
  • 7. Expanding the Topic  Social events often revolve around a topic Examples: Festivals, sport events, …  Problem: Users to no adhere to a controlled vocabulary  Idea: Expand textual representation of a given topic Example: Expand the term concert by relating terms like festival, gig, band, sound, etc.  Accomplish through combination of WordNet, DBpedia and some initial evidence
  • 8. Handling Geographic Locations  Venue location of a social event is an important cue  Interested in gaining a more complete understanding such as of the city and country a event takes place to expand the query  Beneficial as users often refer to a different geographical hierarchy, e.g. foreigner to a country but local to a city  Also consider geographic coordinates to later match geo-tagged photos  Use Google Geocoding API
  • 9. Compiling Names of Locations  Identify and understand any textual annotations in photos that refer to geographic locations  Used in retrieval process to isolate photos that do not likely correspond to the venue of a queried event  Extract all countries and larger cities from the GeoNames dataset
  • 10. Topic-Specific: Soccer Matches Use DBpedia (SPARQL) to find all soccer clubs and associated stadiums for a given city in the query
  • 11. PREPROCESSING  Matching geographic locations  Translating terms and stop-words  Composing textual features
  • 12. Matching Geographic Locations  Geo-tagged photos are becoming more and more popular  Identify photos as belonging and not belonging to a venue (and an event when also considering the time)  For each venue compile two sets of photos (within/outside its bounds)
  • 13. Translating Terms and Stop-words  Photos get annotated and tagged in many different languages  Translate topic-related terms and stop-words into other languages  Limit to languages prevailing in the countries in which the query venues are located  Use Google Translate API
  • 14. Composing Textual Features  Concatenate all information into a combined textual representation (title, description, keywords, username, …)  Also include information obtained from external sources  Use Roman preprocessor to converts text into lower case, strip punctuation as well as whitespaces and remove accents from Unicode characters  Eliminates common stop-words, numbers and terms commonly associated with photography  Apply language-agnostic character-based tokenizer  Convert tokens into a matrix of occurrences (TF/IDF)
  • 15. RETRIEVING PHOTOS OF AN EVENT In the most basic case, we (already) know about a specific event, and we wish to simply retrieve all photos associated with it  Classification-based approach  Limiting search space  Expanding feature space  Visual pruning
  • 16. Classification-based Approach: I  Treat each event independently (we instantiate a separate classifier for each event for a series of events)  Train classifier on the textual features we compose beforehand according to each event  No separate training dataset required
  • 17. Classification-based Approach: II  Binary classification, but also introduce a third class that reflects events of the same topic to improve results  Possible to include features of another query  Two different fusing strategies implemented  Experiment with multiple classifiers (Linear SVC, SGD, …)  Use spare data representation and sparse-adjusted classifier
  • 18. Limiting Search Space  Generally, the date and time a photo was captured are effective cues to bound the search space  For each event’s prediction step, we consider only those photos that lie within the event’s temporal search window  Specified by the query (e.g. New Year’s Eve)  Retrieved by the framework through external topic-specific sources (e.g. the specific days of a concert tour)  Roughly estimated (based on a clustering scheme) in the forthcoming event detection method  Exclude photos not matching geographic location
  • 19. Expanding Feature Space  Expand feature space based on query information and photo collection itself  Helpful when “training” information is sparse (the case when there are few geo-tagged photos)  Iterative two-step process: 1. Train initial classifier on the few query terms available 2. Then compile new list of textual terms based on the predicted outcome over all applicable photos 3. Finally, used gained terms to refine initial query terms  Example: Photos related to a specific music venue contain terms of the playing band or artist
  • 20. Visual Pruning  Mixing textual and visual features is not straightforward  Employ a cascade of two separate classifiers, each separately adjusted to its feature space and data representation  First fast textual classification, then visual binary pruning on few remaining photos  Utilize MPEG-7 color and texture features  Experiment with several classifiers (Random Forrest, SVC with RBF kernel, Linear SVC)
  • 21. DETECTING EVENTS Two proposals:  If the date but not time of day is known, apply a clustering method on all candidates of a given day  largest clusters then reflect events  Otherwise: Expand approach by performing a prediction step for any day instead of just selected days conforming to the events  will inadvertently grow the search space  In both cases apply a threshold (number of photos relating to potential event) prior considering a new event
  • 22. EXPERIMENTS  Dataset  Implementation details and setup  Results
  • 23. Dataset  2012 MediaEval SED Dataset – Challenge II  167.332 photos collected from Flickr  Metadata: unique Flickr ID, capture timestamp, username, title, description, keywords and partial geographic coordinates (in about a fifth of the cases:)  Ground truth in the form of event clusters (specifying associated photos) for two topics/challenges  “Training set”: 2011 MediaEval SED Dataset
  • 24. Implementation Details and Setup  Define event as a distinct combination of location and date (one event per day at the same location)  Use English names of locations only  Bounding threshold of 500 meter  Default: Linear SVC, no feature expansion, no visual pruning  Evaluation measures: Precision (P), Recall (R), F-score, Normalized Mutual Information (NMI)
  • 25. Dataset Setup  Focus on Challenge II  Challenge I/III: Current approach has limitation  No event/venue detection through social media websites like Twitter  Only basic venue/location detection/clustering  issue when the destination covers a large area (e.g. entire country)
  • 26. Results: Challenge II  Detected: 32 events  Identified several thousand photos not belonging to any relevant venue  substantial reduction of candidates  large amount of training samples P R F NMI Default configuration 79.0 67.1 72.6 0.65 Basic event detection 56.0 69.6 62.0 0.53  worse With visual pruning 83.2 61.9 71.0 0.63 With feature expansion 79.0 66.9 72.5 0.65
  • 27. CONCLUSION  External information, e.g. about a venue, helpful for both event detection and retrieval of associated photos  Finding and linking external data in a uniform way still challenging  Visual information does not improve results much  Future considerations:  Social media websites like Facebook and Twitter  Improved venue/location detection/clustering
  • 28. Thank you! Questions?