Mobile Photos April 17, 2008. Auto Extraction of Flickr Tags Unstructured text labels Extract structured knowledge Place and event semantics Scale-structure.

Slides:



Advertisements
Similar presentations
Workshop on Online Social Networks Microsoft Research Cambridge December 7, 2007.
Advertisements

Taxonomy & Ontology Impact on Search Infrastructure John R. McGrath Sr. Director, Fast Search & Transfer.
Using Large-Scale Web Data to Facilitate Textual Query Based Retrieval of Consumer Photos.
Information Society Technologies Third Call for Proposals Norbert Brinkhoff-Button DG Information Society European Commission Key action III: Multmedia.
Management, Population and Marketing of institutional repositories / open access journals Iryna Kuchma, eIFL Open Access program manager, eIFL.net Presented.
Haystack: Per-User Information Environment 1999 Conference on Information and Knowledge Management Eytan Adar et al Presented by Xiao Hu CS491CXZ.
1 Evaluation Rong Jin. 2 Evaluation  Evaluation is key to building effective and efficient search engines usually carried out in controlled experiments.
A Better Mobile Location Landscape May 2008 Sam Altman, Co-founder and CEO.
GENERATING AUTOMATIC SEMANTIC ANNOTATIONS FOR RESEARCH DATASETS AYUSH SINGHAL AND JAIDEEP SRIVASTAVA CS DEPT., UNIVERSITY OF MINNESOTA, MN, USA.
Explorations in Tag Suggestion and Query Expansion Jian Wang and Brian D. Davison Lehigh University, USA SSM 2008 (Workshop on Search in Social Media)
 Hamed Sadeghi Neshat.  With Internet delivery of video content surging to an unprecedented level, video advertising is becoming increasingly pervasive.
Information Retrieval Review
Semantic Web and Web Mining: Networking with Industry and Academia İsmail Hakkı Toroslu IST EVENT 2006.
Event Extraction: Learning from Corpora Prepared by Ralph Grishman Based on research and slides by Roman Yangarber NYU.
Information Retrieval Concerned with the: Representation of Storage of Organization of, and Access to Information items.
Information Retrieval in Practice
Re-ranking Documents Segments To Improve Access To Relevant Content in Information Retrieval Gary Madden Applied Computational Linguistics Dublin City.
Contextual Intelligence: Scalability Issues in Personal Semantic Networks Oliver Brdiczka.
Web Mining Research: A Survey
Information retrieval Finding relevant data using irrelevant keys Example: database of photographic images sorted by number, date. DBMS: Well structured.
Important Task in Patents Retrieval Recall is an Important Factor Given Query Patent -> the Task is to Search all Related Patents Patents have Complex.
Semantic Web and Web Mining: Networking with Industry and Academia İsmail Hakkı Toroslu IST EVENT 2006.
Yuri de Lugt Collexis Karin Clavel TU Delft Library.
Finding Wormholes with Flickr Geotags Maarten Clements Marcel Reinders Arjen de Vries Pavel Serdyukov December 3 rd, 2009 GIS.
CS598CXZ Course Summary ChengXiang Zhai Department of Computer Science University of Illinois, Urbana-Champaign.
Research paper: Web Mining Research: A survey SIGKDD Explorations, June Volume 2, Issue 1 Author: R. Kosala and H. Blockeel.
Reyyan Yeniterzi Weakly-Supervised Discovery of Named Entities Using Web Search Queries Marius Pasca Google CIKM 2007.
The Yellow Group Design Informatics (Regli, Stone, Kusiak, Leifer, Gupta, Chung, Fenves, Law, Kopena)
The Semantic Web and Microformats. The Semantic Web Syntax = how you say something – Letters, words, punctuation Semantics = meaning behind what you say.
UMBC iConnect Audumbar Chormale, Dr. A. Joshi, Dr. T. Finin, Dr. Z. Segall.
Xiaoying Gao Computer Science Victoria University of Wellington Intelligent Agents COMP 423.
WebMining Web Mining By- Pawan Singh Piyush Arora Pooja Mansharamani Pramod Singh Praveen Kumar 1.
1 Information Retrieval Acknowledgements: Dr Mounia Lalmas (QMW) Dr Joemon Jose (Glasgow)
Data Mining By Dave Maung.
Page 1 Alliver™ Page 2 Scenario Users Contents Properties Contexts Tags Users Context Listener Set of contents Service Reasoner GPS Navigator.
Search Engine Architecture
Prof. Thomas Sikora Technische Universität Berlin Communication Systems Group Thursday, 2 April 2009 Integration Activities in “Tools for Tag Generation“
Research Topics/Areas. Adapting search to Users Advertising and ad targeting Aggregation of Results Community and Context Aware Search Community-based.
Co-funded by the European Union Semantic CMS Community Content and Knowledge Management From free text input to automatic entity enrichment Copyright IKS.
Introduction to Information Retrieval Example of information need in the context of the world wide web: “Find all documents containing information on computer.
Measuring How Good Your Search Engine Is. *. Information System Evaluation l Before 1993 evaluations were done using a few small, well-known corpora of.
Information Retrieval CSE 8337 Spring 2007 Introduction/Overview Some Material for these slides obtained from: Modern Information Retrieval by Ricardo.
Recuperação de Informação Cap. 01: Introdução 21 de Fevereiro de 1999 Berthier Ribeiro-Neto.
Information Retrieval
FriendFinder Location-aware social networking on mobile phones.
FriendFinder Location-aware social networking on mobile phones.
SAPIR Search in Audio-Visual Content using P2P Information Retrival For more information visit: Support.
RICHES TM Connections Tool Connie Harper Amy Larner Giroux, PhD.
FriendFinder Location-aware social networking on mobile phones.
What is touchPRO EXPRESS? touchPRO EXPRESS is a way for Associations who meet certain criteria to be able to get a mobile app at a low cost and have their.
Flickr Tag Recommendation based on Collective Knowledge Hyunwoo Kim SNU IDB Lab. August 27, 2008 Borkur Sigurbjornsson, Roelof van Zwol Yahoo! Research.
An Ontology-based Automatic Semantic Annotation Approach for Patent Document Retrieval in Product Innovation Design Feng Wang, Lanfen Lin, Zhou Yang College.
WHIM- Spring ‘10 By:-Enza Desai. What is HCIR? Study of IR techniques that brings human intelligence into search process. Coined by Gary Marchionini.
Semantic Web Technologies Readings discussion Research presentations Projects & Papers discussions.
COMP423 Intelligent Agents. Recommender systems Two approaches – Collaborative Filtering Based on feedback from other users who have rated a similar set.
Information Retrieval in Practice
Search Engine Architecture
Datamining : Refers to extracting or mining knowledge from large amounts of data Applications : Market Analysis Fraud Detection Customer Retention Production.
Multimedia Information Retrieval
Accounting for the relative importance of objects in image retrieval
Information Retrieval
Text Categorization Document classification categorizes documents into one or more classes which is useful in Information Retrieval (IR). IR is the task.
CSE 635 Multimedia Information Retrieval
Web Mining Department of Computer Science and Engg.
Search Engine Architecture
Web and Internet Search: What’s Next?
Information Retrieval and Web Design
Recuperação de Informação
Privacy-Aware Tag Recommendation for Image Sharing
Presentation transcript:

Mobile Photos April 17, 2008

Auto Extraction of Flickr Tags Unstructured text labels Extract structured knowledge Place and event semantics Scale-structure identification Spatial and temporal patterns at various scales Events/place as small bursts in time/space Standard IR metrics to evaluate performance ◦low precision: most of the items retrieved are irrelevant ◦low recall: may fail to retrieve some documents that are actually relevant to the search question Ground truth manual annotation, 803 tags

World Explorer aggregate knowledge from unstructured tags “representativeness” of a tag primary and secondary tags for visualizing markers (text size) on a map tourism tasks

Photos on the Go social, spatial (specific places), topical on mobile phone Zurfer: wallet for world’s media self-selected >500, 69 active, 9 interviewees grounded with mobile logs nearby, latest from contacts, own photos, highly ranked Flickr ease of use; multitasking; social interaction and physical convenience 3 use modes: Task Time, Down Time, and Killing Time. Implications: speed, location content, social content, 3 use modes

Mobile Advertising (B-MAD) location-aware mobile advertisements permission-based needs ads complemented with personalization push service quantitative: device discovery and latency of network (positioning and ad delivery) qualitative: user reaction to ads figure 6 scale: which one’s neutral? privacy and security issues