ImageNet: A Large-Scale Hierarchical Image Database

Slides:



Advertisements
Similar presentations
Computer Vision Group UC Berkeley How should we combine high level and low level knowledge? Jitendra Malik UC Berkeley Recognition using regions is joint.
Advertisements

Improved TF-IDF Ranker
Large-Scale Entity-Based Online Social Network Profile Linkage.
Jing-Shin Chang National Chi Nan University, IJCNLP-2013, Nagoya 2013/10/15 ACLCLP – Activities ( ) & Text Corpora.
3 Small Comments Alex Berg Stony Brook University I work on recognition: features – action recognition – alignment – detection – attributes – hierarchical.
Discriminative Relevance Feedback With Virtual Textual Representation For Efficient Image Retrieval Suman Karthik and C.V.Jawahar.
Large-Scale Image Retrieval From Your Sketches Daniel Brooks 1,Loren Lin 2,Yijuan Lu 1 1 Department of Computer Science, Texas State University, TX, USA.
So What Does it All Mean? Geospatial Semantics and Ontologies Dr Kristin Stock.
Building a Large- Scale Knowledge Base for Machine Translation Kevin Knight and Steve K. Luk Presenter: Cristina Nicolae.
Creating a Similarity Graph from WordNet
Large Scale Visual Recognition Challenge 2011 Alex BergStony Brook Jia DengStanford & Princeton Sanjeev SatheeshStanford Hao SuStanford Fei-Fei LiStanford.
›SIFT features [3] were computed for 100 images (from ImageNet [4]) for each of our 48 subordinate-level categories. ›The visual features of an image were.
IT’S NOT POLITE TO POINT: DESCRIBING PEOPLE WITH UNCERTAIN ATTRIBUTES CVPR 2013 Poster.
Large dataset for object and scene recognition A. Torralba, R. Fergus, W. T. Freeman 80 million tiny images Ron Yanovich Guy Peled.
Tour the World: building a web-scale landmark recognition engine ICCV 2009 Yan-Tao Zheng1, Ming Zhao2, Yang Song2, Hartwig Adam2 Ulrich Buddemeier2, Alessandro.
Li-Jia Li Yongwhan Lim Li Fei-Fei Chong Wang David M. Blei B UILDING AND U SING A S EMANTIVISUAL I MAGE H IERARCHY CVPR, 2010.
Image Retrieval Discussion
EECS 442 – Computer vision Segments of this lectures are courtesy of Prof F. Li, R. Fergus and A. Zisserman Databases for object recognition and beyond.
WMES3103 : INFORMATION RETRIEVAL
CS335 Principles of Multimedia Systems Content Based Media Retrieval Hao Jiang Computer Science Department Boston College Dec. 4, 2007.
MUSCLE/ImageCLEF workshop 2005 Extracting an Ontology of Portrayable Objects from WordNet Atomic Energy Agency of France (CEA) LIC2M (Multilingual Multimedia.
Properties of Text CS336 Lecture 3:. 2 Information Retrieval Searching unstructured documents Typically text –Newspaper articles –Web pages Other documents.
Presented by Zeehasham Rasheed
Visual Object Recognition Rob Fergus Courant Institute, New York University
Agenda Introduction Bag-of-words models Visual words with spatial location Part-based models Discriminative methods Segmentation and recognition Recognition-based.
Ontology Learning and Population from Text: Algorithms, Evaluation and Applications Chapters Presented by Sole.
Semantic Web Technologies Lecture # 2 Faculty of Computer Science, IBA.
Joint Image Clustering and Labeling by Matrix Factorization
Course G Web Search Engines 3/9/2011 Wei Xu
The Three R’s of Vision Jitendra Malik.
Lecture #32 WWW Search. Review: Data Organization Kinds of things to organize –Menu items –Text –Images –Sound –Videos –Records (I.e. a person ’ s name,
Human abilities Presented By Mahmoud Awadallah 1.
Short Text Understanding Through Lexical-Semantic Analysis
WordNet ® and its Java API ♦ Introduction to WordNet ♦ WordNet API for Java Name: Hao Li Uni: hl2489.
An ontology is a semantic structure that formalizes the knowledge that members of a community have about a given domain. consists of concepts and relations.
Jennie Ning Zheng Linda Melchor Ferhat Omur. Contents Introduction WordNet Application – WordNet Data Structure - WordNet FrameNet Application – FrameNet.
NaLIX Natural Language Interface for querying XML Huahai Yang Department of Information Studies Joint work with Yunyao Li and H.V. Jagadish at University.
SYMPOSIUM ON SEMANTICS IN SYSTEMS FOR TEXT PROCESSING September 22-24, Venice, Italy Combining Knowledge-based Methods and Supervised Learning for.
10/22/2015ACM WIDM'20051 Semantic Similarity Methods in WordNet and Their Application to Information Retrieval on the Web Giannis Varelas Epimenidis Voutsakis.
WordNet: Connecting words and concepts Christiane Fellbaum Cognitive Science Laboratory Princeton University.
80 million tiny images: a large dataset for non-parametric object and scene recognition CS 4763 Multimedia Systems Spring 2008.
10/31/20151 EASTERN MEDITERRANEAN UNIVERSITY COMPUTER ENGINEERING DEPARTMENT Presented By Duygu CELIK Supervised By Atilla ELCI Intelligent Semantic Web.
MSRI workshop, January 2005 Object Recognition Collected databases of objects on uniform background (no occlusions, no clutter) Mostly focus on viewpoint.
UNBIASED LOOK AT DATASET BIAS Antonio Torralba Massachusetts Institute of Technology Alexei A. Efros Carnegie Mellon University CVPR 2011.
Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li and Li Fei-Fei Dept. of Computer Science, Princeton University, USA CVPR ImageNet1.
School of Engineering and Computer Science Victoria University of Wellington Copyright: Peter Andreae, VUW Image Recognition COMP # 18.
Wordnet - A lexical database for the English Language.
Image Classification for Automatic Annotation
Image Classification over Visual Tree Jianping Fan Dept of Computer Science UNC-Charlotte, NC
A Semantic Knowledge Base for the UK Government Web Archive Tom Storrar & Claire Newing Applying records management processes principles to the open government.
Towards Total Scene Understanding: Classification, Annotation and Segmentation in an Automatic Framework N 工科所 錢雅馨 2011/01/16 Li-Jia Li, Richard.
Local Naïve Bayes Nearest Neighbor for image classification Scancho McCann David G.Lowe University of British Columbia 2012 CVPR WonJun Na.
Annotation Framework & ImageCLEF 2014 JAN BOTOREK, PETRA BUDÍKOVÁ
Using Wikipedia for Hierarchical Finer Categorization of Named Entities Aasish Pappu Language Technologies Institute Carnegie Mellon University PACLIC.
2/10/2016Semantic Similarity1 Semantic Similarity Methods in WordNet and Their Application to Information Retrieval on the Web Giannis Varelas Epimenidis.
Semantic Interoperability in GIS N. L. Sarda Suman Somavarapu.
Semantic search-based image annotation Petra Budíková, FI MU CEMI meeting, Plzeň,
Most Professional Translation Services provider in USA.
YOLO9000:Better, Faster, Stronger
Next-Generation Search Engines -Perspective and challenges
Basic Intro Tutorial on Machine Learning and Data Mining
Finding Clusters within a Class to Improve Classification Accuracy
Database.
WordNet: A Lexical Database for English
WordNet WordNet, WSD.
Automatic Detection of Causal Relations for Question Answering
Using Natural Language Processing to Aid Computer Vision
Semantic Similarity Methods in WordNet and their Application to Information Retrieval on the Web Yizhe Ge.
Giannis Varelas Epimenidis Voutsakis Paraskevi Raftopoulou
Presentation transcript:

ImageNet: A Large-Scale Hierarchical Image Database Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li and Li Fei-Fei Dept. of Computer Science, Princeton University, USA CVPR 2009 You Zhou youzhou@usc.edu

Dataset in Computer Vision

Dataset in Computer Vision UIUC Cars (2004) S. Agarwal, A. Awan, D. Roth CMU/VASC Faces (1998) H. Rowley, S. Baluja, T. Kanade FERET Faces (1998) P. Phillips, H. Wechsler, J. Huang, P. Raus COIL Objects (1996) S. Nene, S. Nayar, H. Murase MNIST digits (1998-10) Y LeCun & C. Cortes KTH human action (2004) I. Leptev & B. Caputo Sign Language (2008) P. Buehler, M. Everingham, A. Zisserman Segmentation (2001) D. Martin, C. Fowlkes, D. Tal, J. Malik.

WordNet WordNet is a large lexical database of English. Nouns, verbs, adjectives and adverbs are grouped into sets of cognitive synonyms (synsets), each expressing a distinct concept. WordNet as an ontology

ImageNet Image database organized according to the WordNet hierarchy, in which each node of the hierarchy is depicted by hundreds and thousands of images. Knowledge ontology: Taxonomy, Partonomy

Collect Candidate Images For each synset, the queries are the set of WordNet synonyms Accuracy of Internet image search results: 10% For 500-1000 clean images, need 10K images Query expansion Synonyms: German shepherd, German police dog, German shepherd dog, Alsatian Appending words from ancestors: sheepdog, dog Multiple languages Italian, Dutch, Spanish, Chinese More search engines

Clean Candidate Images Rely on humans to verify each candidate image for a given synset 19 years’ work No graduate students would want to do this project Amazon Mechanical Turk (AMT) 300 images: 0.02 dollar 14,197,122 images: 946 dollars 10 repetition: 9460 dollars July 2008 - April 2010: 11 million images, 15,000+ synsets

HIT Design HIT(Human Intelligence Task) Application Qualification Test Start tasks Learn about the keyword: Wiki, Google Definition quiz: choice question about the keyword Choose images fit the keyword (Yes or No) Pass cheating detection Feedback

Quality Control System Human users make mistakes Not all users follow the instructions Users do not always agree with each other Subtle or confusing synsets, e.g. Burmese cat

Properties of ImageNet Scale 14,197,122 images, 21841 synsets indexed Hierarchy densely populated semantic hierarchy

Properties of ImageNet Accuracy Diversity

ImageNet Applications Non-parametric Object Recognition NN-voting + noisy ImageNet NN-voting + clean ImageNet Naive Bayesian Nearest Neighbor (NBNN) NBNN-100 Tree Based Image Classification Automatic Object Localization

Pros and Cons Pros: Large dataset as training resource Benchmarking Open: Download Original Images, URLs, Features, Object Attributes, API Cons: The matching between physical world/ WordNet / ImageNet. Counterword Only one tag per image