What Helps Where And Why? Semantic Relatedness for Knowledge Transfer
|
|
- Gordon Hutchinson
- 6 years ago
- Views:
Transcription
1 What Helps Where And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 1,2 Michael Stark 1,2 György Szarvas 1 Iryna Gurevych 1 Bernt Schiele 1,2 1 Department of Computer Science, TU Darmstadt 2 MPI Informatics, Saarbrücken
2 Knowledge transfer for zero-shot object class recognition Unseen class (no training images) Giant panda? Attributes for knowledge transfer Describing using attributes [Farhadi et al., CVPR `09 & `10] Group classes by attributes [Lampert et al., CVPR `09] animal four legged mammal Manual supervision: Attribute labels white paw Manual supervision: Object class-attribute associations CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 2
3 Knowledge transfer for zero-shot object class recognition Unseen Attributes class for knowledge transfer (no Replace training manual images) supervision Giant panda? by semantic relatedness mined from language resources WordNet Attributes for knowledge transfer Describing using attributes [Farhadi et al., CVPR `09 & `10] Group classes by attributes [Lampert et al., CVPR `09] animal four legged mammal Unsupervised Transfer Manual supervision: Attribute labels white paw Manual supervision: Object class-attribute associations CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 3
4 Attribute-based model [Lampert et al., CVPR `09] Known training classes Class-attribute associations Attributes classifiers spots white ocean [Lampert et al., CVPR `09] Supervised: manual (human judges) Class-attribute associations Unseen test classes CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 4
5 Attribute-based model [Lampert et al., CVPR `09] Known training classes Class-attribute associations Attribute classifiers spots white ocean Word Net semantic relatedness from language [Lampert et al., CVPR `09] Supervised: manual (human judges) Class-attribute associations Unseen test classes CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 5
6 Direct similarity-based model Known training classes Class-attribute associations Attribute classifiers spots white ocean Word Net semantic relatedness from language Class-attribute associations Unseen test classes CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 6
7 Direct similarity-based model Known training classes Classifier per class Dalmatian polar bear killer whale Word Net semantic relatedness from language Class-attribute associations Unseen test classes CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 7
8 Direct similarity-based model Known training classes Classifier per class Dalmatian polar bear killer whale Word Net semantic relatedness from language most similar classes Unseen test classes CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 8
9 Outline Models for visual knowledge transfer Semantic relatedness measures Language resources WordNet Wikipedia WWW Image search Respective state-of-the-art measures Evaluation Conclusion CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 9
10 Semantic Relatedness Measures WordNet Lin measure [Budanitsky & Hirst, CL `06] Wikipedia Explicit Semantic Analysis [Gabrilovich & MarkovitchI, IJCAI `07] Word Wide Web Hitcount (Dice coeffient) [Kilgarriff & Grefenstette, CL `03] Image search Visually more relevant Hitcount (Dice coeffient) horse WordNet [Fellbaum, MIT press `98] animal mammal entity elephant car vehicle bike CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 10
11 Semantic Relatedness Measures WordNet Lin measure [Budanitsky & Hirst, CL `06] Wikipedia Explicit Semantic Analysis [Gabrilovich & MarkovitchI, IJCAI `07] Word Wide Web Hitcount (Dice coeffient) [Kilgarriff & Grefenstette, CL `03] Image search Visually more relevant Hitcount (Dice coeffient) horse WordNet [Fellbaum, MIT press `98] animal mammal entity elephant car vehicle bike CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 11
12 Semantic Relatedness Measures WordNet Lin measure [Budanitsky & Hirst, CL `06] Wikipedia Explicit Semantic Analysis [Gabrilovich & MarkovitchI, IJCAI `07] Word Wide Web Hitcount (Dice coeffient) [Kilgarriff & Grefenstette, CL `03] Image search Visually more relevant Hitcount (Dice coeffient) Farm A farm is an area A of farm lan is an area of lan the training of horses. the training of horses. Hoof A hoof is the tip of A a hoof toe is the tip of a toe Rear hooves of a horse Rear hooves of a horse Most evem tped ungulat Tusk Article horse elephant Farm 3 0 Hoof 2 1 Tusk 0 4 Farm Hoof Tusk Tusks are long teeth, Tusks u are long teeth, u Elephants and narwhals Elephants and narwhals CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 12
13 Semantic Relatedness Measures WordNet Lin measure [Budanitsky & Hirst, CL `06] Wikipedia Explicit Semantic Analysis [Gabrilovich & MarkovitchI, IJCAI `07] Word Wide Web Hitcount (Dice coeffient) [Kilgarriff & Grefenstette, CL `03] Image search Visually more relevant Hitcount (Dice coeffient) Farm A farm is an area A of farm lan is an area of lan the training of horses. the training of horses. Hoof A hoof is the tip of A a hoof toe is the tip of a toe Rear hooves of a horse Rear hooves of a horse Most evem tped ungulat Tusk Article horse elephant Farm 3 0 Hoof 2 1 Tusk 0 4 Farm Hoof Tusk Tusks are long teeth, Tusks u are long teeth, u Elephants and narwhals Elephants and narwhals cosine CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 13
14 Semantic Relatedness Measures WordNet Lin measure [Budanitsky & Hirst, CL `06] Wikipedia Explicit Semantic Analysis [Gabrilovich & MarkovitchI, IJCAI `07] Word Wide Web Hitcount (Dice coeffient) [Kilgarriff & Grefenstette, CL `03] Image search Visually more relevant Hitcount (Dice coeffient) CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 14
15 Semantic Relatedness Measures WordNet Lin measure [Budanitsky & Hirst, CL `06] Wikipedia Explicit Semantic Analysis [Gabrilovich & MarkovitchI, IJCAI `07] Word Wide Web Hitcount (Dice coeffient) [Kilgarriff & Grefenstette, CL `03] Image search Visually more relevant Hitcount (Dice coeffient) web search We watched a horse race yesterday. [..] Tomorrow we go in the zoo to look at the baby elephant. Incidental co-occurence image search [ lahierophant/ /] the dance of the horse and elephant Terms refer to same entity (the image) CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 15
16 Outline Models for visual knowledge transfer Semantic relatedness measures Evaluation Attributes Querying class-attribute associations Mining attributes Direct similarity Attribute-based vs. direct similarity Conclusion CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 16
17 Experimental Setup Animals with attributes dataset [Lampert et al., CVPR `09] 40 training, 10 test classes (disjoint) images total Downsampled to 92 training images per class Manual associations to 85 attributes Image classification SVM: Histogram intersection kernel Area under ROC curve (AUC) - chance level: 50% Mean over all 10 test classes CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 17
18 Performance of supervised approach CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 18
19 Querying class-attribute association Performance of queried association Encouraging Below manual supervision Image search Based on image related text Wikipedia Robust resource Yahoo Web Very noisy resource WordNet Path length poor indicator of class-attribute associations Querying: abbreviation agile Manual supervision: detailed description having a high degree of physical coordination CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 19
20 Querying class-attribute association Performance of queried association Encouraging Below manual supervision Image search (Yahoo Img, Flickr) Based on image related text Wikipedia Robust resource (definition texts) Yahoo Web Very noisy resource WordNet Path length poor indicator of class-attribute associations image search the dance of the horse and elephant CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 20
21 Querying class-attribute association Performance of queried association Encouraging Below manual supervision Image search (Yahoo Img, Flickr) Based on image related text Wikipedia Robust resource (definition text) Yahoo Web Very noisy resource WordNet Path length poor indicator of class-attribute associations Noise: While he watched a horse race the leg of his chair broke. CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 21
22 Querying class-attribute association Performance of queried association Encouraging Below manual supervision Image search (Yahoo Img, Flickr) Based on image related text Wikipedia Robust resource (definition text) Yahoo Web Very noisy resource WordNet Path length poor indicator of class-attribute associations entity mammal horse elephant tooth tusk CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 22
23 Mining attributes Known training classes Class-attribute associations Attribute terms spots white ocean Word Net semantic relatedness from language Class-attribute associations Unseen test classes CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 23
24 Mining attributes Known training classes Class-attribute associations Attribute terms Class-attribute associations???? Word Net semantic relatedness from language Unseen test classes CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 24
25 Mining attributes Known training classes Class-attribute associations Part Attribute attributes Leg classifiers of a dog semantic relatedness leg paw flipper from language Word Net Word Net Class-attribute associations Unseen test classes CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 25
26 Mining attributes Additional measure: Holonym patterns Only part attributes Hit Counts of Patterns [Berland & Charniak, ACL 1999] cow s leg leg of a cow Dice coefficient web search While he watched a horse race the leg of his chair broke. Incidental co-occurence holonym patterns Leg of the horse One term likely part of other term CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 26
27 Mining attributes Best: Yahoo Holonyms Close to manual attributes Tailored towards part attributes CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 27
28 Mining attributes Best: Yahoo Holonyms Close to manual attributes Tailored towards part attributes Performance drop Reduced diversity Only part attributes Specialized terms E.g. pilus (=hair) Coverage problem: Image search, Wikipedia CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 28
29 Outline Models for visual knowledge transfer Semantic relatedness measures Evaluation Attributes Querying class-attribute associations Mining attributes Direct similarity Attribute-based vs. direct similarity Conclusion CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 29
30 Direct similarity-based model Known training classes Classifier per class Dalmatian polar bear killer whale Word Net semantic relatedness from language most similar classes Unseen test classes CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 30
31 Direct Similarity Nearly all very good On par with manual supervision attribute model (black) Clearly better than any mined attribute-associations result Why? Five most related classes Ranking of semantic relatedness reliable Similar between methods CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 31
32 mean AUC (in %) Attributes vs. direct similarity Extending the test set Add images From known classes As negatives More realistic setting Results Direct similarity drop in performance (orange curve) Attribute models generalize well 70 attributes: manually defined attributes: queried mined associations attributes: mined attributes 65 direct similarity 0 10, , Number of additional training class images in test set CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 32
33 Outline Models for visual knowledge transfer Semantic relatedness measures Evaluation Conclusion CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 33
34 Conclusion Supervision replaced with semantic relatedness Direct similarity better than attributes on par with supervised approach Attributes: generalizes better Semantic relatedness measures Overall best Yahoo image with hit count Holonym patterns for web search Improvement Limited to part attributes CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 34
35 mean AUC (in %) Conclusion Supervision replaced with semantic relatedness Direct similarity better than attributes on par with supervised approach Attributes: generalize better Semantic relatedness measures Overall best Yahoo image with hit count Holonym patterns for web search Improvement Limited to part attributes attributes: manually defined attributes: queried mined associations attributes: mined attributes direct similarity Number of additional training class images in test set CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 35
36 mean AUC (in %) Conclusion Supervision replaced with semantic relatedness Direct similarity better than attributes on par with supervised approach Attributes: generalize better Semantic relatedness measures Overall best Yahoo image with hit count Holonym patterns for web search Improvement Limited to part attributes WordNet poor for object-attributes associations Number of additional training class images in test set patterns: dog s leg leg of the dogs attributes: manually defined attributes: queried mined associations attributes: mined attributes direct similarity CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 36
37 Thank you! Further supervision for closing the semantic gap? See us at our poster (A2, Atrium)! Software? CVPR 2010 What Helps Where - And Why? Semantic Relatedness for Knowledge Transfer Marcus Rohrbach 37
UKParl: A Data Set for Topic Detection with Semantically Annotated Text
UKParl: A Data Set for Topic Detection with Semantically Annotated Text Federico Nanni, Mahmoud Osman, Yi-Ru Cheng, Simone Paolo Ponzetto and Laura Dietz My Research Post-Doc in computational social science
More informationCase-based reasoning using electronic health records efficiently identifies eligible patients for clinical trials
Case-based reasoning using electronic health records efficiently identifies eligible patients for clinical trials Riccardo Miotto and Chunhua Weng Department of Biomedical Informatics Columbia University,
More informationAnnotation and Retrieval System Using Confabulation Model for ImageCLEF2011 Photo Annotation
Annotation and Retrieval System Using Confabulation Model for ImageCLEF2011 Photo Annotation Ryo Izawa, Naoki Motohashi, and Tomohiro Takagi Department of Computer Science Meiji University 1-1-1 Higashimita,
More informationAction Recognition. Computer Vision Jia-Bin Huang, Virginia Tech. Many slides from D. Hoiem
Action Recognition Computer Vision Jia-Bin Huang, Virginia Tech Many slides from D. Hoiem This section: advanced topics Convolutional neural networks in vision Action recognition Vision and Language 3D
More informationFINAL REPORT Measuring Semantic Relatedness using a Medical Taxonomy. Siddharth Patwardhan. August 2003
FINAL REPORT Measuring Semantic Relatedness using a Medical Taxonomy by Siddharth Patwardhan August 2003 A report describing the research work carried out at the Mayo Clinic in Rochester as part of an
More informationEbook Code: REAU5038
Ebook Code: REAU5038 Contents Science and Technology, Society and Environment/HSIE What is a Mammal?... 6 Aquatic Animals... 7 Looking at the Humpback... 8 Whale Acrobatics... 9 Food Chains... 1 0 Keeping
More informationGrade 3. Practice Test. Plight of the Polar Bear Giant Pandas
Name Date Grade 3 Plight of the Polar Bear Giant Pandas Today you will read two passages. Read these sources carefully to gather information to answer questions and write an essay. Excerpt from Plight
More informationMARINE SCIENCE. Monday 23 Jan 2017
MARINE SCIENCE Monday 23 Jan 2017 Entry Task Cyberlab discussion: Based on your field research from Friday, which marine mammals are never observed on land? Why? Agenda Housekeeping Unit 21 (Marine Mammals)
More informationGIANT: Geo-Informative Attributes for Location Recognition and Exploration
GIANT: Geo-Informative Attributes for Location Recognition and Exploration Quan Fang, Jitao Sang, Changsheng Xu Institute of Automation, Chinese Academy of Sciences October 23, 2013 Where is this? La Sagrada
More informationFish 475: Marine Mammalogy
Fish 475: Marine Mammalogy Wednesday, 31 March 2010 Course website: http://faculty.washington.edu/glennvb/fish475 Pieter Folkens Taxonomy Cetaceans: General characteristics I: 1. Loss of rear limbs and
More informationGRAY WHALE. Text source: The Marine Mammal Center
GRAY WHALE Gray whales are found only in the Pacific Ocean, and they have one of the longest migrations of any mammal. During the summer, they live in the Arctic. In the fall, they travel to Baja California,
More informationSupplemental Materials for Paper 113
Supplemental Materials for Paper 113 August 19, 2012 In this document, we include the following items: 1. Concept definition: the full list of our 101 concepts including actions, scenes, and objects. 2.
More informationFor Creative Minds. The Inuit
For Creative Minds The For Creative Minds educational section may be photocopied or printed from our website by the owner of this book for educational, non-commercial uses. Cross-curricular teaching activities,
More informationA. Reading Comprehension 20 marks. Facts about Seals. Seals bark like a dog, have whiskers like a cat and swim like a fish.
A. Reading Comprehension 20 marks A. 1. Read the following text carefully. Facts about Seals Seals bark like a dog, have whiskers like a cat and swim like a fish. Seals have special qualities that allow
More informationSentiment Analysis of Reviews: Should we analyze writer intentions or reader perceptions?
Sentiment Analysis of Reviews: Should we analyze writer intentions or reader perceptions? Isa Maks and Piek Vossen Vu University, Faculty of Arts De Boelelaan 1105, 1081 HV Amsterdam e.maks@vu.nl, p.vossen@vu.nl
More informationMARINE SCIENCE. Monday 14 May 2018
MARINE SCIENCE Monday 14 May 2018 Entry Task Grab a ChromeBook from the cart. Be sure to grab the number that corresponds to the number on your desk. Log in & go to the following link @ www.kahoot.it Wait
More informationVision: Over Ov view Alan Yuille
Vision: Overview Alan Yuille Why is Vision Hard? Complexity and Ambiguity of Images. Range of Vision Tasks. More 10x10 images 256^100 = 6.7 x 10 ^240 than the total number of images seen by all humans
More informationRunning Head: SENSITIVITY TO TAXNOMIC ASSOCIATIONS
Taxonomic Association Sensitivity 1 Running Head: SENSITIVITY TO TAXNOMIC ASSOCIATIONS Sensitivity to Purely Taxonomic Associations among Young Children Wyatt D Emilia Carnegie Mellon University Taxonomic
More informationDeep Networks and Beyond. Alan Yuille Bloomberg Distinguished Professor Depts. Cognitive Science and Computer Science Johns Hopkins University
Deep Networks and Beyond Alan Yuille Bloomberg Distinguished Professor Depts. Cognitive Science and Computer Science Johns Hopkins University Artificial Intelligence versus Human Intelligence Understanding
More informationCost-aware Pre-training for Multiclass Cost-sensitive Deep Learning
Cost-aware Pre-training for Multiclass Cost-sensitive Deep Learning Yu-An Chung 1 Hsuan-Tien Lin 1 Shao-Wen Yang 2 1 Dept. of Computer Science and Information Engineering National Taiwan University, Taiwan
More informationExtracting Opinion Targets in a Single- and Cross-Domain Setting with Conditional Random Fields
Extracting Opinion Targets in a Single- and Cross-Domain Setting with Conditional Random Fields Niklas Jakob Technische Universität Darmstadt Hochschulstraße 10 64289 Darmstadt, Germany Iryna Gurevych
More informationNon-Fiction Close Reading Passages
Non-Fiction Close Reading Passages Common Core Aligned Ocean Animal Edition 1 st and 2 nd Grade Michelle Arold THANK YOU for downloading! Thank you for downloading! In this packet I have included 4 non-fiction
More informationData Mining in Bioinformatics Day 4: Text Mining
Data Mining in Bioinformatics Day 4: Text Mining Karsten Borgwardt February 25 to March 10 Bioinformatics Group MPIs Tübingen Karsten Borgwardt: Data Mining in Bioinformatics, Page 1 What is text mining?
More informationObject Recognition: Conceptual Issues. Slides adapted from Fei-Fei Li, Rob Fergus, Antonio Torralba, and K. Grauman
Object Recognition: Conceptual Issues Slides adapted from Fei-Fei Li, Rob Fergus, Antonio Torralba, and K. Grauman Issues in recognition The statistical viewpoint Generative vs. discriminative methods
More informationBuilding Blocks. Ready-To-Use Activities to Supplement Any Teaching Situation
Cross-Curricular Grades 3-4 Building Blocks Ready-To-Use Activities to Supplement Any Teaching Situation Concept: Geoffrey R. Lorenz Authors: Judy A. Johnson Bonnie J. Krueger Editor: Barbara S. Meeks
More informationRumor Detection on Twitter with Tree-structured Recursive Neural Networks
1 Rumor Detection on Twitter with Tree-structured Recursive Neural Networks Jing Ma 1, Wei Gao 2, Kam-Fai Wong 1,3 1 The Chinese University of Hong Kong 2 Victoria University of Wellington, New Zealand
More informationEEG Signal Description with Spectral-Envelope- Based Speech Recognition Features for Detection of Neonatal Seizures
EEG Signal Description with Spectral-Envelope- Based Speech Recognition Features for Detection of Neonatal Seizures Temko A., Nadeu C., Marnane W., Boylan G., Lightbody G. presented by Ladislav Rampasek
More informationFlexible, High Performance Convolutional Neural Networks for Image Classification
Flexible, High Performance Convolutional Neural Networks for Image Classification Dan C. Cireşan, Ueli Meier, Jonathan Masci, Luca M. Gambardella, Jürgen Schmidhuber IDSIA, USI and SUPSI Manno-Lugano,
More informationMARINE SCIENCE. Monday 21 May 2018
MARINE SCIENCE Monday 21 May 2018 Entry Task What was one of the major types of sea mammals named in the video? Pinnipeds When was the Marine Mammal Protection Act established? 1972 Agenda Housekeeping
More informationSPICE: Semantic Propositional Image Caption Evaluation
SPICE: Semantic Propositional Image Caption Evaluation Presented to the COCO Consortium, Sept 2016 Peter Anderson1, Basura Fernando1, Mark Johnson2 and Stephen Gould1 1 Australian National University 2
More informationSemantic Pattern Transformation
Semantic Pattern Transformation IKNOW 2013 Peter Teufl, Herbert Leitold, Reinhard Posch peter.teufl@iaik.tugraz.at Our Background Topics Mobile device security Cloud security Security consulting for public
More informationCONSTRAINED SEMI-SUPERVISED LEARNING ATTRIBUTES USING ATTRIBUTES AND COMPARATIVE
CONSTRAINED SEMI-SUPERVISED LEARNING USING ATTRIBUTES AND COMPARATIVE ATTRIBUTES Abhinav Shrivastava, Saurabh Singh, Abhinav Gupta The Robotics Institute Carnegie Mellon University SUPERVISION BIG-DATA
More informationWHAT S HAPPENING SEPTEMBER - NOVEMBER:
WHAT S HAPPENING SEPTEMBER - NOVEMBER: In the fall you will see elephant seals that are too young to take part in the winter breeding season hauling out to rest. They gather together in large groups lying
More informationNon-fiction: Elephant Tales. NOAA Scientists are trying to find out how elephants communicate.
Non-fiction: Elephant Tales Elephant Tales NOAA Scientists are trying to find out how elephants communicate. Shirley, a 4-ton elephant, has something to say. She opens her mouth and gurgles. The nearby
More informationIE Applications. What is Information Extraction? General Techniques. Named Entity Recognition (NER) 11/15/16
What is Information Extraction? Information extraction (IE) is an umbrella term for NLP tasks that involve extracting pieces of information from text and assigning some meaning to the information. Many
More informationElephants. Ending a z visit for thousands of books and materials. Word Count: 693. A Reading A-Z Level N Leveled Book
Elephants A Reading A-Z Level N Leveled Book Word Count: 693 Ending a z visit www.readingo-z.com for thousands of books and materials. www.readinga-z.com Elephants Photo Credits: Front cover: Fritz Kocher/123RF;
More informationWord Sense Disambiguation Using Sense Signatures Automatically Acquired from a Second Language
Word Sense Disambiguation Using Sense Signatures Automatically Acquired from a Second Language Document Number Working Paper 6.12h(b) (3rd Round) Project ref. IST-2001-34460 Project Acronym MEANING Project
More informationA Cooperative Multiagent Architecture for Turkish Sign Tutors
A Cooperative Multiagent Architecture for Turkish Sign Tutors İlker YILDIRIM Department of Computer Engineering Bogazici University, Bebek, 34342, Turkey ilker.yildirim@boun.edu.tr EASSS 2008 1 Outline
More informationElephants. Elephants LEVELED BOOK N. Visit for thousands of books and materials.
Elephants A Reading A Z Level N Leveled Book Word Count: 693 LEVELED BOOK N Elephants Written by Kira Freed Visit www.readinga-z.com for thousands of books and materials. www.readinga-z.com Elephants Photo
More informationWHY STUDY THE MAMMARY GLAND AND MILK SECRETION?
WHY STUDY THE MAMMARY GLAND AND MILK SECRETION? 1. Greater knowledge allows us to alter environment, nutrition, milking procedures, or general management to maximize production WHY STUDY THE MAMMARY GLAND
More informationVILNIAUS MIESTO 3 KLASIŲ MOKINIŲ ANGLŲ KALBOS OLIMPIADOS UŽDUOTYS 2016 M. Student s name, school
TOTAL /70 VILNIAUS MIESTO 3 KLASIŲ MOKINIŲ ANGLŲ KALBOS OLIMPIADOS UŽDUOTYS 2016 M. Student s name, school 1. Read the text and answer the questions. Circle the correct answer. FIRST AIRPLANE TRIP Time:
More informationLesson 3: Researching Individual Whale and Dolphin Species
Cetaceans 4 th Grade Curriculum Lesson 3: Researching Individual Species Page 3-1 Lesson 3: Researching Individual Whale and Dolphin Species Objective: Students will play a modified game of Bingo to learn
More informationIntroduction to Deep Reinforcement Learning and Control
Carnegie Mellon School of Computer Science Deep Reinforcement Learning and Control Introduction to Deep Reinforcement Learning and Control Lecture 1, CMU 10703 Katerina Fragkiadaki Logistics 3 assignments
More informationWhales Dolphins And Seals A Field Guide To The Marine Mammals Of The World
Whales Dolphins And Seals A Field Guide To The Marine Mammals Of The World We have made it easy for you to find a PDF Ebooks without any digging. And by having access to our ebooks online or by storing
More informationReader s Emotion Prediction Based on Partitioned Latent Dirichlet Allocation Model
Reader s Emotion Prediction Based on Partitioned Latent Dirichlet Allocation Model Ruifeng Xu, Chengtian Zou, Jun Xu Key Laboratory of Network Oriented Intelligent Computation, Shenzhen Graduate School,
More information2. Related Work. 1 Throughout this paper we refer to rank as a real-valued score.
Relative Attributes Devi Parih Toyota Technological Institute Chicago (TTIC) dparih@ttic.edu Kristen Grauman University of Texas at Austin grauman@cs.utexas.edu Abstract Human-nameable visual attributes
More informationCategorizing Events using Spatio-Temporal and User Features from Flickr
Categorizing Events using Spatio-Temporal and User Features from Flickr Steven Van Canneyt a,, Steven Schockaert b, Bart Dhoedt a a Ghent University - iminds, Gaston Crommenlaan 8, Ghent, Belgium b Cardiff
More informationIntentional and Incidental Classification Learning in Category Use
Intentional and Incidental Classification Learning in Category Use Michael Romano (mrr2@nyu.edu) Department of Psychology, New York University, 6 Washington Place New York, NY 1000 USA Abstract Traditional
More informationVILNIAUS MIESTO 3 KLASIŲ MOKINIŲ ANGLŲ KALBOS OLIMPIADOS UŽDUOČIŲ ATSAKYMAI 2016 M. Student s name, school
TOTAL /70 VILNIAUS MIESTO 3 KLASIŲ MOKINIŲ ANGLŲ KALBOS OLIMPIADOS UŽDUOČIŲ ATSAKYMAI 2016 M. Student s name, school 1. Read the text and answer the questions. Circle the correct answer. FIRST AIRPLANE
More informationBayesian models of inductive generalization
Bayesian models of inductive generalization Neville E. Sanjana & Joshua B. Tenenbaum Department of Brain and Cognitive Sciences Massachusetts Institute of Technology Cambridge, MA 239 nsanjana, jbt @mit.edu
More informationHacettepe University Department of Computer Science & Engineering
Subject Hacettepe University Department of Computer Science & Engineering Submission Date : 29 May 2013 Deadline : 12 Jun 2013 Language/version Advisor BBM 204 SOFTWARE LABORATORY II EXPERIMENT 5 for section
More informationObject Detection. Honghui Shi IBM Research Columbia
Object Detection Honghui Shi IBM Research 2018.11.27 @ Columbia Outline Problem Evaluation Methods Directions Problem Image classification: Horse (People, Dog, Truck ) Object detection: categories & locations
More informationBy Zara. Asian Elephant
By Zara Asian Elephant Introduction The scientific name for the Asian Elephants is Elephas Maximus. They are currently endangered, and is fastly decreasing because of deforestation and making room for
More informationCharacterizing Concepts in Taxonomy for Entity Recommendations
Wright State University CORE Scholar Browse all Theses and Dissertations Theses and Dissertations 2017 Characterizing Concepts in Taxonomy for Entity Recommendations Siva Kumar Cheekula Wright State University
More informationPARTS OF AN ELEPHANT TRUNK EAR EYE TAIL LEG HOOF TUSK
PARTS OF AN ELEPHANT TRUNK EAR EYE TAIL LEG HOOF TUSK Elephants 1. Match the descriptions to the pictures. 1. 2. 3. A. High up, near tall mountains (Asia). B. Here, it hasn t rained for months (Africa).
More informationA Cooperative Multiagent Architecture for Turkish Sign Tutors
A Cooperative Multiagent Architecture for Turkish Sign Tutors İlker Yıldırım Department of Computer Engineering Boğaziçi University Bebek, 34342, Istanbul, Turkey ilker.yildirim@boun.edu.tr 1 Introduction
More informationText Features. Title Page. Timeline. Table of Contents. Illustrations and Photographs. Index. Captions. Glossary. Diagrams. Subtitle. Labels.
Text Features Title Page Table of Contents Index Glossary Subtitle Heading Subheading Keywords Guide Words Text Box Timeline Illustrations and Photographs Captions Diagrams Labels Map Charts and Graphs
More informationNatural Logic Inference for Emotion Detection
Natural Logic Inference for Emotion Detection Han Ren 1, Yafeng Ren 2, Xia Li 1, Wenhe Feng 1 and Maofu Liu 3 1 Laboratory of Language Engineering and Computing, Guangdong University of Foreign Studies,
More informationFeature selection methods for early predictive biomarker discovery using untargeted metabolomic data
Feature selection methods for early predictive biomarker discovery using untargeted metabolomic data Dhouha Grissa, Mélanie Pétéra, Marion Brandolini, Amedeo Napoli, Blandine Comte and Estelle Pujos-Guillot
More informationEUTHERIAN MAMMALS. Eutherian Mammals are classified into orders on the basis of dentition. It does not involve phylogeny.
EUTHERIAN MAMMALS Eutherian Mammals are classified into orders on the basis of dentition. It does not involve phylogeny. Dinosaurs..? TROPHIC TYPES FOUND AMONG EUTHERIAN MAMMALS Predators Flesh eaters
More informationAn unsupervised machine learning model for discovering latent infectious diseases using social media data
Journal of Biomedical Informatics j o u r n al homepage: www.elsevier.com/locate/yj b i n An unsupervised machine learning model for discovering latent infectious diseases using social media data ARTICLE
More informationWord2Vec and Doc2Vec in Unsupervised Sentiment Analysis of Clinical Discharge Summaries
Word2Vec and Doc2Vec in Unsupervised Sentiment Analysis of Clinical Discharge Summaries Qufei Chen University of Ottawa qchen037@uottawa.ca Marina Sokolova IBDA@Dalhousie University and University of Ottawa
More informationLesson 2: Cetaceans What makes a whale a whale?
Cetaceans 4 th Grade Curriculum Lesson 2: What makes a whale a whale? Page 2-1 Lesson 2: Cetaceans What makes a whale a whale? Objectives: Students will learn about general whale (and dolphin) biology.
More informationThis is the accepted version of this article. To be published as : This is the author version published as:
QUT Digital Repository: http://eprints.qut.edu.au/ This is the author version published as: This is the accepted version of this article. To be published as : This is the author version published as: Chew,
More informationDomain Generalization and Adaptation using Low Rank Exemplar Classifiers
Domain Generalization and Adaptation using Low Rank Exemplar Classifiers 报告人 : 李文 苏黎世联邦理工学院计算机视觉实验室 李文 苏黎世联邦理工学院 9/20/2017 1 Outline Problems Domain Adaptation and Domain Generalization Low Rank Exemplar
More informationVisiting the Zoo s Elephant Exhibit. National Zoo Social Narrative: Elephant Trails
Visiting the Zoo s Elephant Exhibit National Zoo Social Narrative: Elephant Trails There are many animals to visit at the Zoo. Today, I am going to visit the elephant exhibit. There are many places to
More informationWhat is preexisting strength? Predicting free association probabilities, similarity ratings, and cued recall probabilities
Psychonomic Bulletin & Review 2005, 12 (4), 711-719 What is preexisting strength? Predicting free association probabilities, similarity ratings, and cued recall probabilities DOUGLAS L. NELSON University
More informationCount how many butterflies you can spot on the wall. Count how many butterflies you can spot on the floor
Count how many butterflies you can spot on the wall Count how many butterflies you can spot on the floor What is an acquired trait? A trait that an organism acquires or gains over its lifetime. It cannot
More informationConcepts and Categories
Concepts and Categories Functions of Concepts By dividing the world into classes of things to decrease the amount of information we need to learn, perceive, remember, and recognise: cognitive economy They
More informationDiscovering and Understanding Self-harm Images in Social Media. Neil O Hare, MFSec Bucharest, Romania, June 6 th, 2017
Discovering and Understanding Self-harm Images in Social Media Neil O Hare, MFSec 2017. Bucharest, Romania, June 6 th, 2017 Who am I? PhD from Dublin City University, 2007. Multimedia Search Currently
More informationThe Elephant Family MATRIARCH HERDS FEMALES MALES
The Elephant Family Elephants live in family groups called HERDS. Herds are made up of all the mother elephants and their babies. The oldest mother is called the MATRIARCH who is the leader of the herd.
More informationData Mining in Bioinformatics Day 9: String & Text Mining in Bioinformatics
Data Mining in Bioinformatics Day 9: String & Text Mining in Bioinformatics Karsten Borgwardt March 1 to March 12, 2010 Machine Learning & Computational Biology Research Group MPIs Tübingen Karsten Borgwardt:
More informationSVM-based Discriminative Accumulation Scheme for Place Recognition
SVM-based Discriminative Accumulation Scheme for Place Recognition Andrzej Pronobis CAS/CVAP, KTH Stockholm, Sweden pronobis@csc.kth.se Óscar Martínez Mozos AIS, University Of Freiburg Freiburg, Germany
More informationGETTING APPROVED STRENGTH AND BALANCE CLASSES INTO YOUR COMMUNITY
GETTING APPROVED STRENGTH AND BALANCE CLASSES INTO YOUR COMMUNITY WWW.LIVESTRONGER.ORG.NZ 2 GETTING APPROVED You can be part of a national network to help reduce the risk of falls and fall injures for
More informationToday. Conceptual modeling. Principles of Information and Database Management 198:336 Week 3 Feb 7 Matthew Stone. Pictorial view.
Today Principles of Information and Database Management 198:336 Week 3 Feb 7 Matthew Stone Conceptual modeling What concepts are there? How are concepts related? How do you find them? How do you represent
More informationPrinciples of Information and Database Management 198:336 Week 3 Feb 7 Matthew Stone
Principles of Information and Database Management 198:336 Week 3 Feb 7 Matthew Stone Today Conceptual modeling What concepts are there? How are concepts related? How do you find them? How do you represent
More informationReproduction: Cetaceans.
Fish 475: Marine Mammalogy 24 May 2010 Reproduction: Cetaceans. Course website: http://faculty.washington.edu/glennvb/fish475 Text reading reference: Chapter 10 Cetacean reproduction Some general patterns:
More informationTopic 10: Origin of Cetaceans: A Macroevolutionary Case Study
Topic 10: Origin of Cetaceans: A Macroevolutionary Case Study All content and conclusions, except for photos, CR Hardy 1. Fully aquatic, mostly marine mammals Colloquially called dolphins, porpoises, &
More informationClassifying Cognitive Load and Driving Situation with Machine Learning
International Journal of Machine Learning and Computing, Vol. 4, No. 3, June 2014 Classifying Cognitive Load and Driving Situation with Machine Learning Yutaka Yoshida, Hayato Ohwada, Fumio Mizoguchi,
More informationAsthma Surveillance Using Social Media Data
Asthma Surveillance Using Social Media Data Wenli Zhang 1, Sudha Ram 1, Mark Burkart 2, Max Williams 2, and Yolande Pengetnze 2 University of Arizona 1, PCCI-Parkland Center for Clinical Innovation 2 {wenlizhang,
More informationWikipedia-Based Automatic Diagnosis Prediction in Clinical Decision Support Systems
Wikipedia-Based Automatic Diagnosis Prediction in Clinical Decision Support Systems Danchen Zhang 1, Daqing He 1, Sanqiang Zhao 1, Lei Li 1 School of Information Sciences, University of Pittsburgh, USA
More informationInductive Reasoning. Induction, Analogy, Metaphor & Blending. Abduction Schema. Abduction or Specific Induction
Inductive Reasoning Induction, Analogy, Metaphor & Blending How observations and beliefs support other beliefs In some ways, opposite of deductive reasoning P Q Q Therefore: P is more likely Inherently
More informationCSE 258 Lecture 2. Web Mining and Recommender Systems. Supervised learning Regression
CSE 258 Lecture 2 Web Mining and Recommender Systems Supervised learning Regression Supervised versus unsupervised learning Learning approaches attempt to model data in order to solve a problem Unsupervised
More informationSupplementary Material: Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning
Supplementary Material: Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning Soravit Changpinyo U. of Southern California Los Angeles, CA schangpi@usc.edu Wei-Lun Chao U. of Southern California
More informationClass Mammalia. Biology ~ Advanced Studies
Class Mammalia Biology ~ Advanced Studies DOL 60-64 VI. Class Mammalia A. General characteristics 1. Hair on bodies 2. Females have mammary glands a. nourish young with milk 3. Breathe air with lungs 4.
More information2. What happens to the bunny population if a friend is never added? What happens when you add a friend?
Name: Natural Selection Simulation at PHET http://phet.colorado.edu/simulations/sims.php?sim=natural_selection (link is also posted on Evolution Unit page at www.biologybynapier.com ) Exploration: Access
More informationModule 10b--Operant and Cognitive Approaches
Module 10b--Operant and Cognitive Approaches Student: 1. Classical conditioning involves behavior and its consequences. 2. According to the law of effect, behavior that is followed by positive consequences
More informationNon Surgical Hip Therapy Athletic Hip Injury: Therapist Information
Non Surgical Hip Therapy Athletic Hip Injury: Therapist Information Please read entire protocol prior to initiating therapy Please note: Individual hip injuries vary widely. This therapy protocol should
More informationLearning Multifunctional Binary Codes for Both Category and Attribute Oriented Retrieval Tasks
Learning Multifunctional Binary Codes for Both Category and Attribute Oriented Retrieval Tasks Haomiao Liu 1,2, Ruiping Wang 1,2,3, Shiguang Shan 1,2,3, Xilin Chen 1,2,3 1 Key Laboratory of Intelligent
More informationCopyright by the monkey in the pic
Copyright by the monkey in the pic disclaimer: if you find the content of this presentation unpleasant or insulting, please realize that you have a beef with reality, not me. Don't shoot the messenger.
More informationSentiment Classification of Chinese Reviews in Different Domain: A Comparative Study
Sentiment Classification of Chinese Reviews in Different Domain: A Comparative Study Qingqing Zhou and Chengzhi Zhang ( ) Department of Information Management, Nanjing University of Science and Technology,
More informationEstimating scene typicality from human ratings and image features
Estimating scene typicality from human ratings and image features Krista A. Ehinger (kehinger@mit.edu) Department of Brain & Cognitive Sciences, MIT, 77 Massachusetts Ave. Jianxiong Xiao (jxiao@csail.mit.edu)
More informationHierarchical Convolutional Features for Visual Tracking
Hierarchical Convolutional Features for Visual Tracking Chao Ma Jia-Bin Huang Xiaokang Yang Ming-Husan Yang SJTU UIUC SJTU UC Merced ICCV 2015 Background Given the initial state (position and scale), estimate
More informationSocial Data and College Statistics
Social Data and College Statistics Sean Choi Stanford University yo2seol@stanford.edu Elena Grewal Stanford University etgrewal@stanford.edu Kai Wen Stanford University kaiwen@stanford.edu ABSTRACT We
More informationChapter 09 Marine Reptiles, Birds, and Mammals
Chapter 09 Marine Reptiles, Birds, and Mammals Multiple Choice Questions 1. Marine amphibians: A. Do not exist at all B. Are gill-breathers C. Are fish-like D. Include only tropical species E. Are oviparous
More informationINCEpTION Workshop: Preference Learning
INCEpTION Workshop: Preference Learning Outine of tak: Chaenges for efficient text annotation Introducing to preference earning Our preference earning approach: GPPL GPPL Experiments with argument convincingness
More informationTAKS TEST PREPARATION FOR MATH IN SCIENCE
Name Date Class CHAPTER TAKS TEST PREPARATION FOR MATH IN SCIENCE Math Mini-Test Section 1 1 There are about 16,000 hair cells inside the cochlea of a person s ear. If 30% of those hair cells are damaged,
More informationIntroduction. Help your students learn how to learn!
Introduction Help your students learn how to learn! Lay a strong foundation in listening skills, the ability to follow directions, and in the ability to remember what one sees and hears important skills
More informationThe Role of Face Parts in Gender Recognition
The Role of Face Parts in Gender Recognition Yasmina Andreu Ramón A. Mollineda Pattern Analysis and Learning Section Computer Vision Group University Jaume I of Castellón (Spain) Y. Andreu, R.A. Mollineda
More information