GIANT: Geo-Informative Attributes for Location Recognition and Exploration

Similar documents
Shu Kong. Department of Computer Science, UC Irvine

Shu Kong. Department of Computer Science, UC Irvine

Annotation and Retrieval System Using Confabulation Model for ImageCLEF2011 Photo Annotation

Beyond R-CNN detection: Learning to Merge Contextual Attribute

Part 1: Bag-of-words models. by Li Fei-Fei (Princeton)

A Vision-based Affective Computing System. Jieyu Zhao Ningbo University, China

Motivation: Attention: Focusing on specific parts of the input. Inspired by neuroscience.

Data Mining in Bioinformatics Day 4: Text Mining

Predicting Sleep Using Consumer Wearable Sensing Devices

Automatic Diagnosis of Ovarian Carcinomas via Sparse Multiresolution Tissue Representation

Statistics 202: Data Mining. c Jonathan Taylor. Final review Based in part on slides from textbook, slides of Susan Holmes.

Incorporating Privileged Genetic Information for Fundus Image Based Glaucoma Detection

Effective Diagnosis of Alzheimer s Disease by means of Association Rules

Agent-Based Models. Maksudul Alam, Wei Wang

Gene Selection for Tumor Classification Using Microarray Gene Expression Data

Inferring Clinical Correlations from EEG Reports with Deep Neural Learning

arxiv: v1 [stat.ml] 23 Jan 2017

arxiv: v1 [cs.lg] 4 Feb 2019

Causal Knowledge Modeling for Traditional Chinese Medicine using OWL 2

MEM BASED BRAIN IMAGE SEGMENTATION AND CLASSIFICATION USING SVM

CONSTRAINED SEMI-SUPERVISED LEARNING ATTRIBUTES USING ATTRIBUTES AND COMPARATIVE

Generalized additive model for disease risk prediction

Memory-Augmented Active Deep Learning for Identifying Relations Between Distant Medical Concepts in Electroencephalography Reports

Class discovery in Gene Expression Data: Characterizing Splits by Support Vector Machines

Automatic Hemorrhage Classification System Based On Svm Classifier

Bootstrapped Integrative Hypothesis Test, COPD-Lung Cancer Differentiation, and Joint mirnas Biomarkers

Data Analysis with SPSS

Recognizing Scenes by Simulating Implied Social Interaction Networks

VIDEO SALIENCY INCORPORATING SPATIOTEMPORAL CUES AND UNCERTAINTY WEIGHTING

A Predictive Chronological Model of Multiple Clinical Observations T R A V I S G O O D W I N A N D S A N D A M. H A R A B A G I U

A Novel Capsule Neural Network Based Model For Drowsiness Detection Using Electroencephalography Signals

Visual Saliency Based on Multiscale Deep Features Supplementary Material

Bayesian Networks Representation. Machine Learning 10701/15781 Carlos Guestrin Carnegie Mellon University

Discovering Symptom-herb Relationship by Exploiting SHT Topic Model

May All Your Wishes Come True: A Study of Wishes and How to Recognize Them

Efficacy of the Extended Principal Orthogonal Decomposition Method on DNA Microarray Data in Cancer Detection

Object Detectors Emerge in Deep Scene CNNs

Putting Context into. Vision. September 15, Derek Hoiem

Action Recognition. Computer Vision Jia-Bin Huang, Virginia Tech. Many slides from D. Hoiem

POC Brain Tumor Segmentation. vlife Use Case

Video Saliency Detection via Dynamic Consistent Spatio- Temporal Attention Modelling

Learning Spatiotemporal Gaps between Where We Look and What We Focus on

Large-scale Histopathology Image Analysis for Colon Cancer on Azure

Automated Volumetric Cardiac Ultrasound Analysis

B657: Final Project Report Holistically-Nested Edge Detection

Computational Cognitive Science

Improving the Interpretability of DEMUD on Image Data Sets

Domain Generalization and Adaptation using Low Rank Exemplar Classifiers

Detection of Cognitive States from fmri data using Machine Learning Techniques

UNDERSTANDING THE EMOTIONS BEHIND SOCIAL IMAGES: INFERRING WITH USER DEMOGRAPHICS

Heterogeneous Data Mining for Brain Disorder Identification. Bokai Cao 04/07/2015

ITERATIVELY TRAINING CLASSIFIERS FOR CIRCULATING TUMOR CELL DETECTION

Personalized Travel Recommendation by Mining People Attributes from Community-Contributed Photos

Jia Jia Tsinghua University 26/09/2017

Fine-Grained Image Classification Using Color Exemplar Classifiers

Using Information From the Target Language to Improve Crosslingual Text Classification

Hierarchical Convolutional Features for Visual Tracking

Fine-Grained Image Classification Using Color Exemplar Classifiers

Spatial Cognition for Mobile Robots: A Hierarchical Probabilistic Concept- Oriented Representation of Space

Medical Image Analysis

Improved Intelligent Classification Technique Based On Support Vector Machines

Does daily travel pattern disclose people s preference?

EECS 433 Statistical Pattern Recognition

Reader s Emotion Prediction Based on Partitioned Latent Dirichlet Allocation Model

AClass: A Simple, Online Probabilistic Classifier. Vikash K. Mansinghka Computational Cognitive Science Group MIT BCS/CSAIL

A Comparison of Collaborative Filtering Methods for Medication Reconciliation

Rating prediction on Amazon Fine Foods Reviews

Realization of Visual Representation Task on a Humanoid Robot

Asthma Surveillance Using Social Media Data

FEATURE EXTRACTION USING GAZE OF PARTICIPANTS FOR CLASSIFYING GENDER OF PEDESTRIANS IN IMAGES

Colon cancer subtypes from gene expression data

Automated Tessellated Fundus Detection in Color Fundus Images

Event Classification and Relationship Labeling in Affiliation Networks

A micropower support vector machine based seizure detection architecture for embedded medical devices

Design of Palm Acupuncture Points Indicator

Semantic Pattern Transformation

Chapter 1. Introduction

Mike Davies Director, Neuromorphic Computing Lab Intel Labs

Confluence: Conformity Influence in Large Social Networks

DEEP LEARNING BASED VISION-TO-LANGUAGE APPLICATIONS: CAPTIONING OF PHOTO STREAMS, VIDEOS, AND ONLINE POSTS

I. INTRODUCTION III. OVERALL DESIGN

ABSTRACT I. INTRODUCTION. Mohd Thousif Ahemad TSKC Faculty Nagarjuna Govt. College(A) Nalgonda, Telangana, India

Cervix Cancer Classification using Colposcopy Images by Deep Learning Method

1. INTRODUCTION. Vision based Multi-feature HGR Algorithms for HCI using ISL Page 1

Hybrid HMM and HCRF model for sequence classification

Rumor Detection on Twitter with Tree-structured Recursive Neural Networks

Scenes Categorization based on Appears Objects Probability

Informative Gene Selection for Leukemia Cancer Using Weighted K-Means Clustering

BREAST CANCER EPIDEMIOLOGY MODEL:

Development of Soft-Computing techniques capable of diagnosing Alzheimer s Disease in its pre-clinical stage combining MRI and FDG-PET images.

Figure 1: MRI Scanning [2]

A NOVEL CLASSIFICATION MODEL FOR ANALYSIS OF A CRIME USING NAÏVE BYES AND KNN IN DATA MINING

Analyzing Spammers Social Networks for Fun and Profit

What Helps Where And Why? Semantic Relatedness for Knowledge Transfer

Convolutional Neural Networks (CNN)

ECG Beat Recognition using Principal Components Analysis and Artificial Neural Network

FUNNEL: Automatic Mining of Spatially Coevolving Epidemics

Categorizing Events using Spatio-Temporal and User Features from Flickr

Predicting Seizures in Intracranial EEG Recordings

Transcription:

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 Família, Barcelona

And how about this one? Gothic Quarter, Barcelona? Can computer localize this streetview photo & tell what this is about?

UGC photos is flourishing 8 billion images 250 billion images 16 billion images 200 million images a day 150 billion images 350 million images a day

Geo-location is available San Francisco London Chicago Paris Berlin New York Barcelona Istanbul Beijing Tokyo 8 billion images 16 billion images 200 million images a day Cairo Hong Kong Taipei Singapore Sao Paulo Sydney

when photos meet geo-location

Barcelona

Discriminative Regions

Geo-informative Attributes Discriminative Region Semantic Interpretation Roofs rooftop Roofs Eaves Windows colorful Balcony

Geo-informative Attributes Geographically discriminative Differentiate this location from others Representative Occur frequently in this location Semantically interpretable

Our Goal: Given a large geo-tagged image dataset, we automatically discover geo-informative attributes towards location recognition and exploration

Motivation Related Work Outline Our Solution Geo-informative Attribute Discovery Geo-informative Attribute Interpretation Evaluation Conclusion

Geographical Location Estimation Landmark recognition Matching; classification model [Li et al ICCV 2009]; [Kalogerakis et al, ICCV 2009]; [Zheng et al, CVPR2009];[Liu et al, MM2012] Not applicable to general location recognition Location recognition High visual diversity; intra-class variance Scene matching; classification models [IM2GPS, CVPR 2008]; [Crandall et al, WWW 2009]; [G.Friedland et al. MM2011]; Limited scalability; black-box mode

Visual Attributes Visual Attributes Learning Machine detectable; semantically meaningful Mid-level representation [Singh et al. ECCV2014];[Doersch et al. Siggraph 2012] [Farhadi et al, CVPR2009];[Parikh ICCV2011] Geographical visual attribute mining WHAT MAKES PARIS LOOK LIKE PARIS? [Doersch et al. Siggraph 2012] Discover visual elements that characterize a city Discriminative clustering Independently mine the visual patches No text interpretation

Outline Motivation Problem Related Work Our Solution Geo-informative Attribute Discovery Geo-informative Attribute Interpretation Evaluation Conclusion

Solution Geo-informative Attribute Discovery Discriminative Region Detection & Clustering Tag-Region Learning & Interpretation Discriminative Representative Semantically Understandable Geo-informative Attributes Geo-informative Attribute Interpretation

Outline Motivation Problem Related Work Our Solution Geo-informative Attribute Discovery Geo-informative Attribute Interpretation Evaluation Conclusion

Geo-informative Attribute Discovery Input Output Neighbor Voting Region-based Latent SVM Meanshift Clustering Geo-tagged Photos Geo-discriminative Photo Selection Geo-discriminative Regions Detection Geo-informative Attributes

Step 1: Non-discriminative Photo Filtering Nearest neighbor voting Photo Nearest neighbors Barcelona Not Barcelona

Step 2: Discriminative Region Selection Region Generation Hierarchically grid-based segmentation

Region-based Latent SVM Combine region feature, region discriminative capability, location label in a principled model Core idea: Each region is associated with a binary latent variable z indicating whether it s geo-informative or not Learn a function f w : X L R Region feature vector Latent variable Location label w T Φ x, z, l = Feature vs. Latent Variable Potential N i=1 + α T φ(x i, z i + N i=1 β T φ(z i, l γ T ψ(z i, z j, x i, x j (i,j E Latent variable vs. location label Potential Latent variable vs. Latent variable Potential

Region-based Latent SVM Feature vs. Latent Variable Potential l α T φ(x i, z i = α T b 1(z i = b x i b Z Latent Variable vs. Location Label Potential z k zi z j z t β T φ(z i, l = β b,c 1(l = b 1(z i = c b K c Z Latent Variable vs. Latent Variable Potential x k x i x j x t γ T ψ(z i, z j, x i, x j = b Z c Z γ b,c p(x i, x j 1(z i = b 1(z j = c p(x i, x j = e x i x j

Region-based Latent SVM Model Learning Holding latent variables z fixed, learn parameters w to minimize the objective Non-convex bundle optimization Model Inference Holding parameters w fixed, search the best variable configuration such that w T Φ(x, z, l is maximized Loopy belief propagation M 1 min w,ξ 0 2 w 2 + C 1 ξ i i=1 s. t. max z wt Φ(x i, z, l i max z wt Φ(x i, z, l Δ(l i, l ξ i, l L z = argmax z wt Φ(x i, z, l i )

Step 3: Geo-informative Attribute Generation Meanshift clustering Geo-informative Attributes Discriminative Region

City-scale Location Recognition Region-based Latent SVM Directly apply the RLSVM for a new given photo x GIANT: geo-informative attribute-based recognition Locality-constrained coding over the attribute vocabulary D Discriminative classifier l = arg max{max l z min S N n=1 y n D n s n 2 s. t.1 t s n = 1 w T Φ(x t, z, l

Outline Motivation Problem Related Work Our Solution Geo-informative Attribute Discovery Geo-informative Attribute Interpretation Evaluation Conclusion

Geo-informative Attribute Interpretation Tag-region Relatedness Learning Discriminative SVM Classifiers Discriminative Classifiers Scoring Semantic tags for Attributes

Tag-Region Relatedness Learning Measure the relatedness between the tag and regions Exploit the co-occurrence relationships between tags and photos Learn a bundle of discriminative SVM classifiers for each tag architecture 'architecture' Clustering SVM Learning

Attribute Interpretation Discriminative Classifiers Scoring Score each region with all SVMs Compute and sort tag scores Select the top n tags 'architecture' 'espanya' 'jugendstil architecture: 0.75 espanya: 0.45 jugendstil: 0.4 architecture: 0.8 espanya: 0.55 jugendstil: 0.36 architecture: 0.7 espanya: 0.5 jugendstil: 0.42 architecture: 0.6 espanya: 0.5 jugendstil: 0.42 architecture: 2.85 espanya: 2 jugendstil: 1.6

Motivation Related Work Outline Our Solution Geo-informative Attribute Discovery Geo-informative Attribute Interpretation Evaluation Conclusion

San Francisco Chicago New York London Paris Barcelona Hong Kong Tokyo Taipei Singapore Sao Paulo GoogleStreetView Sydney

London Paris Barcelona Berlin Istanbul Beijing Cairo Flickr City

Dataset Dataset GoogleStreetView Flickr #City 12 7 #Photo per city Nearly 10,000 2,000 ~ 3,000 #Total photo 139,840 13,503

Experiment Setup Dataset Randomly sample near 500 photos for each city GoogleStreetView: 6,111; Flickr city: 3,501; 100 photos per city for training, the rest for testing Compared Methods knn: Scene-matching method [J. Hays et al., CVPR 2008] LF+SVM : Low-level features combined with SVM [J. Zhu et al., MM 2008] BOVW+SVM: Bag of words features combined with SVM [J. Wang et al., CVPR 2010] DRLR: Discriminative region selection at the patch-level [C. Doersch et al., SIGGRAPH 2012]

Performance Comparison map results of recognition algorithms on GoogleStreetView

Performance Comparison map results of recognition algorithms on Flickr City Geo-informative attributes are of great value for location recognition.

Discriminative Region Detection Barcelona Hong Kong Paris Chicago London Istanbul

Cairo Berlin Istanbul Beijing Barcelona London Paris Singapore Chicago HongKong NYC Sanfransisco Sanpaulo Sydney Taipei Tokyo

Barcelona antonigaudi towers sebastianniedlich sagradafamilia nativity catalonia arquitectura espanya jugendstil artnouveau katalonien catalonia catalunya antoniogaudi antonigaudi sagradafamilia cathedral catholic

London Paris Attribute Interpretation Berlin Beijing Istanbul Cairo

Application: City Exploration Barcelona Sagradafamilia Antonigaudi sebastianniedlich catalonia arquitectura espanya Barcelona

Outline Motivation Problem Related Work Our Solution Geo-informative Attribute Discovery Geo-informative Attribute Interpretation Evaluation Conclusion

Conclusion Automatically discover geo-informative attributes Property: discriminative &representative& semantically interpretable Solution: Region-based latent SVM model for attribute detection Exploiting user-contributed tags for attribute interpretation Geo-informative attributes Be effective in general location recognition Visually characterize a city, enabling practical applications

Future Work The world is perceived by Visual + Semantic Geospatial visual + semantic knowledge mining Geo computing for location-based services Travel assistant system based on graph search Sensing Serving Geo Computing Mining Understanding

Thank you!