Style-aware Mid-level Representation for Discovering Visual Connections in Space and Time

Similar documents
CS4495/6495 Introduction to Computer Vision. 8C-L3 Support Vector Machines

Predictive analysis on Multivariate, Time Series datasets using Shapelets

What is semi-supervised learning?

Holdout and Cross-Validation Methods Overfitting Avoidance

Loss Functions and Optimization. Lecture 3-1

Introduction to Machine Learning

Machine Learning Basics

Photo Tourism and im2gps: 3D Reconstruction and Geolocation of Internet Photo Collections Part II

Loss Functions and Optimization. Lecture 3-1

Hierarchical models for the rainfall forecast DATA MINING APPROACH

c 4, < y 2, 1 0, otherwise,

Support Vector Machines

Iterative Laplacian Score for Feature Selection

Predicting flight on-time performance

CSE 417T: Introduction to Machine Learning. Final Review. Henry Chai 12/4/18

Prediction of Citations for Academic Papers

Nearest Neighbors Methods for Support Vector Machines

Discriminative part-based models. Many slides based on P. Felzenszwalb

DETECTING HUMAN ACTIVITIES IN THE ARCTIC OCEAN BY CONSTRUCTING AND ANALYZING SUPER-RESOLUTION IMAGES FROM MODIS DATA INTRODUCTION

Kronecker Decomposition for Image Classification

CS145: INTRODUCTION TO DATA MINING

ECS289: Scalable Machine Learning

ECS289: Scalable Machine Learning

The state of the art and beyond

Graph-Based Anomaly Detection with Soft Harmonic Functions

Nonlinear Classification

Modeling Complex Temporal Composition of Actionlets for Activity Prediction

Kernel Density Topic Models: Visual Topics Without Visual Words

Deep Feedforward Networks. Sargur N. Srihari

Activity Mining in Sensor Networks

Text Mining. Dr. Yanjun Li. Associate Professor. Department of Computer and Information Sciences Fordham University

An Introduction to Machine Learning

Information Extraction from Text

Instance-based Learning CE-717: Machine Learning Sharif University of Technology. M. Soleymani Fall 2016

Linear and Logistic Regression. Dr. Xiaowei Huang

Machine learning comes from Bayesian decision theory in statistics. There we want to minimize the expected value of the loss function.

From Binary to Multiclass Classification. CS 6961: Structured Prediction Spring 2018

Discriminative Learning and Big Data

Compressed Fisher vectors for LSVR

Supplemental Material: Probability Models for Open Set Recognition

Pivot Selection Techniques

CS 231A Section 1: Linear Algebra & Probability Review

CS 231A Section 1: Linear Algebra & Probability Review. Kevin Tang

2MHR. Protein structure classification is important because it organizes the protein structure universe that is independent of sequence similarity.

Pattern Recognition and Machine Learning. Perceptrons and Support Vector machines

Boosting: Algorithms and Applications

Listwise Approach to Learning to Rank Theory and Algorithm

Clustering with k-means and Gaussian mixture distributions

ECE521 Lectures 9 Fully Connected Neural Networks

Learning from Labeled and Unlabeled Data: Semi-supervised Learning and Ranking p. 1/31

CLUe Training An Introduction to Machine Learning in R with an example from handwritten digit recognition

Statistical Machine Learning Theory. From Multi-class Classification to Structured Output Prediction. Hisashi Kashima.

1 [15 points] Frequent Itemsets Generation With Map-Reduce

SUPERVISED LEARNING: INTRODUCTION TO CLASSIFICATION

Multiple Similarities Based Kernel Subspace Learning for Image Classification

Statistical Machine Learning Theory. From Multi-class Classification to Structured Output Prediction. Hisashi Kashima.

Final Exam, Machine Learning, Spring 2009

Metric Embedding of Task-Specific Similarity. joint work with Trevor Darrell (MIT)

CSE 546 Final Exam, Autumn 2013

10/05/2016. Computational Methods for Data Analysis. Massimo Poesio SUPPORT VECTOR MACHINES. Support Vector Machines Linear classifiers

UAPD: Predicting Urban Anomalies from Spatial-Temporal Data

Latent Geographic Feature Extraction from Social Media

An Optimized Interestingness Hotspot Discovery Framework for Large Gridded Spatio-temporal Datasets

Abstract. 1 Introduction. Cointerpretation of Flow Rate-Pressure-Temperature Data from Permanent Downhole Gauges. Deconvolution. Breakpoint detection

Neural networks and optimization

Temporal and spatial approaches for land cover classification.

Global Scene Representations. Tilke Judd

Urban land use information retrieval based on scene classification of Google Street View images

Machine Learning Concepts in Chemoinformatics

Unsupervised Learning of Discrimina4ve Rela4ve Visual A9ributes

Introduction to Machine Learning

Jeff Howbert Introduction to Machine Learning Winter

Kaggle.

Anomaly (outlier) detection. Huiping Cao, Anomaly 1

6.869 Advances in Computer Vision. Prof. Bill Freeman March 1, 2005

DP Project Development Pvt. Ltd.

CSE446: non-parametric methods Spring 2017

HYPERGRAPH BASED SEMI-SUPERVISED LEARNING ALGORITHMS APPLIED TO SPEECH RECOGNITION PROBLEM: A NOVEL APPROACH

CS325 Artificial Intelligence Chs. 18 & 4 Supervised Machine Learning (cont)

Clustering with k-means and Gaussian mixture distributions

Predictive Analytics on Accident Data Using Rule Based and Discriminative Classifiers

6.036 midterm review. Wednesday, March 18, 15

Discriminative Direction for Kernel Classifiers

Machine Learning. Nonparametric Methods. Space of ML Problems. Todo. Histograms. Instance-Based Learning (aka non-parametric methods)

CS6220: DATA MINING TECHNIQUES

Introduction to Machine Learning. PCA and Spectral Clustering. Introduction to Machine Learning, Slides: Eran Halperin

Mining Classification Knowledge

Machine Learning on temporal data

20 Unsupervised Learning and Principal Components Analysis (PCA)

ECE662: Pattern Recognition and Decision Making Processes: HW TWO

Support Vector Regression (SVR) Descriptions of SVR in this discussion follow that in Refs. (2, 6, 7, 8, 9). The literature

CS 6375 Machine Learning

Classification of Hand-Written Digits Using Scattering Convolutional Network

Gene Expression Data Classification with Revised Kernel Partial Least Squares Algorithm

How to learn from very few examples?

Deep Feedforward Networks

6.867 Machine learning

Mining of Massive Datasets Jure Leskovec, AnandRajaraman, Jeff Ullman Stanford University

Automatic detection and of dipoles in large area SQUID magnetometry

AN INTEGRATED METHOD FOR FOREST CANOPY COVER MAPPING USING LANDSAT ETM+ IMAGERY INTRODUCTION

Transcription:

Style-aware Mid-level Representation for Discovering Visual Connections in Space and Time Experiment presentation for CS3710:Visual Recognition Presenter: Zitao Liu University of Pittsburgh ztliu@cs.pitt.edu March 3, 2015 Zitao Liu (University of Pittsburgh) CS3710:Visual Recognition March 3, 2015 1 / 17

Goal Goal: Discover connections. Zitao Liu (University of Pittsburgh) CS3710:Visual Recognition March 3, 2015 2 / 17

Goal Goal: Discover connections between recurring mid-level visual elements. Zitao Liu (University of Pittsburgh) CS3710:Visual Recognition March 3, 2015 3 / 17

Goal Goal: Discover connections between recurring mid-level visual elements in historic (temporal) and geographic (spatial) image collections. Zitao Liu (University of Pittsburgh) CS3710:Visual Recognition March 3, 2015 4 / 17

Goal Goal: Discover connections between recurring mid-level visual elements in historic (temporal) and geographic (spatial) image collections, and attempts to capture the underlying visual style. Zitao Liu (University of Pittsburgh) CS3710:Visual Recognition March 3, 2015 5 / 17

Visual Style Visual style: Appearance variations of the same visual element due to change in time or location. Zitao Liu (University of Pittsburgh) CS3710:Visual Recognition March 3, 2015 6 / 17

The Proposed Method Three steps: 1 Mining style-sensitive visual elements 2 Establishing correspondences 3 Training style-aware regression models Zitao Liu (University of Pittsburgh) CS3710:Visual Recognition March 3, 2015 7 / 17

Experiment Data: 1 Three datasets are used in the paper and one dataset (CarDb) can be downloaded from the author s website. 2 CarDb: 2.96GB with 13,473 photos. (10130 for training and 3343 for testing) 3 CarDb contains cars made in 1920-1999 crawled from www.cardatabase.net Zitao Liu (University of Pittsburgh) CS3710:Visual Recognition March 3, 2015 8 / 17

Experiment External packages: 1 VOC: extracting features. 2 LibSVM: making classification and regression. Zitao Liu (University of Pittsburgh) CS3710:Visual Recognition March 3, 2015 9 / 17

Experiment Preprocessing: CarDb 1920 1930 1940 1950 1960 1970 1980 1990 8 decades in total. Zitao Liu (University of Pittsburgh) CS3710:Visual Recognition March 3, 2015 10 / 17

Experiment - Step1 Goal: find visual elements whose appearance correlates with the date (label). What code does: 1 Select query images from each category. 2 Random sample patches with various scales and locations from each query image. 3 Each patch is represented by a histogram of gradients (HOG). Zitao Liu (University of Pittsburgh) CS3710:Visual Recognition March 3, 2015 11 / 17

Experiment - Step1 Goal: find visual elements whose appearance correlates with the date (label). What code does: 1 Find top N(N = 50) nearest neighbor patches in the database. foreach query decade image subsets(querydec) foreach query image in querydec foreach match decade image subsets(matchdec) foreach image in matchdec(i) foreach detector in image I More than 10K images. Zitao Liu (University of Pittsburgh) CS3710:Visual Recognition March 3, 2015 12 / 17

Experiment - Step1 Goal: find visual elements whose appearance correlates with the date (label). What code does: 1 For each cluster, compute the temporal distribution of labels. (compute entropy based on year distribution) 2 Find good clusters with peaky distributions 3 Rank good clusters and select top M (M = 80) as the discovered style-sensitive visual elements. Peaky examples: 1920 1, 1930 1, 1930 6, 1940 2, 1960 1, 1960 2, 1960 6, 1960 12, etc. Flat examples: 1930 9, 1930 10, 1940 6, etc. Zitao Liu (University of Pittsburgh) CS3710:Visual Recognition March 3, 2015 13 / 17

Experiment - Step2 Goal: model the change in style of the same visual element over the entire label space. What code does: 1 Train a linear SVM with initial cluster images. Negative data are sampled from random Flickr images. 2 Run the learned SVM on a new subset of the data that slightly broader range in label space. 3 Keep the most confident prediction example and continue. Cross-validation is used in each step of the incremental revision. Zitao Liu (University of Pittsburgh) CS3710:Visual Recognition March 3, 2015 14 / 17

Experiment - Step2 Good positive training examples. 1928 1925 1929 1927 1928 1940 1939 1940 1937 1938 1941 1941 1941 1941 1947 1959 1960 1955 1951 1953 1969 1970 1967 1965 1967 1972 1977 1979 1972 1977 1984 1989 1981 1989 1987 1991 1995 1991 1992 1991 Zitao Liu (University of Pittsburgh) CS3710:Visual Recognition March 3, 2015 15 / 17

Experiment - Step3 Goal: Prediction. What code does: 1 Train a SVM with RBF kernels on the correspondences obtained from Step 2. 2 Each training example is weighted by a transformed detection score. Keep in mind: we have 8 decades; 10 clusters for each decades; 50 neighbors in each cluster. Zitao Liu (University of Pittsburgh) CS3710:Visual Recognition March 3, 2015 16 / 17

Thank you! Q & A Zitao Liu (University of Pittsburgh) CS3710:Visual Recognition March 3, 2015 17 / 17

2024 © sciencedocbox.com Privacy Policy | Terms of Service | Feedback