Introduction Problem: Classifying attributes and actions in still images Model:  Collection of part templates  Specific scale space locations (human.

Slides:



Advertisements
Similar presentations
Object Recognition Using Locality-Sensitive Hashing of Shape Contexts Andrea Frome, Jitendra Malik Presented by Ilias Apostolopoulos.
Advertisements

Overview of SPM p <0.05 Statistical parametric map (SPM)
Human Detection Phanindra Varma. Detection -- Overview  Human detection in static images is based on the HOG (Histogram of Oriented Gradients) encoding.
Human Action Recognition by Learning Bases of Action Attributes and Parts Bangpeng Yao, Xiaoye Jiang, Aditya Khosla, Andy Lai Lin, Leonidas Guibas, and.
Context-based object-class recognition and retrieval by generalized correlograms by J. Amores, N. Sebe and P. Radeva Discussion led by Qi An Duke University.
Three things everyone should know to improve object retrieval
Foreground Focus: Finding Meaningful Features in Unlabeled Images Yong Jae Lee and Kristen Grauman University of Texas at Austin.
Olivier Duchenne , Armand Joulin , Jean Ponce Willow Lab , ICCV2011.
Carolina Galleguillos, Brian McFee, Serge Belongie, Gert Lanckriet Computer Science and Engineering Department Electrical and Computer Engineering Department.
Multi-layer Orthogonal Codebook for Image Classification Presented by Xia Li.
MIT CSAIL Vision interfaces Approximate Correspondences in High Dimensions Kristen Grauman* Trevor Darrell MIT CSAIL (*) UT Austin…
CS395: Visual Recognition Spatial Pyramid Matching Heath Vinicombe The University of Texas at Austin 21 st September 2012.
LPP-HOG: A New Local Image Descriptor for Fast Human Detection Andy Qing Jun Wang and Ru Bo Zhang IEEE International Symposium.
Activity Recognition Aneeq Zia. Agenda What is activity recognition Typical methods used for action recognition “Evaluation of local spatio-temporal features.
Intro to DPM By Zhangliliang. Outline Intuition Introduction to DPM Model Inference(matching) Training latent SVM Training Procedure Initialization Post-processing.
Human Action Recognition by Learning Bases of Action Attributes and Parts.
Addressing the Medical Image Annotation Task using visual words representation Uri Avni, Tel Aviv University, Israel Hayit GreenspanTel Aviv University,
Global spatial layout: spatial pyramid matching Spatial weighting the features Beyond bags of features: Adding spatial information.
Stephan Gammeter, Lukas Bossard, Till Quack, Luc Van Gool.
On the Relationship between Visual Attributes and Convolutional Networks Paper ID - 52.
1 Image Recognition - I. Global appearance patterns Slides by K. Grauman, B. Leibe.
Reduced Support Vector Machine
Multi-view stereo Many slides adapted from S. Seitz.
(1) Feature-point matching by D.J.Duff for CompVis Online: Feature Point Matching Detection, Extraction.
1 Accurate Object Detection with Joint Classification- Regression Random Forests Presenter ByungIn Yoo CS688/WST665.
Accurate, Dense and Robust Multi-View Stereopsis Yasutaka Furukawa and Jean Ponce Presented by Rahul Garg and Ryan Kaminsky.
Jeff Howbert Introduction to Machine Learning Winter Machine Learning Feature Creation and Selection.
Computer vision.
Mining Discriminative Components With Low-Rank and Sparsity Constraints for Face Recognition Qiang Zhang, Baoxin Li Computer Science and Engineering Arizona.
Object Recognizing. Recognition -- topics Features Classifiers Example ‘winning’ system.
Hands segmentation Pat Jangyodsuk. Motivation Alternative approach of finding hands Instead of finding bounding box, classify each pixel whether they’re.
Building local part models for category-level recognition C. Schmid, INRIA Grenoble Joint work with G. Dorko, S. Lazebnik, J. Ponce.
1 Action Classification: An Integration of Randomization and Discrimination in A Dense Feature Representation Computer Science Department, Stanford University.
Detecting Curved Symmetric Parts using a Deformable Disc Model Tom Sie Ho Lee, University of Toronto Sanja Fidler, TTI Chicago Sven Dickinson, University.
Svetlana Lazebnik, Cordelia Schmid, Jean Ponce
Classifying Images with Visual/Textual Cues By Steven Kappes and Yan Cao.
Object Detection with Discriminatively Trained Part Based Models
Fast Direct Super-Resolution by Simple Functions
A Codebook-Free and Annotation-free Approach for Fine-Grained Image Categorization Authors Bangpeng Yao et al. Presenter Hyung-seok Lee ( 이형석 ) CVPR 2012.
Efficient Subwindow Search: A Branch and Bound Framework for Object Localization ‘PAMI09 Beyond Sliding Windows: Object Localization by Efficient Subwindow.
Sparse Bayesian Learning for Efficient Visual Tracking O. Williams, A. Blake & R. Cipolloa PAMI, Aug Presented by Yuting Qi Machine Learning Reading.
Gang WangDerek HoiemDavid Forsyth. INTRODUCTION APROACH (implement detail) EXPERIMENTS CONCLUSION.
Guest lecture: Feature Selection Alan Qi Dec 2, 2004.
Recognition Using Visual Phrases
Ariadna Quattoni Xavier Carreras An Efficient Projection for l 1,∞ Regularization Michael Collins Trevor Darrell MIT CSAIL.
Feedforward semantic segmentation with zoom-out features
Object Recognition as Ranking Holistic Figure-Ground Hypotheses Fuxin Li and Joao Carreira and Cristian Sminchisescu 1.
Object Recognizing. Object Classes Individual Recognition.
Locally Linear Support Vector Machines Ľubor Ladický Philip H.S. Torr.
Learning Photographic Global Tonal Adjustment with a Database of Input / Output Image Pairs.
SUN Database: Large-scale Scene Recognition from Abbey to Zoo Jianxiong Xiao *James Haysy Krista A. Ehinger Aude Oliva Antonio Torralba Massachusetts Institute.
A Kernel Approach for Learning From Almost Orthogonal Pattern * CIS 525 Class Presentation Professor: Slobodan Vucetic Presenter: Yilian Qin * B. Scholkopf.
Object Recognizing. Object Classes Individual Recognition.
A Discriminatively Trained, Multiscale, Deformable Part Model Yeong-Jun Cho Computer Vision and Pattern Recognition,2008.
Week 4: 6/6 – 6/10 Jeffrey Loppert. This week.. Coded a Histogram of Oriented Gradients (HOG) Feature Extractor Extracted features from positive and negative.
Does one size really fit all? Evaluating classifiers in a Bag-of-Visual-Words classification Christian Hentschel, Harald Sack Hasso Plattner Institute.
Cascade for Fast Detection
Face Detection EE368 Final Project Group 14 Ping Hsin Lee
Data Driven Attributes for Action Detection
Article Review Todd Hricik.
Lit part of blue dress and shadowed part of white dress are the same color
Nonparametric Semantic Segmentation
Recognition using Nearest Neighbor (or kNN)
Object Localization Goal: detect the location of an object within an image Fully supervised: Training data labeled with object category and ground truth.
Machine Learning Feature Creation and Selection
Cheng-Ming Huang, Wen-Hung Liao Department of Computer Science
Vessel Extraction in X-Ray Angiograms Using Deep Learning
REU Week 1 Ivette Carreras UCF.
Multiple Feature Learning for Action Classification
Presentation transcript:

Introduction Problem: Classifying attributes and actions in still images Model:  Collection of part templates  Specific scale space locations (human centric)  Discriminative learning  Sparse Activation

Motivation TrainTestTrainTest

Overview Image Scoring Mining Parts & Learning Templates

Formulation fractional multiples of width and height Dataset: Model: Objective:

Model fractional multiples of width and height... Part 1 Part 2Part 3 parts d = 1000 Model

Model & Scoring Image Scoring Model overlap constraint sparse activation Optimization: Greedy selection of 0.33 overlap constraint

Model Initialization 1) randomly sample the positive training images for patch positions: 2) Initialize model parts: perfect case: worst case: 3) BoF features normalized 10 5 patches. 3) Prunning: remove unused parts

Learning k = 4

Experiments Willow 7 Human actions 27 Human Attributes (HAT) Stanford 40 Human Actions

Implementation Features: – VLFeat - Dense SIFT, step size: 4 pixels square patches (8 to 40 pixels) – k-means - vocabulary 1000 – explicit feature map + Bhattacharyya (Hellinger – Square root) kernel Baseline: 4 level spatial pyramid Immediate context: – expand the human bounding boxes by 50% in both width and height Full image context: – full image classifier uses 4 level SPM with an exponential 2 kernel

Qualitative Results

Willow Actions

Database of Human Attributes (HAT)

Stanford 40 Actions

Learned Parts - I In each row, the first image is the patch used to initialize the part and the remaining images are its top scoring patches

Learned Parts - II In each row, the first image is the patch used to initialize the part and the remaining images are its top scoring patches

Learned Parts - III In each row, the first image is the patch used to initialize the part and the remaining images are its top scoring patches