Shifting from Naming to Describing: Semantic Attribute Models. Rogerio Feris, June 2014

Size: px
Start display at page:

Download "Shifting from Naming to Describing: Semantic Attribute Models. Rogerio Feris, June 2014"

Transcription

1 Shifting from Naming to Describing: Semantic Attribute Models Rogerio Feris, June 2014

2 Recap Large-Scale Semantic Modeling Feature Coding and Pooling Low-Level Feature Extraction Training Data Slide credit: Rogerio Feris

3 What if no training samples are available for the target class? Is this a practical setting? Slide credit: Rogerio Feris

4 Motivation ImageNet has 30 mushroom synsets, each with 1000 images. Slide credit: Christoph Lampert

5 Motivation In nature, there are 14,000 mushroom species. Zero-data: Many fine-grained visual categorization tasks may have classes with few or no training examples at all. Image: Slide adapted from Christoph Lampert

6 Motivation Suspect Search in Surveillance Videos [Feris et al, IBM] Zero-data: often no example images from suspects are available, only textual descriptions. Slide credit: Rogerio Feris

7 Motivation Prediction of concrete nouns from neural imaging data (mind reading) [Mark Palatucci et al, NIPS 2009] Noun Prediction Zero-Data: many nouns without corresponding neural image examples (costly label acquisition) Slide credit: Rogerio Feris

8 Motivation Similar problems in other fields: Large Vocabulary Speech Recognition Zero-Data: Infeasible to acquire training samples for each word (need sub-word modeling like phonemes) Recommendation Systems Zero-Data: Newly released apps without any user ratings (also known as cold-start problem ) [Schin et al, SIGIR 2002] Slide credit: Rogerio Feris

9 Semantic Attribute Models: Zero-Shot Learning for Visual Recognition [Lampert et al, CVPR 2009] [Farhadi et al, CVPR 2009] [Palatucci et al, NIPS 2009]

10 Attribute-based Classification Attributes: Semantic/nameable properties that are shared across classes Intuitive mid-level feature representation Slide adapted from Christoph Lampert

11 Attribute-based Classification [Lampert et al, CVPR 2009] Unseen categories Standard multi-class classification Unseen categories Semantic Attribute Classifiers Attribute-based classification Similar to Error-Correcting Output codes (ECOC [Dietterich & Bakiri, 1995]), but semantic codes are used instead Semantic Output Code Classifier (SOCC) [Palatucci et al, NIPS 2009] Slide credit: Rogerio Feris

12 Image-Attributes Prediction For each attribute, collect a set of positive and negative samples and train a classifier (e.g., using SVM or Neural networks) Example: Stripe Attribute Positive (Stripe) Negative (Non-Stripe) Binary Attribute Model Attributes transcend class boundaries Learning stripe attribute with images of zebras, clothing, Slide credit: Rogerio Feris

13 Image-Attributes Prediction Issue with Binary Attribute Models [Parikh and Grauman, ICCV 2011] Smiling??? Not smiling Natural??? Not natural

14 Image-Attributes Prediction Relative Attributes Replace binary model by a ranking function [Parikh and Grauman, ICCV 2011] i j i j Max-margin learning to rank formulation of Joachims 2002

15 Attribute-Class Associations Manual Specification of Class-Attribute Associations

16 Attribute-Class Associations Associations may be extracted automatically from other sources [Rohrbach et al, CVPR 2010]

17 Attributes as classes [Rohrbach et al, CVPR 2010] [Felix Yu et al, CVPR 2013] [Mensink et al, CVPR 2014] giant pandas are similar to grizzly and polar bears Attribute-based Direct similarity

18 Generalization: Label Embedding [Akata et al, CVPR 2013] Check talk by Florent Perronnin on Output embedding for large-scale visual recognition (LSVR CVPR 2014 tutorial)

19 Generalization: Label Embedding Label Embedding Framework Automatic Discovery of word associations Frome et al. "DeViSE: A Deep Visual-Semantic Embedding Model", NIPS 2013 Deep Learning Real-Value word vector representation Image Label Skip-gram model: Semantically related words are mapped to similar vector representations

20 Generalization: Label Embedding Label Embedding Framework Automatic Discovery of word associations [Frome et al, NIPS 2013] Zero-Shot Learning / Semantically close mistakes Language Model Source Code:

21 In addition to zero-shot classification, semantic attribute models have shown to be useful for many other tasks

22 Other Uses of Semantic Attributes Check the CVPR 2013 tutorial on Attributes: Slide credit: Rogerio Feris

23 Attribute-based Search Application: Smart Surveillance [Feris et al, IBM - WACV 2009, CVPR 2011, ICMR 2014]

24 Attribute-based People Search Slide credit: Rogerio Feris

25 Attribute-based People Search People Search in Surveillance Videos Traditional Approaches: Face Recognition ( Naming ) Face recognition is very challenging under lighting changes, pose variation, and lowresolution imagery (typical conditions in surveillance scenarios). Attribute-based People Search ( Describing ) Rather than relying on face recognition only, we provide a complementary people search framework based on fine-grained semantic attributes. Query Example: Show me all people with a beard and sunglasses, wearing a white hat and a patterned blue shirt, from all metro cameras in the downtown area, from 2pm to 4pm last Saturday". Slide credit: Rogerio Feris

26 Attribute-based People Search Suspect Description Form Slide credit: Rogerio Feris

27 Attribute-based People Search System Architecture Slide credit: Rogerio Feris

28 Attribute-based People Search Facial Attributes: bald, hair, color of hair, hat, color of hat, sunglasses, eyeglasses, absence of glasses, beard, mustache, absence of facial hair, skin tone (dark, medium,light), gender, Torso Attributes: clothing color, patterned, solid, Timestamp, Camera ID [Siddiquie et al, CVPR 2011] Slide credit: Rogerio Feris

29 Attribute-based People Search Attribute Ranking [Siddiquie, Feris and Davis, CVPR 2011] Learning to rank - confidence of individual attributes as features Pairwise attribute modeling Slide credit: Rogerio Feris

30 Structured Learning Formulation Improved performance over other ranking methods (RankSVM, RankBoost, DORM, TagProp) in three standard datasets (LFW, FaceTracer, PASCAL) See [Siddiquie, Feris and Davis, CVPR 2011] Slide credit: Rogerio Feris

31 Attribute-based People Search Top-1 Ranking Results [Feris et al, ICMR 2014] Slide credit: Rogerio Feris

32 Boston Bombing Event Show me all images of people matching the suspect description from time X to time Y from all cameras in area Z. Ability to spot a person with e.g., a white hat in a crowded scene 1071 detected faces from 50 high-res Boston images (all from Flickr) Suspect #1 found in 4 images in top 8 results Suspect #2 found in 3 images in top page Slide credit: Rogerio Feris

33 Extension to Vehicle Search [Feris et al, IEEE Trans on Multimedia, 2012] Show me all blue trucks larger than 7ft length traveling at high speed northbound last Saturday, from 2pm to 5pm. Slide credit: Rogerio Feris

34 Attribute-based Search Application: Product Search [Kovashka et al, CVPR 2012, ICCV 2013] [Yu & Grauman, CVPR 2014]

35 Whittle Search Slide credit: Kristen Grauman

36 Whittle Search Check Whittle Search demo at:

37 Resources

38 Resources

39 Resources Galaxy Morphological Attributes Data available at: 304,122 Galaxy Images 58,719,719 Annotations 83,943 volunteers 11 tasks / 38 answers (fine morphological attributes) Slide credit: Rogerio Feris

40 Resources 5 Terabytes of annotated data Data will be made publicly available soon! Slide credit: Rogerio Feris

41 Parts and Attributes Workshop (ECCV 2010) (ECCV 2012) (ECCV 2014) Check the Call for Extended Abstracts (Posters) Submission deadline: June 30th, 2014

Class 5: Attributes and Semantic Features

Class 5: Attributes and Semantic Features Class 5: Attributes and Semantic Features Rogerio Feris, Feb 21, 2013 EECS 6890 Topics in Information Processing Spring 2013, Columbia University http://rogerioferis.com/visualrecognitionandsearch Project

More information

Learning Visual Semantics: Models, Massive Computation, and Innovative Applications. Tutorial at CVPR 2014 June 23rd, 1:00pm-5:00pm, Columbus, OH

Learning Visual Semantics: Models, Massive Computation, and Innovative Applications. Tutorial at CVPR 2014 June 23rd, 1:00pm-5:00pm, Columbus, OH Learning Visual Semantics: Models, Massive Computation, and Innovative Applications Tutorial at CVPR 2014 June 23rd, 1:00pm-5:00pm, Columbus, OH Introduction Instructors: Shih-Fu Chang John Smith Rogerio

More information

CS 1674: Intro to Computer Vision. Attributes. Prof. Adriana Kovashka University of Pittsburgh November 2, 2016

CS 1674: Intro to Computer Vision. Attributes. Prof. Adriana Kovashka University of Pittsburgh November 2, 2016 CS 1674: Intro to Computer Vision Attributes Prof. Adriana Kovashka University of Pittsburgh November 2, 2016 Plan for today What are attributes and why are they useful? (paper 1) Attributes for zero-shot

More information

Experiments of Image Retrieval Using Weak Attributes

Experiments of Image Retrieval Using Weak Attributes Columbia University Computer Science Department Technical Report # CUCS 005-12 (2012) Experiments of Image Retrieval Using Weak Attributes Felix X. Yu, Rongrong Ji, Ming-Hen Tsai, Guangnan Ye, Shih-Fu

More information

Describable Visual Attributes for Face Verification and Image Search

Describable Visual Attributes for Face Verification and Image Search Advanced Topics in Multimedia Analysis and Indexing, Spring 2011, NTU. 1 Describable Visual Attributes for Face Verification and Image Search Kumar, Berg, Belhumeur, Nayar. PAMI, 2011. Ryan Lei 2011/05/05

More information

End-to-End Localization and Ranking for Relative Attributes

End-to-End Localization and Ranking for Relative Attributes End-to-End Localization and Ranking for Relative Attributes Krishna Kumar Singh and Yong Jae Lee Presented by Minhao Cheng [Farhadi et al. 2009, Kumar et al. 2009, Lampert et al. 2009, [Slide: Xiao and

More information

Interactive Image Search with Attributes

Interactive Image Search with Attributes Interactive Image Search with Attributes Adriana Kovashka Department of Computer Science January 13, 2015 Joint work with Kristen Grauman and Devi Parikh We Need Search to Access Visual Data 144,000 hours

More information

Recognition Tools: Support Vector Machines

Recognition Tools: Support Vector Machines CS 2770: Computer Vision Recognition Tools: Support Vector Machines Prof. Adriana Kovashka University of Pittsburgh January 12, 2017 Announcement TA office hours: Tuesday 4pm-6pm Wednesday 10am-12pm Matlab

More information

Learning Detectors from Large Datasets for Object Retrieval in Video Surveillance

Learning Detectors from Large Datasets for Object Retrieval in Video Surveillance Learning Detectors from Large Datasets for Object Retrieval in Video Surveillance Rogerio Feris, Sharath Pankanti IBM T. J. Watson Research Center {rsferis,sharat}@us.ibm.com Behjat Siddiquie SRI International

More information

Additional Remarks on Designing Category-Level Attributes for Discriminative Visual Recognition

Additional Remarks on Designing Category-Level Attributes for Discriminative Visual Recognition Columbia University Computer Science Department Technical Report # CUCS 007-13 (2013) Additional Remarks on Designing Category-Level Attributes for Discriminative Visual Recognition Felix X. Yu, Liangliang

More information

Object Classification for Video Surveillance

Object Classification for Video Surveillance Object Classification for Video Surveillance Rogerio Feris IBM TJ Watson Research Center rsferis@us.ibm.com http://rogerioferis.com 1 Outline Part I: Object Classification in Far-field Video Part II: Large

More information

Discriminative classifiers for image recognition

Discriminative classifiers for image recognition Discriminative classifiers for image recognition May 26 th, 2015 Yong Jae Lee UC Davis Outline Last time: window-based generic object detection basic pipeline face detection with boosting as case study

More information

Metric Learning for Large-Scale Image Classification:

Metric Learning for Large-Scale Image Classification: Metric Learning for Large-Scale Image Classification: Generalizing to New Classes at Near-Zero Cost Florent Perronnin 1 work published at ECCV 2012 with: Thomas Mensink 1,2 Jakob Verbeek 2 Gabriela Csurka

More information

Towards Large-Scale Semantic Representations for Actionable Exploitation. Prof. Trevor Darrell UC Berkeley

Towards Large-Scale Semantic Representations for Actionable Exploitation. Prof. Trevor Darrell UC Berkeley Towards Large-Scale Semantic Representations for Actionable Exploitation Prof. Trevor Darrell UC Berkeley traditional surveillance sensor emerging crowd sensor Desired capabilities: spatio-temporal reconstruction

More information

Attributes. Computer Vision. James Hays. Many slides from Derek Hoiem

Attributes. Computer Vision. James Hays. Many slides from Derek Hoiem Many slides from Derek Hoiem Attributes Computer Vision James Hays Recap: Human Computation Active Learning: Let the classifier tell you where more annotation is needed. Human-in-the-loop recognition:

More information

Additional Remarks on Designing Category-Level Attributes for Discriminative Visual Recognition

Additional Remarks on Designing Category-Level Attributes for Discriminative Visual Recognition Columbia University Computer Science Department Technical Report # CUCS 007-13 (2013) Additional Remarks on Designing Category-Level Attributes for Discriminative Visual Recognition Felix X. Yu, Liangliang

More information

Metric Learning for Large Scale Image Classification:

Metric Learning for Large Scale Image Classification: Metric Learning for Large Scale Image Classification: Generalizing to New Classes at Near-Zero Cost Thomas Mensink 1,2 Jakob Verbeek 2 Florent Perronnin 1 Gabriela Csurka 1 1 TVPA - Xerox Research Centre

More information

Attributes and More Crowdsourcing

Attributes and More Crowdsourcing Attributes and More Crowdsourcing Computer Vision CS 143, Brown James Hays Many slides from Derek Hoiem Recap: Human Computation Active Learning: Let the classifier tell you where more annotation is needed.

More information

Visual Recognition and Search

Visual Recognition and Search Visual Recognition and Search Rogerio Feris, Jan 24, 2013 EECS 6890 Topics in Information Processing Spring 2013, Columbia University http://rogerioferis.com/visualrecognitionandsearch Introduction 1970s

More information

24 hours of Photo Sharing. installation by Erik Kessels

24 hours of Photo Sharing. installation by Erik Kessels 24 hours of Photo Sharing installation by Erik Kessels And sometimes Internet photos have useful labels Im2gps. Hays and Efros. CVPR 2008 But what if we want more? Image Categorization Training Images

More information

FACE ATTRIBUTE CLASSIFICATION USING ATTRIBUTE-AWARE CORRELATION MAP AND GATED CONVOLUTIONAL NEURAL NETWORKS

FACE ATTRIBUTE CLASSIFICATION USING ATTRIBUTE-AWARE CORRELATION MAP AND GATED CONVOLUTIONAL NEURAL NETWORKS FACE ATTRIBUTE CLASSIFICATION USING ATTRIBUTE-AWARE CORRELATION MAP AND GATED CONVOLUTIONAL NEURAL NETWORKS Sunghun Kang, Donghoon Lee, and Chang D. Yoo Korea Advanced institute of Science and Technology

More information

Attribute learning in large-scale datasets. Olga Russakovsky and Li Fei-Fei

Attribute learning in large-scale datasets. Olga Russakovsky and Li Fei-Fei Attribute learning in large-scale datasets Olga Russakovsky and Li Fei-Fei Categorization of the visual world Berry Fruit Entity Tree Instrument Furniture Categorization of the visual world Berry Fruit

More information

on learned visual embedding patrick pérez Allegro Workshop Inria Rhônes-Alpes 22 July 2015

on learned visual embedding patrick pérez Allegro Workshop Inria Rhônes-Alpes 22 July 2015 on learned visual embedding patrick pérez Allegro Workshop Inria Rhônes-Alpes 22 July 2015 Vector visual representation Fixed-size image representation High-dim (100 100,000) Generic, unsupervised: BoW,

More information

Compare and Contrast: Learning Prominent Differences in Relative Attributes. Steven Ziqiu Chen

Compare and Contrast: Learning Prominent Differences in Relative Attributes. Steven Ziqiu Chen Compare and Contrast: Learning Prominent Differences in Relative Attributes by Steven Ziqiu Chen stevenchen@utexas.edu Supervised by: Dr. Kristen Grauman Department of Computer Science Abstract Relative

More information

Part-based and local feature models for generic object recognition

Part-based and local feature models for generic object recognition Part-based and local feature models for generic object recognition May 28 th, 2015 Yong Jae Lee UC Davis Announcements PS2 grades up on SmartSite PS2 stats: Mean: 80.15 Standard Dev: 22.77 Vote on piazza

More information

Yiqi Yan. May 10, 2017

Yiqi Yan. May 10, 2017 Yiqi Yan May 10, 2017 P a r t I F u n d a m e n t a l B a c k g r o u n d s Convolution Single Filter Multiple Filters 3 Convolution: case study, 2 filters 4 Convolution: receptive field receptive field

More information

CAP 6412 Advanced Computer Vision

CAP 6412 Advanced Computer Vision CAP 6412 Advanced Computer Vision http://www.cs.ucf.edu/~bgong/cap6412.html Boqing Gong April 5th, 2016 Today Administrivia LSTM Attribute in computer vision, by Abdullah and Samer Project II posted, due

More information

Designing Category-Level Attributes for Discriminative Visual Recognition

Designing Category-Level Attributes for Discriminative Visual Recognition 2013 IEEE Conference on Computer Vision and Pattern Recognition Designing Category-Level Attributes for Discriminative Visual Recognition Felix X. Yu, Liangliang Cao, Rogerio S. Feris, John R. Smith, Shih-Fu

More information

Recognition of Animal Skin Texture Attributes in the Wild. Amey Dharwadker (aap2174) Kai Zhang (kz2213)

Recognition of Animal Skin Texture Attributes in the Wild. Amey Dharwadker (aap2174) Kai Zhang (kz2213) Recognition of Animal Skin Texture Attributes in the Wild Amey Dharwadker (aap2174) Kai Zhang (kz2213) Motivation Patterns and textures are have an important role in object description and understanding

More information

Spoken Attributes: Mixing Binary and Relative Attributes to Say the Right Thing

Spoken Attributes: Mixing Binary and Relative Attributes to Say the Right Thing Spoken ttributes: Mixing inary and Relative ttributes to Say the Right Thing mir Sadovnik Cornell University as2373@cornell.edu ndrew Gallagher Cornell University acg226@cornell.edu Devi Parikh Virginia

More information

A general method for appearance-based people search based on textual queries

A general method for appearance-based people search based on textual queries A general method for appearance-based people search based on textual queries Riccardo Satta, Giorgio Fumera, and Fabio Roli Dept. of Electrical and Electronic Engineering, University of Cagliari Piazza

More information

arxiv: v2 [cs.cv] 13 Apr 2018

arxiv: v2 [cs.cv] 13 Apr 2018 Compare and Contrast: Learning Prominent Visual Differences Steven Chen Kristen Grauman The University of Texas at Austin Abstract arxiv:1804.00112v2 [cs.cv] 13 Apr 2018 Relative attribute models can compare

More information

6.819 / 6.869: Advances in Computer Vision

6.819 / 6.869: Advances in Computer Vision 6.819 / 6.869: Advances in Computer Vision Image Retrieval: Retrieval: Information, images, objects, large-scale Website: http://6.869.csail.mit.edu/fa15/ Instructor: Yusuf Aytar Lecture TR 9:30AM 11:00AM

More information

Deep learning for object detection. Slides from Svetlana Lazebnik and many others

Deep learning for object detection. Slides from Svetlana Lazebnik and many others Deep learning for object detection Slides from Svetlana Lazebnik and many others Recent developments in object detection 80% PASCAL VOC mean0average0precision0(map) 70% 60% 50% 40% 30% 20% 10% Before deep

More information

Lecture 5: Object Detection

Lecture 5: Object Detection Object Detection CSED703R: Deep Learning for Visual Recognition (2017F) Lecture 5: Object Detection Bohyung Han Computer Vision Lab. bhhan@postech.ac.kr 2 Traditional Object Detection Algorithms Region-based

More information

arxiv: v1 [cs.cv] 9 Aug 2016

arxiv: v1 [cs.cv] 9 Aug 2016 arxiv:1608.02676v1 [cs.cv] 9 Aug 2016 End-to-End Localization and Ranking for Relative Attributes Krishna Kumar Singh and Yong Jae Lee University of California, Davis Abstract. We propose an end-to-end

More information

Bilinear Models for Fine-Grained Visual Recognition

Bilinear Models for Fine-Grained Visual Recognition Bilinear Models for Fine-Grained Visual Recognition Subhransu Maji College of Information and Computer Sciences University of Massachusetts, Amherst Fine-grained visual recognition Example: distinguish

More information

Hierarchical Ranking of Facial Attributes

Hierarchical Ranking of Facial Attributes Hierarchical Raning of Facial Attributes Anur Datta IBM T J Watson Research Center, ew Yor, USA anurd@usibmcom Rogerio Feris IBM T J Watson Research Center, ew Yor, USA rsferis@usibmcom Daniel Vaquero

More information

AUTOMATIC VISUAL CONCEPT DETECTION IN VIDEOS

AUTOMATIC VISUAL CONCEPT DETECTION IN VIDEOS AUTOMATIC VISUAL CONCEPT DETECTION IN VIDEOS Nilam B. Lonkar 1, Dinesh B. Hanchate 2 Student of Computer Engineering, Pune University VPKBIET, Baramati, India Computer Engineering, Pune University VPKBIET,

More information

CAP 6412 Advanced Computer Vision

CAP 6412 Advanced Computer Vision CAP 6412 Advanced Computer Vision http://www.cs.ucf.edu/~bgong/cap6412.html Boqing Gong April 21st, 2016 Today Administrivia Free parameters in an approach, model, or algorithm? Egocentric videos by Aisha

More information

Dimensionality Reduction using Relative Attributes

Dimensionality Reduction using Relative Attributes Dimensionality Reduction using Relative Attributes Mohammadreza Babaee 1, Stefanos Tsoukalas 1, Maryam Babaee Gerhard Rigoll 1, and Mihai Datcu 1 Institute for Human-Machine Communication, Technische Universität

More information

Attribute Dominance: What Pops Out?

Attribute Dominance: What Pops Out? 2013 IEEE International Conference on Computer Vision Attribute Dominance: What Pops Out? Naman Turakhia Georgia Tech nturakhia@gatech.edu Devi Parikh Virginia Tech parikh@vt.edu Abstract When we look

More information

CS4495/6495 Introduction to Computer Vision. 8C-L1 Classification: Discriminative models

CS4495/6495 Introduction to Computer Vision. 8C-L1 Classification: Discriminative models CS4495/6495 Introduction to Computer Vision 8C-L1 Classification: Discriminative models Remember: Supervised classification Given a collection of labeled examples, come up with a function that will predict

More information

End-to-End Localization and Ranking for Relative Attributes

End-to-End Localization and Ranking for Relative Attributes End-to-End Localization and Ranking for Relative Attributes Krishna Kumar Singh and Yong Jae Lee University of California, Davis Abstract. We propose an end-to-end deep convolutional network to simultaneously

More information

Pull the Plug? Predicting If Computers or Humans Should Segment Images Supplementary Material

Pull the Plug? Predicting If Computers or Humans Should Segment Images Supplementary Material In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, June 2016. Pull the Plug? Predicting If Computers or Humans Should Segment Images Supplementary Material

More information

Deep Learning for Face Recognition. Xiaogang Wang Department of Electronic Engineering, The Chinese University of Hong Kong

Deep Learning for Face Recognition. Xiaogang Wang Department of Electronic Engineering, The Chinese University of Hong Kong Deep Learning for Face Recognition Xiaogang Wang Department of Electronic Engineering, The Chinese University of Hong Kong Deep Learning Results on LFW Method Accuracy (%) # points # training images Huang

More information

Multi-Attribute Spaces: Calibration for Attribute Fusion and Similarity Search

Multi-Attribute Spaces: Calibration for Attribute Fusion and Similarity Search Beard Round Face Male Beard MultiAttribute Spaces: Calibration for Attribute Fusion and Similarity Search Walter J. Scheirer 1,2 Neeraj Kumar 3 Peter N. Belhumeur 4 Terrance E. Boult 1,2 1 University of

More information

Detecting and Parsing of Visual Objects: Humans and Animals. Alan Yuille (UCLA)

Detecting and Parsing of Visual Objects: Humans and Animals. Alan Yuille (UCLA) Detecting and Parsing of Visual Objects: Humans and Animals Alan Yuille (UCLA) Summary This talk describes recent work on detection and parsing visual objects. The methods represent objects in terms of

More information

Introduction to object recognition. Slides adapted from Fei-Fei Li, Rob Fergus, Antonio Torralba, and others

Introduction to object recognition. Slides adapted from Fei-Fei Li, Rob Fergus, Antonio Torralba, and others Introduction to object recognition Slides adapted from Fei-Fei Li, Rob Fergus, Antonio Torralba, and others Overview Basic recognition tasks A statistical learning approach Traditional or shallow recognition

More information

arxiv: v1 [cs.mm] 12 Jan 2016

arxiv: v1 [cs.mm] 12 Jan 2016 Learning Subclass Representations for Visually-varied Image Classification Xinchao Li, Peng Xu, Yue Shi, Martha Larson, Alan Hanjalic Multimedia Information Retrieval Lab, Delft University of Technology

More information

AN ENHANCED ATTRIBUTE RERANKING DESIGN FOR WEB IMAGE SEARCH

AN ENHANCED ATTRIBUTE RERANKING DESIGN FOR WEB IMAGE SEARCH AN ENHANCED ATTRIBUTE RERANKING DESIGN FOR WEB IMAGE SEARCH Sai Tejaswi Dasari #1 and G K Kishore Babu *2 # Student,Cse, CIET, Lam,Guntur, India * Assistant Professort,Cse, CIET, Lam,Guntur, India Abstract-

More information

Spatial Localization and Detection. Lecture 8-1

Spatial Localization and Detection. Lecture 8-1 Lecture 8: Spatial Localization and Detection Lecture 8-1 Administrative - Project Proposals were due on Saturday Homework 2 due Friday 2/5 Homework 1 grades out this week Midterm will be in-class on Wednesday

More information

arxiv: v1 [cs.cv] 17 Apr 2018

arxiv: v1 [cs.cv] 17 Apr 2018 Zero-shot Learning with Complementary Attributes Xiaofeng Xu 1,2, Ivor W. Tsang 2, Chuancai Liu 1 1 School of Computer Science and Engineering, Nanjing University of Science and Technology 2 Centre for

More information

CS231N Section. Video Understanding 6/1/2018

CS231N Section. Video Understanding 6/1/2018 CS231N Section Video Understanding 6/1/2018 Outline Background / Motivation / History Video Datasets Models Pre-deep learning CNN + RNN 3D convolution Two-stream What we ve seen in class so far... Image

More information

Geodesic Flow Kernel for Unsupervised Domain Adaptation

Geodesic Flow Kernel for Unsupervised Domain Adaptation Geodesic Flow Kernel for Unsupervised Domain Adaptation Boqing Gong University of Southern California Joint work with Yuan Shi, Fei Sha, and Kristen Grauman 1 Motivation TRAIN TEST Mismatch between different

More information

Boosting Object Detection Performance in Crowded Surveillance Videos

Boosting Object Detection Performance in Crowded Surveillance Videos Boosting Object Detection Performance in Crowded Surveillance Videos Rogerio Feris, Ankur Datta, Sharath Pankanti IBM T. J. Watson Research Center, New York Contact: Rogerio Feris (rsferis@us.ibm.com)

More information

Image Retrieval Using Attribute Enhanced Sparse Code Words

Image Retrieval Using Attribute Enhanced Sparse Code Words Image Retrieval Using Attribute Enhanced Sparse Code Words M.Balaganesh 1, N.Arthi 2 Associate Professor, Department of Computer Science and Engineering, SRV Engineering College, sembodai, india 1 P.G.

More information

VERGE IN VBS Thessaloniki, Greece {moumtzid, andreadisst, markatopoulou, dgalanop, heliasgj, stefanos, bmezaris,

VERGE IN VBS Thessaloniki, Greece {moumtzid, andreadisst, markatopoulou, dgalanop, heliasgj, stefanos, bmezaris, VERGE IN VBS 2018 Anastasia Moumtzidou 1, Stelios Andreadis 1 Foteini Markatopoulou 1,2, Damianos Galanopoulos 1, Ilias Gialampoukidis 1, Stefanos Vrochidis 1, Vasileios Mezaris 1, Ioannis Kompatsiaris

More information

Cost-alleviative Learning for Deep Convolutional Neural Network-based Facial Part Labeling

Cost-alleviative Learning for Deep Convolutional Neural Network-based Facial Part Labeling [DOI: 10.2197/ipsjtcva.7.99] Express Paper Cost-alleviative Learning for Deep Convolutional Neural Network-based Facial Part Labeling Takayoshi Yamashita 1,a) Takaya Nakamura 1 Hiroshi Fukui 1,b) Yuji

More information

Reducing Multiclass to Binary. LING572 Fei Xia

Reducing Multiclass to Binary. LING572 Fei Xia Reducing Multiclass to Binary LING572 Fei Xia 1 Highlights What? Converting a k-class problem to a binary problem. Why? For some ML algorithms, a direct extension to the multiclass case may be problematic.

More information

ImageCLEF 2011

ImageCLEF 2011 SZTAKI @ ImageCLEF 2011 Bálint Daróczy joint work with András Benczúr, Róbert Pethes Data Mining and Web Search Group Computer and Automation Research Institute Hungarian Academy of Sciences Training/test

More information

Localizing and Visualizing Relative Attributes

Localizing and Visualizing Relative Attributes Localizing and Visualizing Relative Attributes Fanyi Xiao and Yong Jae Lee Abstract In this chapter, we present a weakly-supervised approach that discovers the spatial extent of relative attributes, given

More information

Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification

Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification Xiaodong Yang, Pavlo Molchanov, Jan Kautz INTELLIGENT VIDEO ANALYTICS Surveillance event detection Human-computer interaction

More information

Object detection with CNNs

Object detection with CNNs Object detection with CNNs 80% PASCAL VOC mean0average0precision0(map) 70% 60% 50% 40% 30% 20% 10% Before CNNs After CNNs 0% 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 year Region proposals

More information

Deep Learning for Broadcast Videos and Multimedia

Deep Learning for Broadcast Videos and Multimedia Deep Learning for Broadcast Videos and Multimedia Lorenzo Baraldi lorenzo.baraldi@unimore.it University of Modena and Reggio Emilia Deep Learning State-of-the-art in image classification, object detection,

More information

People Detection and Video Understanding

People Detection and Video Understanding 1 People Detection and Video Understanding Francois BREMOND INRIA Sophia Antipolis STARS team Institut National Recherche Informatique et Automatisme Francois.Bremond@inria.fr http://www-sop.inria.fr/members/francois.bremond/

More information

Object Recognition. Lecture 11, April 21 st, Lexing Xie. EE4830 Digital Image Processing

Object Recognition. Lecture 11, April 21 st, Lexing Xie. EE4830 Digital Image Processing Object Recognition Lecture 11, April 21 st, 2008 Lexing Xie EE4830 Digital Image Processing http://www.ee.columbia.edu/~xlx/ee4830/ 1 Announcements 2 HW#5 due today HW#6 last HW of the semester Due May

More information

CS5670: Computer Vision

CS5670: Computer Vision CS5670: Computer Vision Noah Snavely Lecture 33: Recognition Basics Slides from Andrej Karpathy and Fei-Fei Li http://vision.stanford.edu/teaching/cs231n/ Announcements Quiz moved to Tuesday Project 4

More information

Every Picture Tells a Story: Generating Sentences from Images

Every Picture Tells a Story: Generating Sentences from Images Every Picture Tells a Story: Generating Sentences from Images Ali Farhadi, Mohsen Hejrati, Mohammad Amin Sadeghi, Peter Young, Cyrus Rashtchian, Julia Hockenmaier, David Forsyth University of Illinois

More information

Scalable Face Image Retrieval Using Attribute-Enhanced Sparse Codewords

Scalable Face Image Retrieval Using Attribute-Enhanced Sparse Codewords IEEE TRANSACTIONS ON MULTIMEDIA, VOL. 15, NO. 5, AUGUST 2013 1163 Scalable Face Image Retrieval Using Attribute-Enhanced Sparse Codewords Bor-Chun Chen, Yan-Ying Chen, Yin-Hsi Kuo, and Winston H. Hsu,

More information

Deformable Part Models

Deformable Part Models CS 1674: Intro to Computer Vision Deformable Part Models Prof. Adriana Kovashka University of Pittsburgh November 9, 2016 Today: Object category detection Window-based approaches: Last time: Viola-Jones

More information

Object Detection. Part1. Presenter: Dae-Yong

Object Detection. Part1. Presenter: Dae-Yong Object Part1 Presenter: Dae-Yong Contents 1. What is an Object? 2. Traditional Object Detector 3. Deep Learning-based Object Detector What is an Object? Subset of Object Recognition What is an Object?

More information

Face Recognition by Deep Learning - The Imbalance Problem

Face Recognition by Deep Learning - The Imbalance Problem Face Recognition by Deep Learning - The Imbalance Problem Chen-Change LOY MMLAB The Chinese University of Hong Kong Homepage: http://personal.ie.cuhk.edu.hk/~ccloy/ Twitter: https://twitter.com/ccloy CVPR

More information

Discovering Localized Attributes for Fine-grained Recognition

Discovering Localized Attributes for Fine-grained Recognition Discovering Localized Attributes for Fine-grained Recognition Kun Duan Indiana University Bloomington, IN kduan@indiana.edu Devi Parikh TTI-Chicago Chicago, IL dparikh@ttic.edu David Crandall Indiana University

More information

Fashion Style in 128 Floats: Joint Ranking and Classification using Weak Data for Feature Extraction SUPPLEMENTAL MATERIAL

Fashion Style in 128 Floats: Joint Ranking and Classification using Weak Data for Feature Extraction SUPPLEMENTAL MATERIAL Fashion Style in 128 Floats: Joint Ranking and Classification using Weak Data for Feature Extraction SUPPLEMENTAL MATERIAL Edgar Simo-Serra Waseda University esimo@aoni.waseda.jp Hiroshi Ishikawa Waseda

More information

By Suren Manvelyan,

By Suren Manvelyan, By Suren Manvelyan, http://www.surenmanvelyan.com/gallery/7116 By Suren Manvelyan, http://www.surenmanvelyan.com/gallery/7116 By Suren Manvelyan, http://www.surenmanvelyan.com/gallery/7116 By Suren Manvelyan,

More information

Semantic Spaces for Zero-Shot Behaviour Analysis

Semantic Spaces for Zero-Shot Behaviour Analysis Semantic Spaces for Zero-Shot Behaviour Analysis Xun Xu Computer Vision and Interactive Media Lab, NUS Singapore 1 Collaborators Prof. Shaogang Gong Dr. Timothy Hospedales 2 Outline Background Transductive

More information

The Caltech-UCSD Birds Dataset

The Caltech-UCSD Birds Dataset The Caltech-UCSD Birds-200-2011 Dataset Catherine Wah 1, Steve Branson 1, Peter Welinder 2, Pietro Perona 2, Serge Belongie 1 1 University of California, San Diego 2 California Institute of Technology

More information

Direct Multi-Scale Dual-Stream Network for Pedestrian Detection Sang-Il Jung and Ki-Sang Hong Image Information Processing Lab.

Direct Multi-Scale Dual-Stream Network for Pedestrian Detection Sang-Il Jung and Ki-Sang Hong Image Information Processing Lab. [ICIP 2017] Direct Multi-Scale Dual-Stream Network for Pedestrian Detection Sang-Il Jung and Ki-Sang Hong Image Information Processing Lab., POSTECH Pedestrian Detection Goal To draw bounding boxes that

More information

CS6501: Deep Learning for Visual Recognition. Object Detection I: RCNN, Fast-RCNN, Faster-RCNN

CS6501: Deep Learning for Visual Recognition. Object Detection I: RCNN, Fast-RCNN, Faster-RCNN CS6501: Deep Learning for Visual Recognition Object Detection I: RCNN, Fast-RCNN, Faster-RCNN Today s Class Object Detection The RCNN Object Detector (2014) The Fast RCNN Object Detector (2015) The Faster

More information

Multimodal Ranking for Non-Compliance Detection in Retail Surveillance

Multimodal Ranking for Non-Compliance Detection in Retail Surveillance Multimodal Ranking for Non-Compliance Detection in Retail Surveillance Hoang Trinh Sharath Pankanti Quanfu Fan IBM T. J. Watson Research Center 19 Skylikne Dr, Hawthorne, NY 10532 Abstract In retail stores,

More information

Columbia University High-Level Feature Detection: Parts-based Concept Detectors

Columbia University High-Level Feature Detection: Parts-based Concept Detectors TRECVID 2005 Workshop Columbia University High-Level Feature Detection: Parts-based Concept Detectors Dong-Qing Zhang, Shih-Fu Chang, Winston Hsu, Lexin Xie, Eric Zavesky Digital Video and Multimedia Lab

More information

[Supplementary Material] Improving Occlusion and Hard Negative Handling for Single-Stage Pedestrian Detectors

[Supplementary Material] Improving Occlusion and Hard Negative Handling for Single-Stage Pedestrian Detectors [Supplementary Material] Improving Occlusion and Hard Negative Handling for Single-Stage Pedestrian Detectors Junhyug Noh Soochan Lee Beomsu Kim Gunhee Kim Department of Computer Science and Engineering

More information

Instances on a Budget

Instances on a Budget Retrieving Similar or Informative Instances on a Budget Kristen Grauman Dept. of Computer Science University of Texas at Austin Work with Sudheendra Vijayanarasimham Work with Sudheendra Vijayanarasimham,

More information

Recognizing people. Deva Ramanan

Recognizing people. Deva Ramanan Recognizing people Deva Ramanan The goal Why focus on people? How many person-pixels are in a video? 35% 34% Movies TV 40% YouTube Let s start our discussion with a loaded question: why is visual recognition

More information

Proceedings of the International MultiConference of Engineers and Computer Scientists 2018 Vol I IMECS 2018, March 14-16, 2018, Hong Kong

Proceedings of the International MultiConference of Engineers and Computer Scientists 2018 Vol I IMECS 2018, March 14-16, 2018, Hong Kong , March 14-16, 2018, Hong Kong , March 14-16, 2018, Hong Kong , March 14-16, 2018, Hong Kong , March 14-16, 2018, Hong Kong TABLE I CLASSIFICATION ACCURACY OF DIFFERENT PRE-TRAINED MODELS ON THE TEST DATA

More information

Face2Face Comparing faces with applications Patrick Pérez. Inria, Rennes 2 Oct. 2014

Face2Face Comparing faces with applications Patrick Pérez. Inria, Rennes 2 Oct. 2014 Face2Face Comparing faces with applications Patrick Pérez Inria, Rennes 2 Oct. 2014 Outline Metric learning for face comparison Expandable parts model and occlusions Face sets comparison Identity-based

More information

The attributes of objects. D.A. Forsyth, UIUC channelling Derek Hoiem, UIUC, with Ali Farhadi, Ian Endres, Gang Wang all of UIUC

The attributes of objects. D.A. Forsyth, UIUC channelling Derek Hoiem, UIUC, with Ali Farhadi, Ian Endres, Gang Wang all of UIUC The attributes of objects D.A. Forsyth, UIUC channelling Derek Hoiem, UIUC, with Ali Farhadi, Ian Endres, Gang Wang all of UIUC Obtain dataset Build features Mess around with classifiers, probability,

More information

Large-Scale Live Active Learning: Training Object Detectors with Crawled Data and Crowds

Large-Scale Live Active Learning: Training Object Detectors with Crawled Data and Crowds Large-Scale Live Active Learning: Training Object Detectors with Crawled Data and Crowds Sudheendra Vijayanarasimhan Kristen Grauman Department of Computer Science University of Texas at Austin Austin,

More information

Self-Supervised Learning & Visual Discovery

Self-Supervised Learning & Visual Discovery CS 2770: Computer Vision Self-Supervised Learning & Visual Discovery Prof. Adriana Kovashka University of Pittsburgh April 10, 2017 Motivation So far we ve assumed access to plentiful labeled data How

More information

Bias-Variance Trade-off + Other Models and Problems

Bias-Variance Trade-off + Other Models and Problems CS 1699: Intro to Computer Vision Bias-Variance Trade-off + Other Models and Problems Prof. Adriana Kovashka University of Pittsburgh November 3, 2015 Outline Support Vector Machines (review + other uses)

More information

An Exploration of Computer Vision Techniques for Bird Species Classification

An Exploration of Computer Vision Techniques for Bird Species Classification An Exploration of Computer Vision Techniques for Bird Species Classification Anne L. Alter, Karen M. Wang December 15, 2017 Abstract Bird classification, a fine-grained categorization task, is a complex

More information

Web-Scale Image Search and Their Applications

Web-Scale Image Search and Their Applications Web-Scale Image Search and Their Applications Sung-Eui Yoon KAIST http://sglab.kaist.ac.kr Project Guidelines: Project Topics Any topics related to the course theme are okay You can find topics by browsing

More information

Computer Vision: Making machines see

Computer Vision: Making machines see Computer Vision: Making machines see Roberto Cipolla Department of Engineering http://www.eng.cam.ac.uk/~cipolla/people.html http://www.toshiba.eu/eu/cambridge-research- Laboratory/ Vision: what is where

More information

Synscapes A photorealistic syntehtic dataset for street scene parsing Jonas Unger Department of Science and Technology Linköpings Universitet.

Synscapes A photorealistic syntehtic dataset for street scene parsing Jonas Unger Department of Science and Technology Linköpings Universitet. Synscapes A photorealistic syntehtic dataset for street scene parsing Jonas Unger Department of Science and Technology Linköpings Universitet 7D Labs VINNOVA https://7dlabs.com Photo-realistic image synthesis

More information

CS230: Lecture 3 Various Deep Learning Topics

CS230: Lecture 3 Various Deep Learning Topics CS230: Lecture 3 Various Deep Learning Topics Kian Katanforoosh, Andrew Ng Today s outline We will learn how to: - Analyse a problem from a deep learning approach - Choose an architecture - Choose a loss

More information

SVM: Multiclass and Structured Prediction. Bin Zhao

SVM: Multiclass and Structured Prediction. Bin Zhao SVM: Multiclass and Structured Prediction Bin Zhao Part I: Multi-Class SVM 2-Class SVM Primal form Dual form http://www.glue.umd.edu/~zhelin/recog.html Real world classification problems Digit recognition

More information

Regionlet Object Detector with Hand-crafted and CNN Feature

Regionlet Object Detector with Hand-crafted and CNN Feature Regionlet Object Detector with Hand-crafted and CNN Feature Xiaoyu Wang Research Xiaoyu Wang Research Ming Yang Horizon Robotics Shenghuo Zhu Alibaba Group Yuanqing Lin Baidu Overview of this section Regionlet

More information

Computer Vision: Summary and Discussion

Computer Vision: Summary and Discussion 12/05/2011 Computer Vision: Summary and Discussion Computer Vision CS 143, Brown James Hays Many slides from Derek Hoiem Announcements Today is last day of regular class Second quiz on Wednesday (Dec 7

More information

DeepIndex for Accurate and Efficient Image Retrieval

DeepIndex for Accurate and Efficient Image Retrieval DeepIndex for Accurate and Efficient Image Retrieval Yu Liu, Yanming Guo, Song Wu, Michael S. Lew Media Lab, Leiden Institute of Advance Computer Science Outline Motivation Proposed Approach Results Conclusions

More information