Richer Human-Machine Communication in Attributes-based Visual Recognition Devi Parikh TTIC.

Slides:



Advertisements
Similar presentations
Thomas Herrmann Software - Ergonomie bei interaktiven Medien Create Meaningful Icons.
Advertisements

Attributes for Classifier Feedback Amar Parkash and Devi Parikh.
Pseudo-Relevance Feedback For Multimedia Retrieval By Rong Yan, Alexander G. and Rong Jin Mwangi S. Kariuki
Visual Vocabulary Construction for Mining Biomedical Images Arnab Bhattacharya, Vebjorn Ljosa, Jia-Yu Pan Presented by Li An, CIS, TU.
Sharing Features Between Visual Tasks at Different Levels of Granularity Sung Ju Hwang 1, Fei Sha 2 and Kristen Grauman 1 1 University of Texas at Austin,
Weakly supervised learning of MRF models for image region labeling Jakob Verbeek LEAR team, INRIA Rhône-Alpes.
Adding Unlabeled Samples to Categories by Learned Attributes Jonghyun Choi Mohammad Rastegari Ali Farhadi Larry S. Davis PPT Modified By Elliot Crowley.
A Unified Framework for Context Assisted Face Clustering
Automatic Image Annotation Using Group Sparsity
1 Copyright Jiawei Han; modified by Charles Ling for CS411a/538a Data Mining and Data Warehousing  Introduction  Data warehousing and OLAP for data mining.
Foreground Focus: Finding Meaningful Features in Unlabeled Images Yong Jae Lee and Kristen Grauman University of Texas at Austin.
CIDEr: Consensus-based Image Description Evaluation Ramakrishna Vedantam, Larry Zitnick, and Devi Parikh.
Large-Scale Object Recognition using Label Relation Graphs Jia Deng 1,2, Nan Ding 2, Yangqing Jia 2, Andrea Frome 2, Kevin Murphy 2, Samy Bengio 2, Yuan.
Capturing Human Insight for Visual Learning Kristen Grauman Department of Computer Science University of Texas at Austin Work with Sudheendra Vijayanarasimhan,
Beyond Mindless Labeling: Really Leveraging Humans to Build Intelligent Machines Devi Parikh Virginia Tech.
Patch to the Future: Unsupervised Visual Prediction
Lecture 31: Modern object recognition
Pose, Illumination and Expression Invariant Pairwise Face-Similarity Measure via Doppelganger List Comparison Author: Florian Schroff, Tali Treibitz, David.
LOCUS (Learning Object Classes with Unsupervised Segmentation) A variational approach to learning model- based segmentation. John Winn Microsoft Research.
Facial feature localization Presented by: Harvest Jang Spring 2002.
Relative Attributes Presenter: Shuai Zheng (Kyle) Supervised by Philip H.S. Torr Author: Devi Parikh (TTI-Chicago) and Kristen Grauman (UT-Austin)
Beyond bags of features: Adding spatial information Many slides adapted from Fei-Fei Li, Rob Fergus, and Antonio Torralba.
Research Update and Future Work Directions – Jan 18, 2006 – Ognjen Arandjelović Roberto Cipolla.
Agenda Introduction Bag-of-words models Visual words with spatial location Part-based models Discriminative methods Segmentation and recognition Recognition-based.
Hanwang Zhang 1, Zheng-Jun Zha 2, Yang Yang 1, Shuicheng Yan 1, Yue Gao 1, Tat-Seng Chua 1 1: National University of Singapore 2: Institute of Intelligent.
From Edges to Objects Piotr Dollár and Larry Zitnick.
Unsupervised Learning of Categories from Sets of Partially Matching Image Features Kristen Grauman and Trevor Darrel CVPR 2006 Presented By Sovan Biswas.
Unsupervised Learning of Hierarchical Spatial Structures Devi Parikh, Larry Zitnick and Tsuhan Chen.
Overcoming Dataset Bias: An Unsupervised Domain Adaptation Approach Boqing Gong University of Southern California Joint work with Fei Sha and Kristen Grauman.
AUTOMATIC ANNOTATION OF GEO-INFORMATION IN PANORAMIC STREET VIEW BY IMAGE RETRIEVAL Ming Chen, Yueting Zhuang, Fei Wu College of Computer Science, Zhejiang.
Exploiting Ontologies for Automatic Image Annotation M. Srikanth, J. Varner, M. Bowden, D. Moldovan Language Computer Corporation
Computer Vision CS 776 Spring 2014 Recognition Machine Learning Prof. Alex Berg.
Marcin Marszałek, Ivan Laptev, Cordelia Schmid Computer Vision and Pattern Recognition, CVPR Actions in Context.
Learning Models for Object Recognition from Natural Language Descriptions Presenters: Sagardeep Mahapatra – Keerti Korrapati
Lecture 31: Modern recognition CS4670 / 5670: Computer Vision Noah Snavely.
Enhancing Human-Machine Communication via Visual Attributes Devi Parikh Virginia Tech.
Semantic Embedding Space for Zero ­ Shot Action Recognition Xun XuTimothy HospedalesShaogang GongAuthors: Computer Vision Group Queen Mary University of.
Using Interactive Evolution for Exploratory Data Analysis Tomáš Řehořek Czech Technical University in Prague.
Sharing Features Between Objects and Their Attributes Sung Ju Hwang 1, Fei Sha 2 and Kristen Grauman 1 1 University of Texas at Austin, 2 University of.
C. Lawrence Zitnick Microsoft Research, Redmond Devi Parikh Virginia Tech Bringing Semantics Into Focus Using Visual.
Object Recognition a Machine Translation Learning a Lexicon for a Fixed Image Vocabulary Miriam Miklofsky.
INTERACTIVELY BROWSING LARGE IMAGE DATABASES Ronald Richter, Mathias Eitz and Marc Alexa.
Competence Centre on Information Extraction and Image Understanding for Earth Observation 29th March 2007 Category - based Semantic Search Engine 1 Mihai.
Probabilistic Latent Query Analysis for Combining Multiple Retrieval Sources Rong Yan Alexander G. Hauptmann School of Computer Science Carnegie Mellon.
EE4-62 MLCV Lecture Face Recognition – Subspace/Manifold Learning Tae-Kyun Kim 1 EE4-62 MLCV.
Week 10 Presentation Wesna LaLanne - REU Student Mahdi M. Kalayeh - Mentor.
Image Classification for Automatic Annotation
WhittleSearch: Image Search with Relative Attribute Feedback CVPR 2012 Adriana Kovashka Devi Parikh Kristen Grauman University of Texas at Austin Toyota.
Colors of Pigment The primary colors of pigment are magenta, cyan, and yellow. [
Recognition Using Visual Phrases
Object-Graphs for Context-Aware Category Discovery Yong Jae Lee and Kristen Grauman University of Texas at Austin 1.
Context Neelima Chavali ECE /21/2013. Roadmap Introduction Paper1 – Motivation – Problem statement – Approach – Experiments & Results Paper 2 Experiments.
Learning Photographic Global Tonal Adjustment with a Database of Input / Output Image Pairs.
Interactively Discovery of Attributes Vocabulary Devi Parikh and Kristen Grauman.
PANDA: Pose Aligned Networks for Deep Attribute Modeling Ning Zhang 1,2 Manohar Paluri 1 Marć Aurelio Ranzato 1 Trevor Darrell 2 Lumbomir Boudev 1 1 Facebook.
Vector GIS. GIS 2 Graphic Features on the World Copyright – Kristen S. Kurland, Carnegie Mellon University.
Analyzing the Behavior of Deep Models Dhruv Batra Devi Parikh Aishwarya Agrawal (EMNLP 2016)
This is a frog. This is a green frog..
Data Driven Attributes for Action Detection
An Additive Latent Feature Model
Chen Jimena Melisa Parodi Menashe Shalom
Object detection as supervised classification
Thesis Advisor : Prof C.V. Jawahar
Accounting for the relative importance of objects in image retrieval
Object-Graphs for Context-Aware Category Discovery
What Color is it?.
John H.L. Hansen & Taufiq Al Babba Hasan
AHED Automatic Human Emotion Detection
Zeroshot Learning Mun Jonghwan.
Face Detection Gender Recognition 1 1 (19) 1 (1)
Presentation transcript:

Richer Human-Machine Communication in Attributes-based Visual Recognition Devi Parikh TTIC

Traditional Recognition DogChimpanzeeTiger ???

Attributes-based Recognition Furry White Black Big Stripped Yellow Stripped Black White Big TigerChimpanzeeDog

Applications Zebra A Zebra is… White Black Stripped Zero-shot learning Image description Stripped Black White Big Attributes provide a mode of communication between humans and machines!

Agenda Enriching the mode of communication Nameable and Discriminative Attributes (to appear CVPR 2011) Relative Attributes (under review) Kristen Grauman

Attributes Attributes are most useful if they are Discriminative Nameable ApproachesDiscriminativ e Nameable

Attributes Attributes are most useful if they are Discriminative Nameable ApproachesDiscriminativ e Nameable Hand- generated Maybe notYes

Attributes Attributes are most useful if they are Discriminative Nameable ApproachesDiscriminativ e Nameable Hand- generated Maybe notYes Mining the webMaybe notYes

Attributes Attributes are most useful if they are Discriminative Nameable ApproachesDiscriminativ e Nameable Hand- generated Maybe notYes Mining the webMaybe notYes Automatic splitsYesMaybe not

Attributes Attributes are most useful if they are Discriminative Nameable ApproachesDiscriminativ e Nameable Hand- generated Maybe notYes Mining the webMaybe notYes Automatic splitsYesMaybe not ProposedYes

Interactive system 1. Name: Fluffy 2. Name: x 3. Name: Metal … How do we show the user a candidate-attribute? How do we ensure proposals are discriminative? How do we ensure proposals are nameable?

Attribute visualization

Attribute Visualization

Ensure Discriminability Normalized cuts Max Margin Clustering

Ensure Nameability 1. Name: Fluffy 2. Name: x 3. Name: Metal …

Ensure Nameability 1. Name: Fluffy 2. Name: x 3. Name: Metal … Mixture of Probabilistic PCA

Interactive System

Evaluation Outdoor Scenes Animals with Attributes Public Figures Face Gist and Color features (LDA)

Interactive System

Evaluation Annotate all candidates off-line “Black” … ~25000 responses

Evaluation Annotate all candidates off-line “Spotted” … ~25000 responses

Evaluation Annotate all candidates off-line Unnameable … ~25000 responses

Evaluation Annotate all candidates off-line “Green” … ~25000 responses

Evaluation Annotate all candidates off-line “Congested” … ~25000 responses

Evaluation Annotate all candidates off-line “Smiling” … ~25000 responses

Results Our active approach discovers more discriminative splits than baselines Structure exists in nameability space allowing for prediction

Results Comparing to discriminative-only baseline

Results Comparing to descriptive-only baseline

Results Automatically generated descriptions

Summary Machines need to understand us – Attributes need to be detectable & discriminative We need to understand machines – Attributes need to be nameable Interactive system for discovering attributes Relative Attributes More precise communication – Helps machines (zero-shot learning) – Helps humans (image descriptions)

Relative Attributes

Summary Machines need to understand us – Attributes need to be detectable & discriminative We need to understand machines – Attributes need to be nameable Interactive system for discovering attributes Relative Attributes More precise communication – Helps machines (zero-shot learning) – Helps humans (image descriptions)

Human-Debugging Larry Zitnick (CVPR 2008, 2010, 2011, under review, in progress)

Thank you.