Oliva, Aude - Department of Brain and Cognitive Science, Massachusetts Institute of Technology (MIT)

Advanced Search

Oliva, Aude - Department of Brain and Cognitive Science, Massachusetts Institute of Technology (MIT)

Not all scene categories are created equal: the role of object and spatial layout in scene gist Aude Oliva 1, Talia Konkle 1, Michelle R Greene 1 & Antonio Torralba 2
ESTIMATION OF SIGNAL INFORMATION CONTENT FOR CLASSIFICATION John W. Fisher III1
54 communicationS of the acm | OcTOber 2010 | VOL. 53 | nO. 10 contributedarticles
Shape Recipes: Scene Representations that Refer to the Image
Consistent and Efficient Reconstruction of Latent Tree Models
3548 IEEE TRANSACTIONS ON SIGNAL PROCESSING, VOL. 56, NO. 8, AUGUST 2008 Sparse Representation in Structured Dictionaries
Vision Research 46 (2006) 17621776 www.elsevier.com/locate/visres
Talia Konkle May 2011 Department of Brain and Cognitive Sciences (617) 308-6291
Computer Science and Artificial Intelligence Laboratory Technical Report
1012 IEEE TRANSACTIONS ON SIGNAL PROCESSING, VOL. 58, NO. 3, MARCH 2010 Gaussian Multiresolution Models: Exploiting Sparse
Computer Science and Artificial Intelligence Laboratory Technical Report
Vision Research 40 (2000) 14691487 Seeing, sensing, and scrutinizing
How long to get to the ``gist'' of real-world natural scenes?
Simpsons quote Network Executive: We at the network want a dog with
265 Massachusetts Ave., Cambridge, MAweb.mit.edu/museum/programs/festival Cambridge Science Festival Events
96:3492-3505, 2006. First published Sep 20, 2006; doi:10.1152/jn.00575.2006J Neurophysiol Stephen V. David, Benjamin Y. Hayden and Jack L. Gallant
A feedforward architecture accounts for rapid categorization
Recognition of facial emotion in low vision: A flexible usage of facial features
Abstract--We have recently completed a large-area, coded-aperture, gamma-ray imager for use in searching for radiation
validity effects, varies systematically as a function of variations in similarity. Importantly, this type of systematic variation also provides the necessary
Building a database of 3D scenes from user annotations Bryan C. Russell
MIMITT CaCaCampmpmpususus,,, BuBuBuililildididingngng 4446-6-6-30303 020202,, 43434343 VVVasasassasaarrr StStStS rererereetetet,, CaCaCaC mbmbmbririridgdgdge,e,e, MMMMAAAA 02020213131 999 hthttptptp:/:/:/://s/s/sunununss.s.mmimitt.edededuuuu Organized by
LabelMe: Online Image Annotation and Applications
A review of visual memory capacity: Beyond individual items and toward structured representations
Sharing features: efficient boosting procedures for multiclass object detection Antonio Torralba Kevin P. Murphy William T. Freeman
Incorporating Prior Information in Machine Learning by Creating Virtual Examples
Contextual Influences on Antonio Torralba
Contextual guidance of eye movements and attention in real-world scenes: The role of global features on object search
Saving energy by suppressing traffic flow instabilities
Visual Scene Perception A visual scene is commonly defined as a view of an environment comprised of objects
ISSN0249-6399 de recherche
Discrete-Continuous Optimization for Large-Scale Structure from Motion David Crandall
The Art and Frdo Durand
Gist of the Scene Studies in scene perception have shown that
Frequency Analysis in the Space-Time
Learning Visual Flows: A Lie Algebraic Approach dhlin@mit.edu
2006, Martinos Imaging Center at McGovern Institute Hazards of the MR Environment
Statistical Analysis of Global Motion Chains Jenny Yuen1
Encoding higher-order structure in visual working memory: A probabilistic model Timothy F. Brady (tfbrady@mit.edu), Joshua B. Tenenbaum (jbt@mit.edu)
Tilke Judd,Antonio Torralba, Frdo Durand Learning to predict
A Tree-Based Context Model for Object Recognition
Perception of Objects in Natural Scenes: Is It Really Attention Free? Karla K. Evans and Anne Treisman
Frdo Durand Lab for Computer Science, MIT
Spatial Constraints on Learning in Visual Search: Modeling Contextual Cuing
Using the visibility complex for radiosity computation Rachel Orti Fredo Durand Stephane Rivi`ere Claude Puech
Neuropsychologia 45 (2007) 844852 Ipsilateral corticospinal projections do not predict congenital mirror
Characterizing the shape and texture of natural objects using Active Appearance Models Krista A.Ehinger and Aude Oliva
Some Thoughts on Visibility Frdo Durand
Introduction Existence of a Perceptual Norm
2006, Martinos Imaging Center at McGovern Institute MR Suite Safety Rules
Normative Representation of Objects: Evidence for an Ecological Bias in Object Perception and Memory
Modeling global scene factors in attention Antonio Torralba
On Invariance in Hierarchical Models Jake Bouvrie, Lorenzo Rosasco, and Tomaso Poggio
Computer Science and Artificial Intelligence Laboratory Technical Report
Semantic Organization of Scenes using Discriminant Structural Templates Antonio Torralba and Aude Oliva
Diagnostic colours contribute to the early stages of scene categorization: Behavioural and
Modeling and Estimating Persistent Motion with Geometric Flows dhlin@mit.edu
Appears in Advances in Neural Information Processing Systems (NIPS) 2009. Nonparametric Bayesian Texture Learning and
Canonical views of scenes depend on the shape of the space Krista A. Ehinger (kehinger@mit.edu)
Foundations and Trends R Computer Graphics and Vision
SIFT Flow: Dense Correspondence across Different Scenes
Fixations on Low-Resolution Images Computer Science and Artificial Intelligence
Perceiving ``Outside the Box'' Occurs Early in Development: Evidence for Boundary Extension in Three-to Seven-Month-Old Infants
Giving a Research Talk Fredo Durand
Multiscale stochastic modeling for tractable inference and data assimilation q
Canonical Visual Size for Real-World Objects Talia Konkle and Aude Oliva
Tractable Bayesian Inference of Time-Series Dependence Structure Michael R. Siracusa
Natural Scene Categorization: from Humans to Computers
James DiCarlo The McGovern Institute for Brain Research
A window into MIT's fascinating world. Cutting-edge technologies, amazing holograms, and the
Modelling search for people in 900 scenes: A combined source model of eye guidance
Estimating scene typicality from human ratings and image features Krista A. Ehinger (kehinger@mit.edu)
Behavioral/Systems/Cognitive Disentangling Scene Content from Spatial Boundary
Canonical Visual Size for Real-World Objects Talia Konkle and Aude Oliva
Same dictionary can support the recognition of many
Normative Representation of Objects: Evidence for an Ecological Bias in Object Perception and Memory
Identifying the Perceptual Dimensions of Visual Complexity of Scenes Aude Oliva (oliva@mit.edu)
Depth Estimation from Image Structure Antonio Torralba and Aude Oliva
Scene-Centered Description from Spatial Envelope Properties
PLEASE SCROLL DOWN FOR ARTICLE This article was downloaded by: [Oliva, Aude]
Modeling Search for People in 900 Scenes: A combined source model of eye guidance
Modeling search for people in 900 scenes:A combined source model of eye guidance Krista A.Ehinger1
The Representation of Simple Ensemble Visual Features Outside the Focus of Attention
Learning to Share Visual Appearance for Multiclass Object Detection Ruslan Salakhutdinov, Antonio Torralba, Josh Tenenbaum
A data-driven approach for event prediction Jenny Yuen and Antonio Torralba
Exploiting Hierarchical Context on a Large Database of Object Categories Myung Jin Choi, Joseph J. Lim, Antonio Torralba, Alan S. Willsky
Learning to Predict Where Humans Look tjudd@mit.edu
Depth from Familiar Objects: A Hierarchical Model for 3D Scenes Erik B. Sudderth, Antonio Torralba, William T. Freeman, and Alan S. Willsky
Contextual Models for Object Detection Using Boosted
Learning Hierarchical Models of Scenes, Objects, and Parts Erik B. Sudderth, Antonio Torralba, William T. Freeman, and Alan S. Willsky
International Journal of Computer Vision 53(2), 169191, 2003 c 2003 Kluwer Academic Publishers. Manufactured in The Netherlands.
Context-Based Vision System for Place and Object
Statistical Context Priming for Object Detection Antonio Torralba Pawan Sinha
Schedule of Talks February1,2008
Scene Understanding Symposium February 1-2, 2007
Behavioral/Systems/Cognitive Context Familiarity Enhances Target Processing by Inferior
From zero to gist in 200 msec: The time course of scene
Natural Scene Categorization from Conjunctions of Ecological Global Properties Michelle R. Greene (mrgreene@mit.edu)
Feedforward theories of visual cortex predict human performance
Latency, duration and codes for objects in inferior temporal cortex
Perception of objects in natural scenes and the role of
Using the Forest to see the Trees: A computational model relating
A Bayesian Generative Approach to Shape from Shading Phillip Isola
What makes an image memorable? Phillip Isola Jianxiong Xiao Antonio Torralba Aude Oliva
Image-based Street-side City Modeling Jianxiong Xiao Tian Fang Peng Zhao Maxime Lhuillier
Image-based Facade Modeling Jianxiong Xiao Tian Fang Ping Tan
ACM Reference Format Xiao, J., Fang, T., Tan, P., Zhao, P., Ofek, E., Quan, L. 2008. Image-based Faade Modeling.
ACM Reference Format Tan, P., Fang, T., Xiao, J., Zhao, P., Quan, L. 2008. Single Image Tree Modeling. ACM Trans. Graph. 27, 5,
Learning Two-View Stereo Matching Jianxiong Xiao, Jingni Chen, Dit-Yan Yeung, and Long Quan
Learning Two-View Stereo Matching Jianxiong Xiao Jingni Chen Dit-Yan Yeung Long Quan
Structuring Visual Words in 3D for Arbitrary-View Object Localization
Jianxiong XIAO, Jingdong WANG, Ping TAN, Long QUAN
Notes on writing Fredo Durand, MIT CSAIL
Photography 101 Fredo Durand
Academy of the Sciences. March, 2, 1908 Session PHOTOGRAPHY. Reversible Prints. Integral Photographs.
Computation is the New Optics
A Fast Approximation of the Bilateral Filter using a Signal Processing Approach
The 3D Visibility Complex FR EDO DURAND
Fast and Accurate Hierarchical Radiosity Using Global Visibility
Research Statement Frdo Durand
C. Project Description Transient Signal Processing for Realistic Imagery
4300 IEEE TRANSACTIONS ON SIGNAL PROCESSING, VOL. 55, NO. 8, AUGUST 2007 Approximate Dynamic Programming for
Shape-Time Photography William T. Freeman Hao Zhang
Time to Contact Relative to a Planar Surface Berthold K.P. Horn Yajun Fang
PROOF COPY 201625APL Lensless focusing with subwavelength resolution by direct synthesis of
Cone-beam image reconstruction by moving frames
2006, Martinos Imaging Center at McGovern Institute EMERGENCY INFORMATION FOR THE MR AREA
2006, Martinos Imaging Center at McGovern Institute Screening Subjects for MRI Compatibility
2006, Martinos Imaging Center at McGovern Institute Certified to Scan Check-off List
Object decoding with attention in inferior temporal cortex
What and where: A Bayesian inference theory of attention Sharat Chikkerur *, Thomas Serre, Cheston Tan, Tomaso Poggio
Spectral Regularization for Support Estimation Ernesto De Vito
Invariant Recognition of Objects by Vision Joel Z Leibo1,2,3
A primal-dual algorithm for group sparse regularization with overlapping groups
Radiosity for dynamic scenes in flatland with the visibility complex
IntroductionIntroduction The effects of local context in visual search: a connectionist model and behavioral study of contextual cueing
Searching in dynamic displays: Effects of con gural predictability and spatiotemporal continuity
TO APPEAR AT IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 1 SIFT Flow: Dense Correspondence across
Projet de recherche Frdo Durand
LabelMe video: Building a Video Database with Human Annotations Jenny Yuen1
J N e urophysiol9 6 : 1 0 1 8 1 0 2 9 ,2 0 0 6 . First published M ay 3, 2006; doi:I 0.1152ljn.0 1358.2005
Person, place, and past influence eye movements during visual search Barbara Hidalgo-Sotelo (bhs@mit.edu)
Properties and Applications of Shape Recipes
Motion-selective recruitment of MT+ by tactile apparent motion stimuli
HighwayForestCoast Inside City Tall BuildingStreetOpenCountryMountain Oliva and Torralba, 2001
The 3D visibility complex : a new approach to the problems of accurate visibility.
acmTransactions onGraphicsDecember 2008
PRE-SCAN CHECK-OFF LIST BEFORE SUBJECT ENTERS THE MAGNET ROOM
Natural Scene Categorization from Conjunctions of Ecological Global Properties Michelle R. Greene (mrgreene@mit.edu)
Exploring Features in a Bayesian Framework for Material Recognition Lavanya Sharan2,3
Recognizing Indoor Scenes Ariadna Quattoni
MIMITT CaCaCampmpmpususus,,, BuBuBuililildididingngng 4446-6-6-30303 020202,, 43434343 VVVasasassasaarrr StStStS rererereetetet,, CaCaCaC mbmbmbririridgdgdge,e,e, MMMMAAAA 02020213131 999 hthttptptp:/:/:/://s/s/sunununss.s.mmimitt.edededuuuu Organized by
Nonparametric Scene Parsing: Label Transfer via Dense Scene Alignment Ce Liu Jenny Yuen Antonio Torralba
A Distributed Message Passing Algorithm for Sensor Localization
Myung (Jin) Choi (617) 850-2742 32 Vassar Street, 32-D570 myungjin@mit.edu
IEEE TRANSACTIONS ON SIGNAL PROCESSING, VOL. 56, NO. 10, OCTOBER 2008 4621 Low-Rank Variance Approximation in GMRF
MAXIMUM ENTROPY RELAXATION FOR MULTISCALE GRAPHICAL MODEL Myung Jin Choi, Venkat Chandrasekaran, and Alan S. Willsky
Multiscale Gaussian Graphical Models and Algorithms for Large-Scale Inference
Exploiting Hierarchical Context on a Large Database of Object Categories -Supplemental Materials -
Learning to Predict Where Humans Look Tilke Judd, Krista Ehinger, Frdo Durand,Antonio Torralba
A window into MIT's fascinating world. Cutting-edge technologies, amazing holograms, and the
[Communicative & Integrative Biology 2:1, 1-3; January/February 2009]; 2009 Landes Bioscience 1 Communicative & Integrative Biology 2009; Vol. 2 Issue 1
www.landesbioscience.com Communicative & Integrative Biology 479 Communicative & Integrative Biology 2:6, 479-481; November/December 2009; 2009 Landes Bioscience
Current Biology, Volume 19 Supplemental Data
6 Representing, perceiving and remembering the shape of visual
Talia Konkle & Aude Oliva Organizing Object Knowledge by Real-World Size
Background Does learning affect the speed of encoding? Brady, Konkle, & Alvarez (2009). Compression in visual
small space Everyday computation of scene volume
Reconstructive Memory Biases for Object and Scene Views Talia Konkle & Aude Oliva
Efficient Coding in Visual Short-Term Memory: Evidence for an Information-Limited Capacity
QuantitativepredictionoferrorsinRSVP: Modelingthetimecourseofsuppressionduringtheattentionalblink.
Constructing Depth Information in Briefly Presented Scenes Talia Konkle, Elisa McDaniel, Michelle R. Greene, Aude Oliva
Selection of Action: Can transcranial magnetic stimulation influence hand choice in reaching? 1 Helen Wills Neuroscience Institute,Department of Psychology,University of California,Berkeley
Response Variability in a Rhythmic Tapping Task During Sub-and Suprathreshold TMS Over Motor Cortex
Sources of increased timing variability following TMS over motor cortex
Compression in visual short-term memory: Using statistical regularities to form more efficient memory representations
Locating objects in the local environment is essential for successful navigation in a complex world, and visual
Selective Disruption of Rapid Resumption Timothy Brady Justin Jung Marvin Chun
Copyright 2008 Psychonomic Society, Inc. 1366 Contextual cuing is a process by which long-term
Canonical views of scenes depend on the shape of the space Krista A. Ehinger, Ken M. Haggerty, & Aude Oliva
Building a taxonomy of visual scenes:Typicality ratings and hierarchical classification Krista A.Ehinger1
Journal of Vision (2003) 3, 440-455 http://journalofvision.org/3/6/5/ 440 Is it an animal? Is it a human face? Fast processing in
Toward Understanding Natural Language Directions Thomas Kollar*
Multidimensional Visual Statistical Learning Nicholas B. Turk-Browne, Phillip J. Isola, Brian J. Scholl, and Teresa A. Treat
Copyright 2006 by the Association for Computing Machinery, Inc. Permission to make digital or hard copies of part or all of this work for personal or
Volume 130, Number 29 tech.mit.edu Wednesday, July 7, 2010 Oldest and Largest
Detecting Faces in Impoverished Images
To appear in SIGGRAPH 2005. Texture Design Using a Simplicial Complex of Morphable Textures
Seeing the {Closed+Camouflage+Natural=Forest} for the Trees: Rapid Scene Categorization can be mediated by conjunctions of global scene properties
International Journal of Computer Vision 42(3), 145175, 2001 c 2001 Kluwer Academic Publishers. Manufactured in The Netherlands.
The role of context in object recognition
2011, Athinoula A. Martinos Imaging Center at McGovern Institute Athinoula A. Martinos Imaging Center
Human Learning of Contextual Priors for Object Search: Where does the time go?
DOI: 10.1126/science.1117593 , 863 (2005);310Science
Journal of Machine Learning Research 1 (2011) 1-48 Submitted 4/00; Published 10/00 Learning Latent Tree Graphical Models
Contextual Guidance of Eye Movements and Attention in Real-World Scenes: The Role of Global Features in Object Search
The Art and Science of Depiction Fredo Durand
BOOKS ET AL. www.sciencemag.org SCIENCE VOL 329 27 AUGUST 2010 1017
Describing Visual Scenes using Transformed Dirichlet Processes
TOP-DOWN CONTROL OF VISUAL ATTENTION IN OBJECT DETECTION Cognitive Science, MSU
Olivia Carter1,2, Talia Konkle3, Qi Wang4, Vincent Hayward5, & Chris Moore3. Results: Visual and Tactile Rivalry
PROOF COPY 275614APL Multibeam interferometric illumination as the primary source of resolution
Running Protocols Tips for scanning on the Siemens Tim Trio Scanner
Computer Science and Artificial Intelligence Laboratory Technical Report
COGNITIVE PSYCHOLOGY 34, 72107 (1997) ARTICLE NO. CG970667
Using machine learning to predict where people look
Recognition using Regions Chunhui Gu, Joseph J. Lim, Pablo Arbelaez, Jitendra Malik
Hybrid Images Aude Oliva & Antonio Torralba
IEEE TRANSACTIONS ON SIGNAL PROCESSING, VOL. 58, NO. 11, NOVEMBER 2010 5481 Learning Graphical Models for Hypothesis
Single Image Tree Modeling Tian Fang Jianxiong Xiao Peng Zhao Long Quan
MASSACHUSETTS INSTITUTE OF TECHNOLOGY ARTIFICIAL INTELLIGENCE LABORATORY
LabelMe: a database and web-based tool for image Bryan C. Russell, Antonio Torralba
Dr. Angry and Mr. Smile: when categorization flexibly modifies the perception of faces in
2238 IEEE TRANSACTIONS ON NUCLEAR SCIENCE, VOL. 51, NO. 5, OCTOBER 2004 Large Area Imaging Detector for Long-Range,
Cognitive Psychology 41, 176210 (2000) doi:10.1006/cogp.1999.0728, available online at http://www.idealibrary.com on
Joint Affinity Propagation for Multiple View Segmentation Jianxiong Xiao Jingdong Wang Ping Tan Long Quan
Joint Affinity Propagation for Multiple View Segmentation Jianxiong Xiao Jingdong Wang Ping Tan Long Quan
Spectral Hashing Yair Weiss1,3
Compression in visual short-term memory: Using statistical regularities to form more efficient memory representations
SCENE UNDERSTANDING SYMPOSIUM SUnS 09 FRIDAY JANUARY 30 2009
PERCEPTUAL ORGANIZATION IN SPATIAL FREQUENCY Page | 1 Spatial frequency integration during active perception: Perceptual
Automatic Registration of LIDAR and Optical Images of Urban Scenes Andrew Mastin,1,2
Computer Science and Artificial Intelligence Laboratory Technical Report
Computer Science and Artificial Intelligence Laboratory Technical Report
Computer Science and Artificial Intelligence Laboratory Technical Report
Computer Science and Artificial Intelligence Laboratory Technical Report
P. Cisek, T. Drew & J.F. Kalaska (Eds.) Progress in Brain Research, Vol. 165
Neuron, Vol. 24, 8793, September, 1999, Copyright 1999 by Cell Press Are Cortical Models Really Bound Review
Image Representations for Visual Learning David Beymer and Tomaso Poggio*
http://pss.sagepub.com/ Psychological Science
Harrisjen: "CHAP14" --2011/3/11 --19:40 --page 308 --#1 Representing, perceiving, and
Life after the PhD Frdo Durand
Exploiting Hierarchical Context on a Large Database of Object Categories Myung Jin Choi, Joseph J. Lim, Antonio Torralba, Alan S. Willsky
MIT MUSEUM PRESS RELEASE Date: January 25, 2008
Peer Review Frdo Durand
Complete Functional Characterization of Sensory
Object and Event Recognition for Aerial Surveillance Yi Li, Indriyati Atmosukarto, Masaharu Kobashi, Jenny Yuen and Linda G. Shapiro
Fixations on Low-resolution Images Tilke Judd, Frdo Durand, Antonio Torralba
1 Infinite Images: Creating 2 and Exploring a Large
Remembering Thousands of Objects with High Fidelity Massive Memory I Massive Memory II Category Distinctiveness
Barbara Hidalgo-Sotelo (MIT)Naomi M.Kenner (MIT,BWH) Aude Oliva (MIT) Rapid goal-directed exploration of a scene: Scene context and salience
To appear in the ACM SIGGRAPH conference proceedings Hybrid images
2006, Martinos Imaging Center at McGovern Institute MR SYSTEM OPERATION AND SAFETY TRAINING
Rectilinear Parsing of Architecture in Urban Environment , Tian Fang1
Realisme et representation de la realite Fredo Durand
Experimental Analysis of BRDF Models -Supplemental Addy Ngan, Frdo Durand and Wojciech Matusik
Multiple View Semantic Segmentation for Street View Images Jianxiong Xiao Long Quan
Found Comput Math (2010) 10: 455479 DOI 10.1007/s10208-010-9064-2
This article appeared in a journal published by Elsevier. The attached copy is furnished to the author for internal non-commercial research
0 200 400 600 800 View agreement vs. scene area
Experimental evaluation of support vector machine-based and correlation-based approaches to automatic particle selection
Control Experiments A shallow RBM tends to learn hidden units that are strongly connected to
B. Yao*, A. Khosla* and L. Fei-Fei. "Combining Randomization and Discrimination for Fine-
Transfer Learning by Borrowing Examples for Multiclass Object Detection
Isola, Parikh, Torralba, and Oliva. Understanding the intrinsic memorability of images. NIPS 2011 preprint. Understanding the Intrinsic Memorability of Images
IMAGE-BASED BUILDING MODELING JIANXIONG XIAO
1 INTRODUCTION 1 Video Annotation and Tracking with Active Learning
Nonparametric Scene Parsing via Label Transfer
Transfer Learning by Borrowing Examples for Multiclass Object Detection
Understanding Natural Language Commands for Robotic Navigation and Mobile Manipulation
Toward Understanding Natural Language Directions Thomas Kollar*
Utilizing object-object and object-scene context when planning to find things
Microsoft Research Technical Report MSR-TR-2011-99
Context Models and Out-of-context Objects Myung Jin Choi, Antonio Torralba, Alan S. Willsky
Our Approach In addi'on to train , another goal is to learn , which indicates how much we borrow from class for training .