MIT AI-TR
* *Massachusetts Institute of Technology, AI Lab
* 2D-3D Rigid-Body Registration of X-Ray Fluoroscopy and CT Images
* Alignment by Maximization of Mutual Information
* Analysis of the Effect of Gaussian Error in Object Recognition, An
* Attentional Selection in Object Recognition
* Biological Model of Object Recognition with Feature Learning, A
* Boundaries and Topological Algorithms
* Compact Representations for Fast Nonrigid Registration of Medical Images
* Computation of Color, The
* Computer Analysis of Visual Properties of Curved Objects
* Computer Recognition of Prismatic Solids
* Computer Recognition of Three-Dimensional Objects in a Visual Scene
* Computer System for Visual Recognition Using Active Knowledge, A
* Computing 3-D Motion in Custom Analog and Digital VLSI
* Coupled Depth/Slope Approach to Surface Reconstruction, The
* Design of Shape from Motion Constraints, The
* Early Detection of Motion Boundaries, The
* Enhanced Reality Visualization in a Surgical Environment
* Feature Extraction Without Edge Detection
* Feature Point Detection and Curve Approximation for Early Processing of Free-Hand Sketches
* Finding Edges and Lines in Images
* Finding Texture Boundaries in Images
* Gait Analysis for Classification
* Generating Semantic Descriptions from Drawings of Scenes with Shadows
* Geometric Aspects of Visual Object Recognition
* Geometry and Photometry in 3D Visual Recognition
* Hierarchical Object Recognition Using Libraries of Parameterized Model Sub-Parts
* Hierarchical Shape Description of Objects by Selection and Modification of Prototypes
* Image Irradiance Equation: Its Solution and Application, The
* Implementation of a Theory of Edge Detection
* Improving Multi-class Text Classification with Naive Bayes
* Internal Camera Calibration Using Rotation and Geometric Shapes
* Learning and Example Selection for Object and Pattern Detection
* Learning Shape Descriptions: Generating and Generalizing Models of Visual Objects
* Learning Structural Descriptions from Examples
* Local Rotational Symmetries
* Marvel: A System for Recognizing World Locations with Stereo Vision
* Mid-Level Vision and Recognition of Non-Rigid Objects
* Modern Differential Geometric Approach to Shape from Shading, A
* Natural Object Categorization
* Object Recognition with Pictorial Structures
* On Interpreting Stereo Disparity
* Polynomial-Time Geometric Matching for Object Recognition
* Pose-Invariant Face Recognition Using Real and Virtual Views
* Probabilistic Solution of Inverse Problems
* Recognizing 3-D Objects Using 2-D Images
* Reflectance Map Techniques for Analyzing Surface Defects in Metal Casings
* Region-Based Feature Interpretation for Recognizing 3-D Models in 2-D Images
* Representation and Detection of Shapes in Images
* Representation of Image Texture, The
* Robot Motion Vision by Fixation
* Robust 2-D Model-Based Object Recognition
* Robust and Efficient 3D Recognition by Alignment
* Robust Photo-Topography by Fusing Shape-from-Shading and Stereo
* Role of Fixation and Visual Attention in Object Recognition, The
* Role of Knowledge in Visual Shape Representation, The
* Segmentation of Brain Tissue from MR Images
* Shape from Contour
* Shape from Shading: A Method for Obtaining the Shape of a Smooth Opaque Object from One View
* SketchIT: A Sketch Interpretation Tool for Conceptual Mechanical Design
* Some Aspects of Pattern Recognition by Computer
* Specialization of Perceptual Processes
* Statistical Image-Based Shape Model for Visual Hull Reconstruction and 3D Structure Inference, A
* Statistical Object Recognition
* Stereo-Based Head Pose Tracking Using Iterative Closest Point and Normal Flow Constraint
* Study of Qualitative and Geometric Knowledge in Reasoning about Motion, A
* Surface Perception from Local Analysis of Texture and Contour
* Surface Reflectance Recognition and Real-World Illumination Statistics
* Temporal Surface Reconstruction
* Theory of Networks for Approximation and Learning, A
* Three-Dimensional Correspondence
* Three-Dimensional Motion Estimation Using Shading Information in Multiple Frames
* Three-Dimensional Recognition of Solid Objects from a Two-Dimensional Image
* Towards Man-Machine Interfaces: Combining Top-down Constraints with Bottom-up Learning in Facial Analysis
* Trainable System for Object Detection in Images and Video Sequences, A
* Use of Grouping in Visual Object Recognition, The
* Vector Signal Processing Approach to Color, A
* Vision, Instruction and Action
* Visual Navigation: Constructing and Utilizing Simple Maps of and Indoor Environment
79 for MIT AI-TR
MIT AI Memo
* *Massachusetts Institute of Technology, AI Lab
* 3D Object Recognition: Symmetry and Virtual Views
* 3D Pose from Three Corresponding Points Under Weak-Perspective Projection
* Affine Matching With Bounded Sensor Error: Study of Geometric Hashing and Alignment
* Against Direct Perception
* Algebraic Functions for Recognition
* Alignment of Objects with Smooth Surfaces, The
* Alignment of Objects with Smooth Surfaces: Error Analysis of the Curvature Method, The
* Ambiguities of a Motion Field
* Analysis of a Cooperative Stereo Algorithm
* Analysis of Differential and Matching Methods for Optical Flow
* Analysis of Occluding Contour
* Analysis of Visual Motion: From Computational Theory to Neuronal Mechanisms, The
* Analytical Representation of Contours
* Analyzing Natural Images: A Computational Theory of Texture Vision
* Apparent Opacity Affects Perception of Structure from Motion
* Application of the Photometric Stereo Method, An
* Approach to Object Recogniton: Aligning Pictorial Descriptions, An
* Bandpass Channels, Zero-Crossings, and Early Visual Information Processing
* Binford-Horn Line Finder, The
* Binocular Shading and Visual Surface Reconstruction
* Boosting Image Database Retrieval
* Boundaries of Visual Motion
* Bringing the Grandmother Back into the Picture: A Memory-Based View of Pattern Recognition
* Calculating the Reflectance Map
* CARTOON: A Biologically Motivated Edge Detection Algorithm
* Classifying Objects from Visual Information
* Codon Constraints on Closed 2D Shapes
* Color Vision and Image Intensities: When Are Changes Material?
* Color Vision: Representing Material Categories
* Combinatorics of Heuristic Search Termination for` Object Recognition in Cluttered Environments, The
* Combinatorics of Local Constraints in Model-Based Recognition and Localization from Sparse Data, The
* Combinatorics of Object Recognition in Cluttered Environments Using Constrained Search, The
* Complex Feature Recognition: A Bayesian Approach for Learning to Recognize Objects
* Complexity as a Scale-Space for the Medial Axis Transform
* Computation of Locally Parallel Structure
* Computation of the Velocity Field, The
* Computational Approach to Vision and Motor Control, The
* Computational Approaches to Image Understanding
* Computational Experiments with a Feature Based Stereo Algorithm
* Computational Models of Object Recognition in Cortex: A Review
* Computational Studies in the Interpretation of Structure and Motion: Summary and Extension
* Computational Study of Vision, The
* Computational Theory of Visual Surface Interpolation, A
* Computational Vision: A Critical Review
* Computations Underlying the Measurement of Visual Motion
* Computer Implementation of a Theory of Human Stereo Vision, A
* Computer Perception of Three-Dimensional Objects
* Computing Visible Surface Representations
* Conclusions from the Commodity Expert Project
* Conditions for Viewpoint Dependent Face Recognition
* Constraints on the Visual Interpretation of Surface Contours
* Constructing a Depth Map from Images
* Contour Matching Using Local Affine Transformations
* Cooperative Computation of Stereo Disparity
* Correspondence and Affine Shape from Two Orthographic Views: Motion and Recognition
* Curvature Primal Sketch, The
* Data and Model-Driven Selection Using Color Regions
* Data and Model-Driven Selection Using Parallel-Line Groups
* Decomposition of a Visual Scene into Three-Dimensional Bodies
* Dense Depth Maps from Epipolar Images
* Density Reconstruction Using Arbitrary Ray Sampling Schemes
* Describing Surfaces
* Destriping Satellite Images
* Determining Attitude of Object From Needle Map Using Extended Gaussian Image
* Determining Grasp Configurations Using Photometric Stereo and the PRISM Binocular Stereo System
* Determining Optical Flow
* Determining Shape and Reflectance Using Multiple Images
* Differential Geometry, Surface Patches and Convergence Methods
* Direct Computation of 3D Shape and Motion Invarients
* Direct Estimation of Structure and Motion from Multiple Frames
* Direct Method for Locating the Focus of Expansion, A
* Direct Methods for Estimation of Structure and Motion from Three Views
* Direct Object Recognition Using No Higher Than Second or Third Order Statistics of the Image
* Direct Passive Navigation
* Direct Passive Navigation: Analytical Solution for Planes
* Direct Passive Navigation: Analytical Solution for Quadratic Patches
* Direct Recovery of Motion and Shape in the General Case by Fixation
* Directional Selectivity and its Use in Early Visual Processing
* Disparity Gradients and Depth Scaling
* Distance Metric between 3D Models and 2D Images for Recognition and Classification
* Edge and Mean Based Image Compression
* Edge Detection
* Effect of Indexing on the Complexity of Object Recognition, The
* Efficient Correspondence Based Algorithm for 2D and 3D Model Based Recognition, An
* Empirical Comparison of SNoW and SVMs for Face Detection, An
* Estimation of Discontinuous Displacement Vector Fields with the Minimum Description Length Criterion
* Estimation of Pose and Illuminant Direction for Face Processing
* Example Based Image Analysis and Synthesis
* Example-Based Learning for View-Based Human Face Detection
* Exploring Object Perception with Random Image Structure Evolution
* Extended Gaussian Images
* Extending Guzman's SEE Program
* Extracting Salient Curves from Images: An Analysis of the Saliency Network
* Extremum Principle for Shape from Contour, An
* Face Detection in Still Gray Images
* Face Recognition from One Example View
* Face Recognition Under Varying Pose
* Fan-beam Reconstruction Methods
* Fast Object Recognition in Noisy Images Using Simulated Annealing
* Fast Perceptual Learning in Visual Hyperacuity
* Feature Correspondence by Interleaving Shape and Texture Computations
* Feature Matching for Object Localization in the Presence of Uncertainty
* Feature Selection for Face Detection
* Filling the Gaps: The Shape of Subjective Contours and a Model for their Generation
* Finding Junctions Using the Image Gradient
* Fingerprint Theorems for Zero-Crossings
* Focusing
* Generalized Ordering Constraint for Stereo Correspondence, A
* Generating and Generalizing Models of Visual Objects
* Geometric and Algebraic Aspects of 3D Affine and Projective Structures from Perspective 2D Views
* Green Theorems and Qualitative Properties of the Optical Flow
* Grouping for Recognition
* Height and Gradient from Shading
* Heterarchical Program for Recognition of Polyhedra, A
* Ill-Posed Problems and Regularization Analysis in Early Vision
* Ill-Posed Problems in Early Vision
* Image Intensity Understanding
* Implementation of a Theory for Inferring Surface Shape from Contours
* Implicit Constraints of the Primal Sketch, The
* Incremental Rigidity Scheme for Recovering Structure from Motion: Position vs. Velocity Based Formulations, The
* Indexing for Visual Recognition from a Large Model Base
* Inferring 3D Shapes from 2D Codons
* Inferring Shape from Motion Fields
* Interaction of Different Modules in Depth Perception
* Interpretation of Biological Motion, The
* Interpretation of Structure from Motion, The
* Laboratory Environment for Applications Oriented Vision and Manipulation, A
* Learning a Color Algorithm from Examples
* Learning and Reasoning by Analogy
* Learning-Based Approach to Estimation of Morphable Model Parameters
* Lens Distortion Calibration Using Point Correspondences
* Lightness Scale from Image Intensity Distributions, A
* Limitations of Geometric Hashing in the Presence of Gaussian Noise
* Limitations of Non Model-Based Recognition Schemes
* Linear Object Classes and Image Synthesis from a Single Example Image
* Localization and Positioning Using Combinations of Model Views
* Low-level Symbolic Representation of Intensity Changes in an Image, The
* Machine Recognition as Representation and Search
* Marvel: Location Recognition Using Stereo Vision
* Matching of Doubly Ambiguous Stereograms, The
* Maximizing Rigidity: The Incremental Recovery of 3-D Structure from Rigidity and Rubbery Motion
* Measurement of Visual Motion, The
* Model-Based Matching of Line Drawings by Linear Combinations of Prototypes
* Model-Based Matching of Line Drawings by Linear Combinations of Prototypes
* Model-Based Recognition and Localization from Sparse Range or Tactile Data
* Model-Group Indexing for Recognition
* Motion Estimation from Disparity Images
* Motion Field and Optical Flow: Differences and Qualitative Properties
* Multi-Level Reconstruction of Visual Surfaces: Variational Principles and Finite Element Representations
* Multi-Scale Vector-Ridge-Detection for Perceptual Organization Without Edges
* Multigrid Relaxation Methods and the Analysis of Lightness, Shading and Flow
* Non-Rigid Motion and Regge Calculus
* Nonlinear Analog Networks for Image Smoothing and Segmentation
* Novel Approach to Graphics, A
* Numerical Shape from Shading and Occluding Contours in a Single View
* Object Recognition by Alignment Using Invariant Projections of Planar Surfaces
* Occlusion Clues and Subjective Contours
* On Boundary Detection
* On Edge Detection
* On Lightness
* On the Purpose of Low-level Vision
* On the Recognition of Curved Objects
* On the Recognition of Parameterized 2-D Objects
* On the Sensitivity of the Hough Transform for Object Recognition
* On the Uniqueness of Correspondence under Orthographic and Perspective Projections
* On the Verification of Hypothesized Matches in Model-Based Recognition
* On Visual Detection of Light Sources
* Optical Flow from 1-D Correlation: Application to a Simple Time-to-Crash Detector
* Optical Flow of Planar Surfaces, The
* Optimal Scale for Edge Detection, An
* Orienting Silicon Integrated Circuit Chips for Lead Bonding
* Parallel Algorithms for Computer Vision on the Connection Machine
* Parallel and Deterministic Algorithms from MRFs: Surface Reconstruction and Integration
* Parts of Recognition
* Passive Navigation
* Pattern Motion Perception: Feature Tracking or Integration of Component Motions?
* People Recognition in Image Sequences by Supervised Learning
* Perception of Subjective Surfaces, The
* Perceptual Buildup of Three-Dimensional Structure from Motion, The
* Perceptual Organization, Figure Ground, Attention And Saliency
* Perspective Projection Invariants
* Photometric Stereo
* Picking Parts out of a Bin
* Picking up an Object from a Pile of Objects
* Plan-View Trajectory Estimation with Dense Stereo Background Models
* Polynomial-Time Object Recognition in the Presence of Clutter, Occlusions, and Uncertainty
* Primitive Recognizer of Figures in a Scene, A
* Prism Trees: An Efficient Representation for Manipulating and Displaying Polyhedra With Many Faces
* PRISM: A Practical Real-Time Imaging Stereo Matcher
* Probabilistic Solution of Ill-Posed Problems in Computational Vision
* Projective Structure from Uncalibrated Images: Structure-from-Motion and Recognition
* Quadric Reference Surface: Theory and Applications, The
* Qualitative Depth and Shape from Stereo, in Agreement with Psychophysical Evidence
* Real-Time Part Position Sensing
* Recognition and Localization of Overlapping Parts from Sparse Data
* Recognition and Structure from one 2D Model View: Observations on Prototypes, Object Classes and Symmetries
* Recognition by Linear Combinations of Models
* Recognition by Prototypes
* Recognition of Sharp, Closely Spaced Edges, The
* Recognizing 3D Objects from 2D Images: An Error Analysis
* Recognizing 3D Objects Using Photometric Invariant
* Recognizing Rigid Objects by Aligning Them with an Image
* Recognizing Three-Dimensional Objects without the Use of Models
* Recovering Heading for Visually-Guided Navigation
* Recovering Three-Dimensional Structure from Motion with Surface Reconstruction
* Reducing Drift in Parametric Motion Tracking
* Regularization Theory and Shape Constraints
* Regularized Solution to Edge Detection, A
* Relative Affine Structure: Canonical Model for 3D from 2D Geometry and Applications
* Relative Orientation
* Relaxing the Brightness Constancy Assumption in Computing Optical Flow
* Representation and Recognition of the Spatial Organization of Three-Dimensional Shapes
* Representation and Recognition of Three-Dimensional Shapes
* Representing Visual Information
* Rigidity and Smoothness of Motion
* Rotationally Symmetric Operators for Surface Interpolation
* Scaling Theorems for Zero-Crossings
* Seeing Ghost Solutions in Stereo Vision
* Self Calibration of Motion and Stereo Vision for Mobile Robot Navigation
* Sensing Strategies for Disambiguating Among Multiple Objects in Known Poses
* Shape and Source from Shading
* Shape from Regular Patterns: An Example of Constraint Propagation in Vision
* Shape from Shading, Occlusion and Texture
* Shape of Shading, The
* Smoothed Local Symmetries and Their Implementation
* Smoothest Velocity Field and Token Matching Schemes, The
* Solving the Find-Path Problem by Representing Free Space as Generalized Cones
* Some Properties of Discontinuities in the Image Irradiance Equation
* Space Efficient 3D Model Indexing
* Spatial Disposition of Axes in a Generalized Cylinder Representation of Objects that Do Not Encompass the Viewer
* Spatial Planning: A Configuration Space Approach
* Spatial Reference Frames for Object Recognition Tuning for Rotations in Depth
* Stereo and Eye Movement
* Stereo Feature Matching in Disparity Space
* Structural Saliency: The Detection of Globally Salient Structures Using a Locally Connected Network
* Structure from Stereo and Motion
* Subdivision Algorithm in Configuration Space for Findpath with Rotation, A
* Summer Vision Project, The
* Surface Reconstruction Preserving Discontinuities
* Symbolic Construction of a 2-D Scale-Space Image
* Synthesis of Visual Modules from Examples: Learning Hyperacuity
* Synthesizing Constraint Expressions
* Tactile Recognition and Localization Using Object Models: The Case of Polyhedra on a Plane
* Template Matching: Matched Spatial Filters And Beyond
* Theory of Edge Detection
* Theory of Human Stereo Vision, A
* Three-Dimensional Interpretation of a Class of Simple Line-Drawings, The
* Toward a Computational Theory of Early Visual Processing in Reading
* Toward a Surface Primal Sketch
* Towards an Example-Based Image Compression Architecture for Video-Conferencing
* Towards Autonomous Motion Vision
* Uncertainty Propagation in Model-Based Recognition
* Using Enhanced Spherical Images for Object Representation
* Using Synthetic Images to Register Real Surfaces with Surface Models
* Using the Gaussian Image to Find the Orientation of Objects
* Variational Approach to Shape from Shading, The
* Vectorizing Face Images by Interleaving Shape and Texture Computations
* View-Based Models of 3D Object Recognition and Class-Specific Invariances
* View-Based Strategies for 3D Object Recognition
* Viewpoint-specific Representations in Three-dimensional Object Recognition
* Visual Algorithms
* Visual Integration and Detection of Discontinuities: The Key Role of Intensity Edges
* Visual Routines
* Visual Tracking
* What Makes a Good Feature?
* Why Do We See Three-dimensional Objects?
* Why Stereo Vision is Not Always About 3D Reconstruction
268 for MIT AI Memo
MIT AI TR
* *Massachusetts Institute of Technology, AI Lab
* Automatically Recovering Geometry and Texture from Large Sets of Calibrated Images
MIT AI
* *Massachusetts Institute of Technology, AI Lab
* Active Knowledge
* Application of Line Labeling and Other Scene-Analysis Techniques to the Problem of Hidden-Line Removal, An
* Binford-Horn Line Finder, The
MIT AIM
* *Massachusetts Institute of Technology, AI Lab
* Biologically Plausible Neural Model for the Recognition of Biological Motion and Actions
* Component based recognition of objects in an office environment
* Context-Based Vision System for Place and Object Recognition
* Contextual models for object detection using boosted random fields
* Contextual Priming for Object Detection
* Detecting Faces in Impoverished Images
* Direction Estimation of Pedestrian from Images
* Dissociated Dipoles: Image representation via non-local comparisons
* Early Sketch Processing with Application in HMM Based Sketch Recognition
* Efficient Image Matching with Distributions of Local Invariant Features
* Evaluation of sets of oriented and non-oriented receptive fields as local descriptors
* Exploring Vision-Based Interfaces: How to Use Your Head in Dual Pointing Tasks
* Face processing in humans is compatible with a simple shape-based model of vision
* Fast Contour Matching Using Approximate Earth Mover's Distance
* Fast Pose Estimation with Parameter-Sensitive Hashing
* Gait Dynamics for Recognition and Classification
* Generalization Over Contrast and Mirror Reversal, But not Figure-ground Reversal, in an Edge-based Model of IT Neurons
* Global Depth Perception from Familiar Scene Structure
* How do Humans Determine Reflectance Properties under Unknown Illumination?
* Improving Multiclass Text Classification with the Support Vector Machine
* Inferring 3D Structure with a Statistical Image-Based Shape Model
* Learning object segmentation from video data
* Learning Object-Independent Modes of Variation with Feature Flow Fields
* Light Field Morphable Models
* Massively Parallel Implementations of Theories for Apparent Motion
* Multiple Resolution Image Classification
* new biologically motivated framework for robust object recognition, A
* Nonparametric Belief Propagation and Facial Appearance Estimation
* On the difficulty of feature-based attentional modulations in visual object recognition: A modeling study.
* Perceiving Illumination Inconsistencies in Scenes
* Perceptual Evaluation of Video-Realistic Speech
* Perceptually-based Comparison of Image Similarity Metrics
* Properties and Applications of Shape Recipes
* Range Segmentation Using Visibility Constraints
* Recognition of Surface Reflectance Properties from a Single Image under Unknown Real-World Illumination
* Recognizing Indoor Scenes
* Recovering Intrinsic Images from a Single Image
* Relative Contributions of Internal and External Features to Face Recognition
* Role of Color in Face Recognition
* Rotation Invariant Object Recognition from One Training Example
* Rotation Invariant Real-time Face Detection and Recognition System
* Shape Recipes: Scene Representations that Refer to the Image
* Shape-Time Photography
* Sharing Visual Features for Multiclass and Multiview Object Detection
* Stimulus Simplification and Object Representation: A Modeling Study
* Surface Reflectance Estimation and Natural Illumination Statistics
* Unified Statistical and Information Theoretic Framework for Multi-modal Image Registration, A
* Virtual Visual Hulls: Example-Based 3D Shape Estimation from a Single Silhouette
49 for MIT AIM
MIT Design Lab
* Cut Locus and Medial Axis in Global Shape Interrogation and Representation
MIT Press
* *Active Vision
* *Artificial Intelligence: An MIT Perspective
* *Contextual Media: Multimedia and Interpretation
* *Geometric Invariance in Computer Vision
* *Models for the Perception of Speech and Visual Form
* *Optical and Electro-Optical Info. Proc.
* *Robotics Research: The First International Symposium
* *Robotics Science
* *Shape from Shading
* *Vision, Brain, and Cooperative Computation
* 2D Object Detection and Recognition Models, Algorithms, and Networks
* 3D Model Recognition from Stereoscopic Cues
* Affective Perception
* Artificial Vision for Mobile Robots: Stereo Vision and Multisensory Perception
* Computational Models of Visual Processing
* Computational Vision: Information Processing in Perception and Visual Behavior
* Experiments in the Machine Interpretation of Visual Motion
* From Images to Surfaces: A Computational Study of the Human Early Visual System
* Geometric Reasoning
* Geometro of Multiple Images, The
* Geometry of Multiple Images: The Laws That Govern the Formation of Multiple Images of a Scene and Some of Their Applications, The
* HANDEY: A Robot Task Planner
* High-Level Motion Processing: Computational, Neurobiological, and Psychophysical Perspectives
* High-Level Vision: Object Recognition and Visual Cognition
* Image and Brain: The Resolution of the Imagery Debate
* Interpretation of Visual Motion, The
* Machine Interpretation of Line Drawings
* Measurement of Visual Motion, The
* Model-Based Image Matching Using Location
* Object Recognition by Computer: The Role of Geometric Constraints
* Object Recognition in Man, Monkey, and Machine
* Perceptrons: An Introduction to Computational Geometry
* Representation and Recognition in Vision
* Robot Vision
* Solid Shape
* Three-Dimensional Computer Vision: A Geometric Viewpoint
* Vision Science: Photons to Phenomenology
* Vision, Instruction and Action
* Visual Reconstruction
39 for MIT Press