| _ | what | _ |
|---|
| Automatic Face Recognition: | what | Representation? |
| Edge Detection: | what | About Rotation Invariance? |
| How To Do With Probabilities | what | People Say You Can'T |
| I'Ve Seen Your Demo; So | what | ? |
| Industrial Machine Vision: Where Are We? | what | Do We Need? How Do We Get It? |
| Relaxation For Point-Pattern Matching: | what | It Really Computes |
| Report Of The Aaai Fall Symposium On Machine Learning And Computer Vision: | what | , Why And How? |
| Supervised Segmentation By Pairwise Interactions: Do Gibbs Models Learn | what | We Expect? |
| what | Accuracy For 3d Measurements With Cameras |
| what | Can Be Seen In A Noisy Optical Flow Field Projected By A Moving Planar Patch In 3d Space? |
| what | Can Be Seen In Three Dimensions With An Uncalibrated Stereo Rig? |
| what | Can Projections Of Flow Fields Tell Us About The Visual Motion |
| what | Can Two Images Tell Us About A Third One? |
| what | Can Two Images Tell Us About A Third One? |
| what | Connectionist Models Learn: Learning And Representation In Connectionist Networks |
| what | Every Engineer Should Know About Artificial Intelligence, Mit Press, Cambridge |
| what | Is A Light Source? |
| what | Is A Surface? |
| what | Is A ``Degenerate'' View? |
| what | Is A ``Degenerate'' View? |
| what | Is Computed By Structure From Motion Algorithms? |
| what | Is Regular In Regularization? |
| what | Is The Center Of The Image? |
| what | Is The Set Of Images Of An Object Under All Possible Illumination Conditions? |
| what | Is The Set Of Images Of An Object Under All Possible Lighting Conditions? |
| what | Is The Spectral Dimensionality Of Illumination Functions In Outdoor Scenes? |
| what | Shadows Reveal About Object Structure |
| what | The Fourier Transform Can Really Bring To Clustering |
| what | 'S In A Mental Model? On Conceptual Models In Reasoning With Spatial Descriptions |
| what | 'S In A Set Of Points |
| what | -And-Where Filter | A Spatial Mapping Neural Network For Object Recognition And Image Understanding, The |
31 for what
| _ | when | _ |
|---|
| About The Adjective ``Neural'' | when | Applied To Smart Sensors |
| Active Exploration: Knowing | when | We'Re Wrong |
| Analysis Of The Behaviour Of Genetic Algorithms | when | Learning Bayesian Network Structure From Data |
| Condensing Image Databases | when | Retrieval Is Based On Non-Metric Distances |
| Determining The Probability Of A False Positive | when | Matching Chains Of Oriented Pixels |
| Motion Estimation: The Proper Formulation For | when | 3 Or 4 Frames Are Available |
| On The Speed And Accuracy Of Object Recognition | when | Using Imperfect Grouping |
| when | Is An Obstacle A Perfect Obstacle? |
| when | Is It Possible To Identify 3d Objects From Single Images Using Class Constraints? |
| when | Should We Consider Lens Distortion In Camera Calibration |
10 for when
| _ | where | _ |
|---|
| Active Visual Attention System To Play `` | where | 'S Waldo'', An |
| Descriptive Pattern Recognition System Applied To Pictorial Patterns | where | The Discriminating Information Is Carried In The Object Shape, A |
| How To Decide From The First View | where | To Look Next |
| How To Tell People | where | To Go: Comparing Navigational Aids |
| Industrial Machine Vision: | where | Are We? What Do We Need? How Do We Get It? |
| Let Them Fall | where | They May: Capture Regions Of Curved Objects And Polyhedra |
| Machine Vision-Algorithms, Architectures, And Systems (Proceedings Of A Workshop ``Machine Vision: | where | Are We Going'', New Brunswick, Nj, April 6-7, 1987), Academic Press |
| What-And- | where | Filter | A Spatial Mapping Neural Network For Object Recognition And Image Understanding, The |
| where | And Why Local Shading Analysis Works |
| where | To Look Next In 3d Object Search |
| where | To Look Next Using A Bayes Net: An Overview |
| where | To Look Next Using A Bayes Net: Incorporating Geometric Relations |
12 for where
| _ | which | _ |
|---|
| Algorithm | which | Automatically Constructs Discrimination Graphs In A Visual Knowledge Base, An |
| Defect-Correction Algorithm For Minimizing The Volume Of A Simple Polyhedron | which | Circumscribes A Sphere, A |
| Dense Depth Map Reconstruction: A Minimization And Regularization Approach | which | Preserves Discontinuities |
| Efficient Boundary Encoding Scheme | which | Is Optimal In The Rate-Distortion Sense, An |
| Kanji Recognition Method | which | Detects Writing Errors, A |
| Mlp-Based Texture Segmentation Technique | which | Does Not Require A Feature Set, An |
| Panel: `` | which | Computer Architecture For Image Processing?'' |
| Position Papers Presented At The Panel: | which | Parallel Architectures Are Useful/Useless For Vision Algorithms |
| Positive-Definite Matrix | which | Is Not Extendible, A |
| Quadtree Approach To Image Segmentation | which | Combines Statistical And Spatial Information, A |
| River Routing Every | which | Way, But Loose |
| which | Hough Transform? |
| which | Ranking Metric Is Optimal? With Applications In Image Retrieval And Stereo Matching |
| which | Shape From Motion? |
14 for which
| _ | why | _ |
|---|
| On Perpendicular Texture, Or: | why | Do We See More Flowers In The Distance? |
| On The Importance Of Being Asymmetric In Stereopsis | Or | why | We Should Use Skewed Parallel Cameras |
| Report Of The Aaai Fall Symposium On Machine Learning And Computer Vision: What, | why | And How? |
| Some Reasons | why | Algebraic Topology Is Important In Neuropsychology: Perceptual And Cognitive Systems As Vibrations |
| Where And | why | Local Shading Analysis Works |
| why | Aspect Graphs Are Not (Yet) Practical For Computer Vision |
| why | Direction-Giving Is Hard: The Complexity Of Using Landmarks In One-Dimensional Navigation |
| why | Linear Arrays Are Better Image Processors |
| why | Progress In Machine Vision Is So Slow |
| why | R.G.B.? Or How To Design Color Displays For Martians |
| Workshop Panel Report- | why | Aspect Graphs Are Not (Yet) Practical For Computer Vision |
11 for why