13.6.8 Context in Computer Vision

Strat, T.M., and Fischler, M.A.,
Context-Based Vision: Recognizing Objects Using Information from Both 2-D and 3-D Imagery,
PAMI(13), No. 10, October 1991, pp. 1050-1065.
IEEE Abstract. IEEE Top Reference.
WWW Version. System: Condor. BibRef 9110
Earlier:
A Context-Based Recognition System for Natural Scenes and Complex Domains,
DARPA90(456-472). BibRef
Earlier: A2, A1:
Recognizing Objects in a Natural Environment: A Contextual Vision System,
DARPA89(774-796). BibRef
And:
Context-Based Vision: Recognition of Natural Scenes,
Asilomar89(532-536). System: CVS. Recognition, Context Based. This discusses the current SRI high-level vision effort. Addresses: object recognition without accurate object delineation, use of contest, use of geometry, and control of complexity. Uses context sets and cliques. BibRef

Strat, T.M.,
Decision Analysis Using Belief Functions,
ApproximateR(4), No. 5, September, 1990, pp. 391-418. BibRef 9009
And: in Advances in the Dempster-Shafer Theory of Evidence, ed. by R. Yager, M. Fedrizzi, and J. Kacprzyk, John Wiley & sons, New York, 1994, pp. 275-310. See also Mathematical Theory of Evidence, A. BibRef

Strat, T.M.,
Explaining Evidential Analyses,
ApproximateR(3), No. 4, July 1989, pp. 299-353. BibRef 8907

Strat, T.M.,
Natural Object Recognition,
New York: Springer1992, 165pp. ISBN 0-387-97832-1. BibRef 9200
And: STAN-CS-91-1376, Stanford, CA, December 1990. BibRef Ph.D.Thesis. System: Condor. Rule Based Analysis. The BibRef Bookfrom his thesis on general object recognition using contextual cues. A set of processes interact through shared data structures. Each process has an associated context set, that when satisfied causes the process to run. BibRef

Strat, T.M.,
Photogrammetry and Knowledge Representation in Computer Vision,
ISPRS94Symposium on Spatial Information from Digital Photogrammetry and Computer Vision, Munich, September 1994. BibRef 9409

Strat, T.M., Fischler, M.A.,
Natural Object Recognition: A Theoretical Framework and Its Implementation,
IJCAI91(1264-1270). BibRef 9100

Strat, T.M.[Thomas M.], Fischler, M.A.[Martin A.],
The Use of Context in Vision,
Context95(xx) BibRef 9500

Strat, T.M.[Thomas M.], Fua, P.V., Connolly, C.I.,
Context-Based Vision,
Radius97(373-388). BibRef 9700

Smith, G.B., Strat, T.M.,
Information Management in a Sensor-Based Autonomous System,
DARPA87(170-177). BibRef 8700

Strat, T.M., Smith, G.B.,
Core Knowledge System: Storage and Retrieval of Inconsistent Information,
DARPA88(660-665). BibRef 8800

Strat, T.M.,
Using Context to Control Computer Vision Algorithms,
Ascona95(3-12). BibRef 9500
Earlier:
Employing Contextual Information in Computer Vision,
DARPA93(217-229). System: Condor. The use of context in understanding objects. Describes the Prolog-like language used to control algorithms in RCDE BibRef

Strat, T.M., Smith, G.B.,
The Management of Spatial Information in a Mobile Robot,
SRMSF87(240-249). BibRef 8700

Lowrance, J., Strat, T.M., Wesley, L.P., Garvey, T.D., and Ruspini, E.,
The Theory, Implementation, and Practice of Evidential Reasoning,
Final Report, SRIProject 5701, June 1991. BibRef 9106

Lowrance, J., Ruspini, E., and Strat, T.M.,
Understanding Evidential Reasoning,
SRI-TN-501, January 1991. BibRef 9101

Bell, B., Pau, L.F.,
Context Knowledge and Search Control Issues in Object-Oriented Prolog-Based Image Understanding,
PRL(13), 1992, pp. 279-290. BibRef 9200

Pau, L.F.,
Context Related Issues in Image Understanding,
HPRCV97(Chapter IV:3). (Digital Equipment Europe) BibRef 9700

Liedtke, C.E., Bückner, J., Pahl, M., Stahlhut, O.,
Knowledge Based System for the Interpretation of Complex Scenes,
Ascona01(3-12). Combine various features for roads and buildings. 0201
BibRef

Bückner, J., Pahl, M., Stahlhut, O., Liedtke, C.E.,
A Knowledge-Based System for Context Dependent Evaluation of Remote Sensing Data,
DAGM02(58 ff.).
HTML Version. 0303
BibRef

Bückner, J.[Jürgen], Pahl, M.[Martin], Stahlhut, O.[Oliver],
Semantic Interpretation of Remote Sensing Data,
PCV02(A: 62). 0305
BibRef

Vailaya, A.[Aditya], Zhang, H.J.[Hong-Jiang], Yang, C.J.[Chang-Jiang], Liu, F.I.[Feng-I], Jain, A.K.[Anil K.],
Automatic image orientation detection,
IP(11), No. 7, July 2002, pp. 746-755.
IEEE DOI Link 0207
BibRef
Earlier: A1, A2, A5 Only: ICIP99(II:600-604).
IEEE Abstract. IEEE Top Reference. Find the orientation of the natural image using features. BibRef

Zhou, G.D.[Guo-Dong],
Direct modelling of output context dependence in discriminative hidden Markov model,
PRL(26), No. 5, April 2005, pp. 545-553.
WWW Version. 0501
BibRef

Luo, J.B.[Jie-Bo], Boutell, M.R.[Matthew R.],
Automatic Image Orientation Detection via Confidence-Based Integration of Low-Level and Semantic Cues,
PAMI(27), No. 5, May 2005, pp. 715-726.
IEEE Abstract. IEEE Top Reference. 0501
BibRef
Earlier:
A Probabilistic Approach to Image Orientation Detection via Confidence-Based Integration of Low-Level and Semantic Cues,
MMDE04(141).
IEEE DOI Link 0406
How to display random collections of (consumer) images in the correct orientation. Low level cues are not sufficient. BibRef

Boutell, M.R.[Matthew R.], Luo, J.B.[Jie-Bo],
Bayesian fusion of camera metadata cues in semantic scene classification,
CVPR04(II: 623-630).
IEEE Abstract. IEEE Top Reference. 0408
Use camera metadata to aid classification (e.g. exposure time). BibRef

Xiang, T.[Tao], Gong, S.G.[Shao-Gang],
Model Selection for Unsupervised Learning of Visual Context,
IJCV(69), No. 2, August 2006, pp. 181-201.
Springer DOI Link 0606
Choosing the model for learning. Bayesian Information Criterion. (small data sets) Completed Likelihood Akaike's Information Criterion. (otherwise) BibRef

Wolf, L.[Lior], Bileschi, S.M.[Stanley M.],
A Critical View of Context,
IJCV(69), No. 2, August 2006, pp. 251-261.
Springer DOI Link 0606
Use context to select locations likely to contain particular objects. BibRef

Wolf, L.[Lior], Bileschi, S.M.[Stan M.], Meyers, E.[Ethan],
Perception Strategies in Hierarchical Vision Systems,
CVPR06(II: 2153-2160).
IEEE DOI Link 0606
BibRef

Bileschi, S.M.[Stanley M.],
StreetScenes: Towards Scene Understanding in Still Images,
Ph.D.Thesis, May 2006, MIT.
PDF Version. BibRef 0605

Bileschi, S.M.[Stanley M.],
CBCL StreetScenes Challenge Framework,
Online2007.
WWW Version. Dataset, Object Detection. Primarily for Cars, people, and street scenes. Data is labeled. BibRef 0700

Hoiem, D.[Derek], Efros, A.A.[Alexei A.], Hebert, M.[Martial],
Recovering Surface Layout from an Image,
IJCV(75), No. 1, October 2007, pp. 151-172.
Springer DOI Link 0709
BibRef
Earlier:
Geometric Context from a Single Image,
ICCV05(I: 654-661).
IEEE DOI Link 0510
Kanade issue. Coarse properties (ground plane, sky, planar regions) from one image. Probabilistic approach to estimate 3D geometry so that not every possible view is needed. BibRef

Quickly determine the approximate surface structure from variety of cues.

Hoiem, D.[Derek], Efros, A.A.[Alexei A.], Hebert, M.[Martial],
Putting Objects in Perspective,
IJCV(80), No. 1, October 2008, pp. xx-yy.
Springer DOI Link 0809
BibRef
Earlier: CVPR06(II: 2137-2144).
IEEE DOI Link 0606
BibRef

Divvala, S.K.[Santosh K.], Efros, A.A.[Alexei A.], Hebert, M.[Martial],
Can similar scenes help surface layout estimation?,
InterNet08(1-8).
IEEE DOI Link 0806
BibRef

Hoiem, D.[Derek],
Seeing the World Behind the Image: Spatial Layout for 3D Scene Understanding,
CMU-RI-TR-07-28, August, 2007. BibRef 0708 Ph.D.Thesis.
WWW Version. BibRef

Hoiem, D.[Derek], Rother, C.[Carsten], Winn, J.[John],
3D Layout CRF for Multi-View Object Class Recognition and Segmentation,
CVPR07(1-8).
IEEE DOI Link 0706
BibRef

Bauckhage, C., Wachsmuth, S., Hanheide, M., Wrede, S., Sagerer, G.F., Heidemann, G., Ritter, H.,
The visual active memory perspective on integrated recognition systems,
IVC(26), No. 1, 1 January 2008, pp. 5-14.
WWW Version. 0711
Cognitive vision; Contextual reasoning; Fusion; Architecture; System integration BibRef

Carbonetto, P.[Peter], Dorkó, G.[Gyuri], Schmid, C.[Cordelia], Kück, H.[Hendrik], de Freitas, N.[Nando],
Learning to Recognize Objects with Little Supervision,
IJCV(77), No. 1-3, May 2008, pp. 219-237.
Springer DOI Link 0803
BibRef
Earlier:
A Semi-supervised Learning Approach to Object Recognition with Spatial Integration of Local Features and Segmentation Cues,
CLOR06(277-300).
Springer DOI Link 0711
BibRef

Kück, H.[Hendrik], Hoffman, M.[Matt], Doucet, A.[Arnaud], de Freitas, N.[Nando],
Inference and Learning for Active Sensing, Experimental Design and Control,
IbPRIA09(1-10).
Springer DOI Link 0906
BibRef

Carbonetto, P.[Peter], de Freitas, N.[Nando], Barnard, K.[Kobus],
A Statistical Model for General Contextual Object Recognition,
ECCV04(Vol I: 350-362).
WWW Version. 0405
Given the image and captions (or descriptions) learn the spatial relationships. BibRef

Kück, H.[Hendrik], Carbonetto, P.[Peter], de Freitas, N.[Nando],
A Constrained Semi-supervised Learning Approach to Data Association,
ECCV04(Vol III: 1-12).
WWW Version. 0405
Show how a wide class of data association tasks arising in computer vision can be interpreted as a constrained semi-supervised learning problem. BibRef

Li, L.J.[Li-Jia], Socher, R.[Richard], Fei-Fei, L.[Li],
Towards total scene understanding: Classification, annotation and segmentation in an automatic framework,
CVPR09(2036-2043).
IEEE DOI Link 0906
Classify general category, segment and annotate individual objects (regions and patches). Apply to 3 sports scenes. BibRef

Divvala, S.K.[Santosh K.], Hoiem, D.[Derek], Hays, J.H.[James H.], Efros, A.A.[Alexei A.], Hebert, M.[Martial],
An empirical study of context in object detection,
CVPR09(1271-1278).
IEEE DOI Link 0906
BibRef

Lazebnik, S.[Svetlana], Raginsky, M.[Maxim],
An empirical Bayes approach to contextual region classification,
CVPR09(2380-2387).
IEEE DOI Link 0906
BibRef

Munoz, D.[Daniel], Bagnell, J.A.[J. Andrew], Vandapel, N.[Nicolas], Hebert, M.[Martial],
Contextual classification with functional Max-Margin Markov Networks,
CVPR09(975-982).
IEEE DOI Link 0906
BibRef

Chong, W.[Wang], Blei, D.[David], Fei-Fei, L.[Li],
Simultaneous image classification and annotation,
CVPR09(1903-1910).
IEEE DOI Link 0906
Class label is a global descriptor, annotation is local descriptor. BibRef

Rabinovich, A.[Andrew], Belongie, S.J.[Serge J.],
Scenes vs. objects: A comparative study of two approaches to context based recognition,
VCL-ViSU09(92-99).
IEEE DOI Link 0906
BibRef

Zhou, N.[Ning], Cheung, W.K.[William K.], Xue, X.Y.[Xiang-Yang], Qiu, G.P.[Guo-Ping],
Collaborative and content-based image labeling,
ICPR08(1-4).
IEEE DOI Link 0812
BibRef

Dong, L.[Le], Izquierdo, E.[Ebroul],
Global-to-local oriented perception on blurry visual information,
ICIP08(2168-2171).
IEEE DOI Link 0810
BibRef

McDaniel, T.L.[Troy L.], Kahol, K.[Kanav], Panchanathan, S.[Sethuraman],
A Bayesian Approach to Visual Size Classification of Everyday Objects,
ICPR06(II: 255-259).
WWW Version. 0609
BibRef

Kumar, S.[Sanjiv], Hebert, M.[Martial],
A Hierarchical Field Framework for Unified Context-Based Classification,
ICCV05(II: 1284-1291).
IEEE DOI Link 0510
BibRef

Kumar, S.[Sanjiv],
Models for Learning Spatial Interactions in Natural Images for Context-Based Classification,
CMU-CS-05-28, Robotics Institute, August, 2005.
WWW Version. BibRef 0508

Morgenstern, C.[Christian], Heisele, B.[Bernd],
Component based recognition of objects in an office environment,
MIT AIM-2003-024, November 28, 2003.
WWW Version. 0501
BibRef

Schlecht, J.[Joseph], Barnard, K.[Kobus], Pryor, B.[Barry],
Statistical Inference of Biological Structure and Point Spread Functions in 3D Microscopy,
3DPVT06(373-380).
IEEE DOI Link 0606
BibRef

Louie, J.[Jennifer],
A Biological Model of Object Recognition with Feature Learning,
MIT AI-TR-2003-009, May 28, 2003. BibRef 0305 Ph.D.Thesis. 2003.
WWW Version. This thesis presents a new model that integrates learning of object-specific features with the HMAX of Riesenhuber and Poggio 0306
BibRef

Serre, T.[Thomas],
Learning a Dictionary of Shape-Components in Visual Cortex: Comparison with Neurons, Humans and Machines,
CSAIL-2006-028, April 2006.
WWW Version. BibRef 0604

Serre, T.[Thomas], Wolf, L.[Lior], Poggio, T.[Tomaso],
A new biologically motivated framework for robust object recognition,
MIT AIM-2004-026, November 14, 2004.
WWW Version. 0501
BibRef

Serre, T.[Thomas], Riesenhuber, M.[Maximilian], Louie, J.[Jennifer], Poggio, T.[Tomaso],
On the Role of Object-Specific Features for Real World Object Recognition in Biological Vision,
BMCV02(387 ff.).
HTML Version. 0303
See also Robust Object Recognition with Cortex-Like Mechanisms. BibRef

Pinhanez, C.[Claudio], Bobick, A.F.[Aaron F.],
Using Approximate Models as Source of Contextual Information for Vision Processing,
Context95(xx) BibRef 9500

Hild, M., and Shirai, Y.,
Interpretation of Natural Scenes Using Multi-Parameter Default Models and Qualitative Constraints,
ICCV93(497-501).
IEEE DOI Link Looks like a basic recognition scheme like early Ohta work and UMass work. BibRef 9300

Kadono, K., Asada, M., Shirai, Y.,
Context-Constrained Matching of Hierarchical CAD-Based Models for Outdoor Scene Interpretation,
CADBV91(186-195). BibRef 9100

Hild, M., Shirai, Y., Asada, M.,
Initial Segmentation For Knowledge Indexing,
ICPR92(I:587-590).
IEEE DOI Link BibRef 9200

Chapter on Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants continues in
Context Supplied by Text or Language .