13.6.7 Integration of Vision Modules, Select Operations, Sequence Operations

Poggio, T.A., Gamble, E.B., and Little, J.J.,
Parallel Integration of Vision Modules,
Science(242), October 21, 1988, pp. 436-439. Data Fusion. Connection Machine. This is the new MIT vision system with multiple processes (motion, stereo, color, texture, edges). BibRef 8810

Poggio, T.[Tomaso],
Visual Algorithms,
MIT AI Memo-683, May 1982. BibRef 8205

Poggio, T.A., Edelman, S., and Fahle, M.,
Learning of Visual Modules from Examples: A Framework for Understanding Adaptive Visual Performance,
CVGIP(56), No. 1, July 1992, pp. 22-30.
Elsevier DOI BibRef 9207

Poggio, T.[Tomaso], Fahle, M.[Manfred], Edelman, S.[Shimon],
Fast Perceptual Learning in Visual Hyperacuity,
Science(256), 15 May 1992, pp. 1018-1021. BibRef 9205
And: MIT AI Memo-1336, December 1991.
WWW Link. BibRef

Poggio, T.[Tomaso], Fahle, M.[Manfred], Edelman, S.[Shimon],
Synthesis of Visual Modules from Examples: Learning Hyperacuity,
MIT AI Memo-1271, January 1991.
WWW Link. BibRef 9101

Weiss, Y.[Yair], Edelman, S.[Shimon], and Fahle, M.[Manfred],
Models of Perceptual Learning in Vernier Hyperacuity,
NeurComp(5), 1993, pp. 695-718. BibRef 9300

Weiss, Y.[Yair], Edelman, S.[Shimon],
Representation of Similarity as a Goal of Early Visual Processing,
WeizmannCS-TR 93-09, 1995. BibRef 9500

Edelman, S., Poggio, T.,
Bringing the Grandmother Back into the Picture: A Memory-Based View of Pattern Recognition,
PRAI(6), 1992, pp. 37-61. BibRef 9200
And: MIT AI Memo-1181, April 1990. BibRef

Aloimonos, Y., and Shulman, D.,
Learning Early-Vision Computations,
JOSA-A(6), 1989, pp. 908-919. Early Vision. BibRef 8900

Aloimonos, Y., and Shulman, D.,
Integration of Visual Modules: An Extension of the Marr Paradigm,
San Diego: Academic Press1989. Survey, Computational Vision. Computational Vision, Survey. A Chapter as a paper (first author only): BibRef 8900
Unification and Integration of Visual Modules: An Extension of the Marr Paradigm,
DARPA89(507-551). A Chapter in the above book. The goal is to provide a framework to discuss computational algorithms. Included are discontinuous regularization, etc. BibRef

Aloimonos, Y., Basu, A.,
Combining Information In Low-Level Vision,
DARPA88(862-906). BibRef 8800

Gamble, E.B.[Ed B.], Poggio, T.[Tomaso],
Visual Integration and Detection of Discontinuities: The Key Role of Intensity Edges,
MIT AI Memo-970, October 1987.
WWW Link. BibRef 8710

Gamble, E.B., Geiger, D., Poggio, T.A., and Weinshall, D.,
Integration of Vision Modules and Labeling of Surface Discontinuities,
SMC(19), No. 6, November/December 1989, pp. 1576-1581. BibRef 8911

Jepson, A.D., and Richards, W.A.,
A Lattice Framework for Integrating Vision Modules,
SMC(22), 1992, pp. 1087-1096. BibRef 9200

Clement, V., and Thonnat, M.,
A Knowledge-Based Approach to Integration of Image Processing Procedures,
CVGIP(57), No. 2, March 1993, pp. 166-184.
DOI Link OCAPI system. BibRef 9303

Thonnat, M., Clement, V., van den Elst, J.,
Supervision of Perception Tasks for Autonomous Systems: The OCAPI Approach,
JIST(3), No. 2, January 1994, pp. 140-163. BibRef 9401
And: INRIA2000, June 1993. BibRef

Maillot, N.E.[Nicolas Eric], Thonnat, M.[Monique], Boucher, A.[Alain],
Towards Ontology Based Cognitive Vision,
MVA(16), No. 1, December 2004, pp. 33-40.
Springer DOI 0501
BibRef
Earlier: CVS03(44 ff).
Springer DOI 0306
BibRef

Maillot, N.E.[Nicolas Eric], Thonnat, M.[Monique],
Ontology based complex object recognition,
IVC(26), No. 1, 1 January 2008, pp. 102-113.
Elsevier DOI 0711
Keywords: Ontology; Machine learning; Categorization; Cognitive vision BibRef

Maillot, N.E.[Nicolas E.], Thonnat, M.[Monique],
A Weakly Supervised Approach for Semantic Image Indexing and Retrieval,
CIVR05(629-638).
Springer DOI 0507
BibRef

Bozma, H.I., and Duncan, J.S.,
A Game-Theoretic Approach to Integration of Modules,
PAMI(16), No. 11, November 1994, pp. 1074-1086.
IEEE DOI BibRef 9411
Earlier:
Integration of Vision Modules: A Game-Theoretic Framework,
CVPR91(501-507).
IEEE DOI Fusion, Modules. Combine modules doing part of the task. BibRef

Bozma, H.I.[H. Isil], Duncan, J.S.[James S.],
Modular System for Image Analysis Using a Game-Theoretic Framework,
IVC(10), No. 6, July-August 1992, pp. 431-443.
Elsevier DOI BibRef 9207

Bobick, A.F., and Bolles, R.C.,
The Representation Space Paradigm of Concurrent Evolving Object Descriptions,
PAMI(14), No. 2, February 1992, pp. 146-156.
IEEE DOI BibRef 9202
Earlier: SRITechnical Note 459. February, 1992.
WWW Link. BibRef
And:
Representation Space: An Approach to the Integration of Visual Information,
CVPR89(492-499).
IEEE DOI BibRef
And: DARPA89(263-272). Discussion of different representations needed for a vision system from the initial 2-D blobs to the 3-D object. BibRef

Crowley, J.L., and Christensen, H.I.,
Integration of Visual Processes,
PRAI(7), No. 6, December 1993. BibRef 9312

Crowley, J.L.,
Integration and Control of Reactive Visual Processes,
RobAS(15), No. 1, December 1995. BibRef 9512
Earlier: Add A2, A3, A4: Bedrune, J.M., Bekker, M., Schneider, M., ECCV94(B:47-58).
Springer DOI BibRef

Drake, K.C., Kim, R.Y.,
Hierarchical Integration of Sensor Data and Contextual Information for Automatic Target Recognition,
AppIntel(5), No. 3, July 1995, pp. 269-290. BibRef 9507

Pankanti, S., Jain, A.K.,
Integrating Vision Modules: Stereo, Shading, Grouping, and Line Labeling,
PAMI(17), No. 9, September 1995, pp. 831-842.
IEEE DOI Stereo. Shape from Shading. Perceptual Grouping. Geons. BibRef 9509

Pankanti, S., Jain, A.K., Tuceryan, M.,
On Integration of Vision Modules,
CVPR94(316-322).
IEEE DOI BibRef 9400
And: A1, A2 only: MSUTR-CS, June 1994. Stereo analysis with surface normals and line labels. BibRef

Gong, L.G., Kulikowski, C.A.,
Composition of Image-Analysis Processes Through Object-Centered Hierarchical Planning,
PAMI(17), No. 10, October 1995, pp. 997-1009.
IEEE DOI BibRef 9510
Earlier:
VISIPLAN: A Hierarchical Planning Framework for Composing Biomedical Image Analysis Processes,
CVPR94(718-723).
IEEE DOI Model the composition of processes. Used for medical image analysis. BibRef

Indiveri, G., Raffo, L., Sabatini, S.P., and Bisio, G.M.,
A Neuromorphic Architecture for Cortical Multilayer Integration of Early Visual Tasks,
MVA(8), No. 5, 1995, pp. 305-314.
Springer DOI BibRef 9500

Tung, C.P., Kak, A.C.,
Integrating Sensing, Task Planning, and Execution for Robotic Assembly,
RA(12), No. 2, April 1996, pp. 187-201. BibRef 9604

Hwang, S.Y.[Shu-Yuen], Tanimoto, S.L.[Steven L.],
Parallel Coordination of Image Operators: Model, Algorithm, and Performance,
IVC(11), No. 3, April 1993, pp. 129-138.
Elsevier DOI BibRef 9304

Ardizzone, E., Chella, A., Gaglio, S.,
Hybrid Architecture for Shape Reconstruction and Object Recognition,
IJIS(11), No. 12, December 1996, pp. 1115-1133. 9612
BibRef

Das, S.[Subhodev], Bhanu, B.[Bir], Ho, C.C.[Chih-Cheng],
Generic Object Recognition Using Multiple Representations,
IVC(14), No. 5, June 1 1996, pp. 323-338.
Elsevier DOI 9607
BibRef

Murino, V., Foresti, G.L., Regazzoni, C.S.,
A Distributed Probabilistic System for Adaptive Regulation of Image-Processing Parameters,
SMC-B(26), No. 1, February 1996, pp. 1-20.
IEEE Top Reference. BibRef 9602

Murino, V.[Vittorio], Peri, M.F.[Massimiliano F.], Regazzoni, C.S.[Carlo S.],
Distributed belief revision for adaptive image processing regulation,
ECCV92(87-91).
Springer DOI 9205
BibRef

Foresti, G.L., Regazzoni, C.S.,
A Real-Time Model-Based Method for 3-D Object Orientation Estimation in Outdoor Scenes,
SPLetters(4), No. 9, September 1997, pp. 248-251.
IEEE Top Reference. 9709
BibRef

Clouard, R.[Regis], El Moataz, A.[Abderrahim], Porquet, C.[Christine], Revenu, M.[Marinette],
Borg: A Knowledge-Based System for Automatic Generation of Image Processing Programs,
PAMI(21), No. 2, February 1999, pp. 128-144.
IEEE DOI User describes task, generate the plan. Chains of image processing programs. BibRef 9902

Ortiz, M.J., Formaggio, A.R., Epiphanio, J.C.N.,
Classification of Croplands Through Integration of Remote-Sensing, GIS, and Historical Database,
JRS(18), No. 1, January 10 1997, pp. 95-105. 9701
Remote Sensing. BibRef

Takatsuka, M.[Masahiro], Caelli, T.M.[Terry M.], West, G.A.W.[Geoff A.W.], Venkatesh, S.[Svetha],
An Application of 'Agent-Oriented' Techniques to Symbolic Matching and Object Recognition,
PRL(23), No. 4, February 2002, pp. 419-429.
Elsevier DOI 0202
Combine the results from multiple agents for recognition. BibRef

Privitera, C.M., Stark, L.W.,
Human-vision-based selection of image processing algorithms for planetary exploration,
IP(12), No. 8, August 2003, pp. 917-923.
IEEE DOI 0308
BibRef

Lai, K.T.[Kuan-Ting], Liu, D.[Dong], Chang, S.F.[Shih-Fu], Chen, M.S.[Ming-Syan],
Learning Sample Specific Weights for Late Fusion,
IP(24), No. 9, September 2015, pp. 2772-2783.
IEEE DOI 1506
Accuracy BibRef

Liu, D.[Dong], Lai, K.T.[Kuan-Ting], Ye, G.[Guangnan], Chen, M.S.[Ming-Syan], Chang, S.F.[Shih-Fu],
Sample-Specific Late Fusion for Visual Category Recognition,
CVPR13(803-810)
IEEE DOI 1309
graph; infinite push; late fusion; ranking BibRef

Jiang, H., Tian, Q., Farrell, J., Wandell, B.A.,
Learning the Image Processing Pipeline,
IP(26), No. 10, October 2017, pp. 5032-5042.
IEEE DOI 1708
Cameras, Computer architecture, Image color analysis, Pipelines, Rendering (computer graphics), Transforms, Local linear learned, camera image processing pipeline, machine learning BibRef

Hu, Y.Q.[Yi-Qi], Liu, X.H.[Xu-Hui], Li, S.Q.[Shu-Qiao], Yu, Y.[Yang],
Cascaded Algorithm Selection With Extreme-Region UCB Bandit,
PAMI(44), No. 10, October 2022, pp. 6782-6794.
IEEE DOI 2209
Tuning, Task analysis, Computer aided software engineering, Machine learning algorithms, Bayes methods, Optimization methods, machine learning BibRef

Casas, S.[Sergio], Sadat, A.[Abbas], Urtasun, R.[Raquel],
MP3: A Unified Model to Map, Perceive, Predict and Plan,
CVPR21(14398-14407)
IEEE DOI 2111
Location awareness, Training, Measurement, Uncertainty, Computational modeling, Semantics, Predictive models BibRef

Lu, Y.[Yao], Pirk, S.[Sören], Dlabal, J.[Jan], Brohan, A.[Anthony], Pasad, A.[Ankita], Chen, Z.[Zhao], Casser, V.[Vincent], Angelova, A.[Anelia], Gordon, A.[Ariel],
Taskology: Utilizing Task Relations at Scale,
CVPR21(8696-8705)
IEEE DOI 2111
Training, Computational modeling, Semantics, Estimation, Prediction algorithms BibRef

Popovic, N.[Nikola], Paudel, D.P.[Danda Pani], Probst, T.[Thomas], Sun, G.[Guolei], Van Gool, L.J.[Luc J.],
CompositeTasking: Understanding Images by Spatial Composition of Tasks,
CVPR21(6866-6876)
IEEE DOI 2111
Codes, Multitasking, Task analysis BibRef

Wallace, B.[Bram], Wu, Z.Y.[Zi-Yang], Hariharan, B.[Bharath],
Can We Characterize Tasks Without Labels or Features?,
CVPR21(1245-1254)
IEEE DOI 2111
Codes, Shape, Computational modeling, Natural languages, Task analysis BibRef

Chen, W.[Wenhu], Gan, Z.[Zhe], Li, L.J.[Lin-Jie], Cheng, Y.[Yu], Wang, W.[William], Liu, J.J.[Jing-Jing],
Meta Module Network for Compositional Visual Reasoning,
WACV21(655-664)
IEEE DOI 2106
Visualization, Scalability, Neural networks, Spread spectrum communication, Computer architecture BibRef

de Sá, J.M.C.[Jáder M. C.], Rossi, A.L.D.[Andre L. D.], Batista, G.E.A.P.A.[Gustavo E. A. P. A.], Garcia, L.P.F.[Luís P. F.],
Algorithm Recommendation for Data Streams,
ICPR21(6073-6080)
IEEE DOI 2105
Heuristic algorithms, Memory management, Machine learning, Companies, Predictive models, Knowledge discovery, Data models BibRef

Lukac, M.[Martin], Bayanov, A.[Ayazkhan], Li, A.[Albina], Abiyeva, K.[Kamila], Izbassarova, N.[Nadira], Gabidolla, M.[Magzhan], Kameyama, M.[Michitaka],
Selecting Algorithms Without Meta-features,
IML20(607-621).
Springer DOI 2103
BibRef

Wu, Y.X.[Yu-Xuan], Nakayama, H.[Hideki],
Graph-based Heuristic Search for Module Selection Procedure in Neural Module Network,
ACCV20(III:560-575).
Springer DOI 2103
BibRef

Liu, S., Liu, J., Zhao, X.,
Feasibility Analysis of Openstack and Dynamips Application Fusion,
CVIDL20(656-659)
IEEE DOI 2102
cloud computing, public domain software, information technology, openstack cloud platform, Fusion BibRef

Hu, Y.H.[Yu-Huang], Delbruck, T.[Tobi], Liu, S.C.[Shih-Chii],
Learning to Exploit Multiple Vision Modalities by Using Grafted Networks,
ECCV20(XVI: 85-101).
Springer DOI 2010
BibRef

Liu, Y.C.[Yen-Cheng], Tian, J.J.[Jun-Jiao], Glaser, N.[Nathaniel], Kira, Z.[Zsolt],
When2com: Multi-Agent Perception via Communication Graph Grouping,
CVPR20(4105-4114)
IEEE DOI 2008
Multiple agents. Task analysis, Bandwidth, Collaboration, Robot sensing systems, Correlation, Semantics, Training BibRef

Zhu, Y.[Yuke], Gordon, D.[Daniel], Kolve, E.[Eric], Fox, D.[Dieter], Fei-Fei, L.[Li], Gupta, A.[Abhinav], Mottaghi, R.[Roozbeh], Farhadi, A.[Ali],
Visual Semantic Planning Using Deep Successor Representations,
ICCV17(483-492)
IEEE DOI 1802
learning (artificial intelligence), planning (artificial intelligence), statistical analysis, Visualization BibRef

Tünnermann, J.[Jan], Grüne, S.[Steffen], Mertsching, B.[Bärbel],
Selection and Execution of Simple Actions via Visual Attention and Direct Parameter Specification,
CVS17(404-414).
Springer DOI 1711
BibRef

Amr, M.F., Qbadou, M., Mansouri, K., Riyami, B.,
Towards a model of adaptation and interfacing based on a middleware layer SOA for interoperability of several different information systems,
ISCV17(1-8)
IEEE DOI 1710
Adaptation models, Information systems, Interoperability, Service-oriented architecture, ATL, BPEL, BPMN, Interoperability, MDA, MDE, Reverse engineering, SOA, information systems, middleware, ontological, database BibRef

Zhang, P.[Peng], Wang, J.[Jiuling], Farhadi, A.[Ali], Hebert, M.[Martial], Parikh, D.[Devi],
Predicting Failures of Vision Systems,
CVPR14(3566-3573)
IEEE DOI 1409
BibRef

Karasev, V.[Vasiliy], Ravichandran, A.[Avinash], Soatto, S.[Stefano],
Active Frame, Location, and Detector Selection for Automated and Manual Video Annotation,
CVPR14(2131-2138)
IEEE DOI 1409
active learning; video annotation Which detector when and where. BibRef

Karayev, S.[Sergey], Fritz, M.[Mario], Darrell, T.J.[Trevor J.],
Anytime Recognition of Objects and Scenes,
CVPR14(572-579)
IEEE DOI 1409
anytime; budgeted classification; visual recognition. Deal with instant recognition, but refinement if time is available. BibRef

Wang, J.[Joseph], Bolukbasi, T.[Tolga], Trapeznikov, K.[Kirill], Saligrama, V.[Venkatesh],
Model Selection by Linear Programming,
ECCV14(II: 647-662).
Springer DOI 1408
Use expensive (computation) models only when needed. BibRef

Bansal, A.[Aayush], Farhadi, A.[Ali], Parikh, D.[Devi],
Towards Transparent Systems: Semantic Characterization of Failure Modes,
ECCV14(VI: 366-381).
Springer DOI 1408
Why vision systems fail. BibRef

Pan, Y.[Yan], Lai, H.J.[Han-Jiang], Liu, C.[Cong], Yan, S.C.[Shui-Cheng],
A Divide-and-Conquer Method for Scalable Low-Rank Latent Matrix Pursuit,
CVPR13(524-531)
IEEE DOI 1309
divide-and-conquer method; low-rank matrices; prediction fushion Robust Late Fusion: multiple score lists from different models. BibRef

Miller, G.[Gregor], Oldridge, S.[Steve], Fels, S.[Sidney],
OpenVL: Abstracting Vision Tasks Using a Segment-Based Language Model,
CRV13(257-264)
IEEE DOI 1308
Algorithm design and analysis BibRef

Moehrmann, J.[Julia], Heidemann, G.[Gunther],
Semi-automatic Image Annotation,
CAIP13(II:266-273).
Springer DOI 1311
BibRef
Earlier:
Efficient Development of User-Defined Image Recognition Systems,
DevCen12(I:242-253).
Springer DOI 1304
BibRef

Attamimi, M.[Muhammad], Nakamura, T.[Tomoaki], Nagai, T.[Takayuki],
Hierarchical multilevel object recognition using Markov model,
ICPR12(2963-2966).
WWW Link. 1302
Multiple levels of recognition -- category, material, etc. Integrate single level recognitions. BibRef

Dornelles, M.M.[Marta M.], Hirata, N.S.T.[Nina S. T.],
A genetic algorithm based approach for combining binary image operators,
ICPR12(3184-3187).
WWW Link. 1302
BibRef

Munoz, D.[Daniel], Bagnell, J.A.[James Andrew], Hebert, M.[Martial],
Co-inference for Multi-modal Scene Analysis,
ECCV12(VI: 668-681).
Springer DOI 1210
Multiple sources, not sensor fusion. Ananyze each and propogate information across. BibRef

Qaffou, I.[Issam], Sadgal, M.[Mohamed], Elfazziki, A.[Aziz],
Selecting Vision Operators and Fixing Their Optimal Parameters Values Using Reinforcement Learning,
ICISP12(103-112).
Springer DOI 1208
BibRef

Sorschag, R.[Robert],
How to Select and Customize Object Recognition Approaches for an Application?,
MMMod12(452-462).
Springer DOI 1201
BibRef

Kaczmarek, P.L.[Pawel L.], Raszkowski, P.[Piotr],
Semantic Integration of Heterogeneous Recognition Systems,
CIARP11(288-295).
Springer DOI 1111
BibRef

Bolme, D.S.[David S.], Beveridge, J.R.[J. Ross], Draper, B.A.[Bruce A.], Phillips, P.J.[P. Jonathon], Lui, Y.M.[Yui Man],
Automatically Searching for Optimal Parameter Settings Using a Genetic Algorithm,
CVS11(213-222).
Springer DOI 1109
BibRef

Miller, G.[Gregor], Oldridge, S.[Steve], Fels, S.S.[Sidney S.],
Towards a General Abstraction through Sequences of Conceptual Operations,
CVS11(183-192).
Springer DOI 1109
BibRef

Gurevich, I.,
The Descriptive Approach to Image Analysis: Current State and Prospects,
SCIA05(214-223).
Springer DOI 0506
BibRef

Sethi, A., Rahurkar, M., Huang, T.S.,
Variable Module Graphs: A Framework For Inference and Learning in Modular Vision Systems,
ICIP05(II: 1326-1329).
IEEE DOI 0512
BibRef

Broadhurst, A.E., Baker, S.,
Setting Low-Level Vision Parameters,
CMU-RI-TR-04-20, March, 2004.
HTML Version. 0501
BibRef

Koryabkina, I.[Irina],
Method for Image Informational Properties Exploitation in Pattern Recognition Environment,
SCIA03(1006-1013).
Springer DOI 0310
BibRef

Müller, H.[Hardo], Gülch, E.[Eberhard], Mayr, W.[Werner],
A New Modelling Technique for Object-Oriented Photogrammetric Computer Vision Algorithms,
PCV02(B: 186). 0305
BibRef

Thonnat, M., Moisan, S., Crubézy, M.,
Experience in Integrating Image Processing Programs,
CVS99(200 ff.).
Springer DOI 0209
BibRef

Nickolay, B.[Bertram], Schneider, B.[Bernd], Jacob, S.[Stefan],
Parameter optimisation of an image processing system using evolutionary algorithms,
CAIP97(637-644).
Springer DOI 9709
BibRef

Hamada, T., Shimizu, A., Hasegawa, J.I., Toriwaki, J.I.,
Automated Construction of Image Processing Procedure Based on Misclassification Condition,
ICPR00(Vol II: 430-433).
IEEE DOI 0009
BibRef

Kohl, C., Hanson, A.R., and Riseman, E.M.,
Goal-Directed Control of Low Level Processes for Image Interpretation,
DARPA87(538-551). BibRef 8700
And: COINS-TR-87-31, April 1987. BibRef

Ozaki, Y., Sato, K., Inokuchi, S.,
Rule-Driven Processing And Recognition From Range Images,
ICPR88(II: 804-807).
IEEE DOI 8811
BibRef

Yamamoto, K., Sakaue, K., Matsubara, H., Yamagishi, K.,
Miracle-IV: Multiple Image Recognition System Aiming Concept Learning -- Intelligent Vision,
ICPR88(II: 818-821).
IEEE DOI 8811
BibRef

Glicksman, J.[Jay],
Using Multiple Information Sources in a Computational Vision System,
IJCAI83(1078-1080). Does not really say much more than it is a good idea, no implementation with real images. BibRef 8300

Garvey, T.D., Lowrance, J., and Fischler, M.A.,
An Inference Technique for Integrating Knowledge for Disparate Sources,
IJCAI81(319-325). BibRef 8100

Garvey, T.D., and Fischler, M.A.,
Perceptual Reasoning in a Hostile Environment,
AAAI-80(253-255). BibRef 8000

Garvey, T.D., and Fischler, M.A.,
The Integration of Multi-Sensor Data for Threat Assessment,
ICPR80(343-347). BibRef 8000

Chapter on Matching and Recognition Using Volumes, High Level Vision Techniques, Invariants continues in
Context in Computer Vision .