Imedia image and Multimedia Indexing, Browsing and Retrieval
tarix 28.10.2017 ölçüsü 445 b. #18813
Evaluation 2001-2005 14 November 2005 INRIA Rocquencourt http://www-rocq.inria.fr/imedia/ The Team (November 2005) Senior members
Overview Objectives Results and Contributions Applications and Grants Positioning Future objectives Objectives Design and Develop new Methods for Visual Information Retrieval by Content Visual appearance modeling Constructing efficient indexes for minimizing query cost Interactive browsing, querying and retrieval Similarity learning Clustering techniques Relevance feedback: learning from user interaction Combine keyword annotation (when available) search with visual-content search Key Issues Fidelity Rich Partial visual query formulation focused on user interest (region-based or point-based) Subjective preference by relevance feedback mechanism Mental image search and “page zero” problem Smart navigation Cross-media General Methodological Issues Image content description: analysis, segmentation; considering specific and generic content Learning from few examples: Active learning for efficient personalization mechanism Semi-supervised clustering Adaptive Clustering (interactive SVM-based refinement) Information theory: Mental Image search Overview Objectives Visual Content Description Clustering Methods Relevance Feedback Mechanism Mental Image Search Applications and Grants Positioning Future Objectives Visual Content Description Generic content: Global image signature: combined color-structure signature (MMCBIR 01, LNCS 05), shape signature (ICIP 05), 3D signature, Local image description: region-based (JVLC 04), color point-based (CBAIVL/CVPR 01) Specific content: Face detection (IJCV 01, JMLR 05) Face recognition (Biometric WS/ECCV 02) Fingerprints recognition (ACCV 02) http://www-rocq.inria.fr/imedia/ikona.html Coarse-to-Fine Strategy for Face Detection Local Description of the Image Region-based Indexing and Retrieval Precise Search by Local Color Invariants Descriptors Overview Objectives Results and Contributions Visual Content Description Clustering Methods Relevance Feedback Mechanism Mental Image Search Applications and Grants Positioning Future Objectives Clustering Methods Context: unknown number of clusters, competitive agglomeration approaches Application: image database categorization, image segmentation Contributions: Adaptive robust clustering (ICPR02) : Noise cluster and cluster density/shape adapting Entropy regularization and extension to non linearly separable data (IEEE Fuz.Sys05) Active semi-supervised learning (MIR05, IEE VISP 05) Overview Objectives Results and Contributions Visual Content Description Clustering Methods Relevance Feedback Mechanism Mental Image Search Applications and Grants Positioning Future Objectives Relevance Feedback Mechanism Contribution to Components of RF Mechanism : Learner: kernels inducing insensitivity to the scale of the data in the feature vector space Selector: active learning selection criterion that minimizes the redundancy between the samples SVM-based decision function select least redundant (orthogonal) items among most ambiguous items User: consistent annotation? Extensive study of user strategies Overview Objectives Results and Contributions Visual Content Description Clustering Methods Relevance Feedback Mechanism Mental Image Search Applications and Grants Positioning Future Objectives Mental Picture Retrieval Context: No starting image example or keyword A person has a picture “in mind”, e.g., a Problem : How to reach the target?Bayesian framework Composition from Visual Thesaurus Bayesian Framework Components: Answer Model: Discover answer models which match human behavior Display Model: (Optimization Problem) Discover approximations to the optimal display Each display should catch as much as possible information about target from user. => The idea is to maximize mutual information between target and answer.Mental face retrieval: Complications Mental matching involves human memory, perception and opinions. Images are not indexed by semantic content, but rather by low-level features (“semantic gap”). Face recognition is easier, yet unsolved. Sparse literature. Query by “Visual Words” Composition Query by “Visual Words” Composition Query composition interface => The Visual Thesaurus = summary of region categories (cluster prototypes set) Additional Results Cross-modal Indexing and Retrieval Copy detection and more generally semantic behavior of local descriptors for selective video content retrieval Kernels for similarity learning Extensive study of user strategies in relevance feedback. 3D model indexing and retrieval, 2D shape descriptors 3D model retrieval Overview Objectives Results and Contributions Applications and Grants Positioning Future objectives Applications and Grants Scientific content collections: Remote sensing images (ACI QuerySat – CNES, IGN) Biodiversity images (ACI Biotim – INRA/NASC, IRD) Audio-visual content: TV news (RIAM Mediaworks – TF1 Tv; INA) Personal and prof. content (IP-FP6 AceMedia) Art and Design: Alinari collection Security application: Pedophilia images (Central Judiciary Police Dep. Europ. STOP) Biometry (Face - Sagem, fingerprints – Thales) Other Grants NoE-FP6 Muscle Important involvement (WP leader, NoE deputy scientific coordinator, steering committee) NoE-FP6 Delos PAI Galilée (recognition for video-surveillance with Modena Univ.) Associated-Team ViMining with NII RNRT - RECIS (FT R&D, INSA, NF) Gene expression studies on “Arabidopsis” Copy detection Security Application Criminal Investigation within Pedophilia Images Overview Objectives Results and Contributions Applications and Grants Positioning Future objectives INRIA Positioning Wrt. INRIA’s strategic goals (2nd): Developing multimedia data and information processing INRIA projects: A RIANA: probabilistic and variational image analysis for earth observation, joint ACI QuerySat on remote sensing image indexing, Muscle NoEL EAR: focus on object recognition involving offline learning methods (learning datasets) while we work on information retrieval and develop different learning methods from few examples (on-line) for image clustering and search personalization - complementary , joint AceMedia FP6V ISTA: Video indexing – complementary, NoE Muscle, MediaWorks,T EXMEX (SymC): Pluri-disciplinary project (NLP, ImageP.,DB), we have joint interest to feature space structuring and hybrid indexing. (Texmex: audio, video, NLP, visual…); AceMedia and NoE MuscleINRIA Positioning Wrt. INRIA’s strategic goals (2nd): Developing multimedia data and information processing INRIA projects: A RIANA: probabilistic and variational image analysis for earth observation, joint ACI QuerySat on remote sensing image indexing, Muscle NoEL EAR: offline learning methods for object recognition (learning datasets) while we focus on on-line learning methods from few examples for image clustering and retrieval personalization - complementary, joint IP-FP6 project AceMediaV ISTA: Video indexing – complementary, NoE Muscle, MediaWorks,T EXMEX (SymC): Pluri-disciplinary project (NLP, ImageP.,DB), we have joint interest to feature space structuring and hybrid indexing. (Texmex: audio, video, NLP, visual…); AceMedia and NoE MuscleNational Positioning Telecom Paris – SIP: Remote sensing indexing, partner within ACI QuerySat, 3D indexing INT ARTEMIS: 2D and 3D indexing Ecole Centrale Lyon (L. Chen): face detection recognition, TechnoVision IV2. INSA Lyon IRIS (J-M Jolion): local descriptors ENSEA ETIS : Relevance feedback, Muscle NoE Ecole des Mines (JP. Vert): kernel design International Positioning Very active domain, below non-exhaustive list T.Huang (Urbana-Champaign), Ed. Chang (U.Cal.Santa-Barbara), Relevance feedback, A. Smeulders (ISIS group U. Amsterdam), D. Lowe (Univ. BC), A. Zisserman (Oxford), H. Bishof (Tech. Univ Graz); point-based features J. Wang (Penn State Univ.), region-based retrieval P. Belhumeur (Columbia Univ.), Leaf species identification and shape descriptors S. Satoh (NII – Japan) Associated-team “ViMining”, saliency detection, face detection, image and text–based retrieval R. Cucchiara (Univ. Modena) PAI Gallileo, biometry and video surveillance , 3D indexing A. Delbimbo (Univ. Florence) NoEDelos, 3D indexing H. Frigui (Univ. NSF-INRIA), semi-supervised clustering T. Tan (CASIA) Liama project Overview Objectives Results and Contributions Applications and Grants Positioning Future Objectives Future Scientific Objectives Visual content description Saliency investigation for selective content retrieval Geometric consistency of local descriptors Specific content: 2D/3D shape (biodiversity), extension of face detection methods to be invariant to view point Efficient search in large collections of images Multidimensional data structure indexing (example: multiple queries processing) Future Scientific Objectives (cont.) Mental image search: improved models for perceptual similarity for a higher degree of coherence between system models and actual human behavior More efficient visual thesaurus construction methods (hierarchical description with relational clustering) Toward scalable methods: semi-supervised clustering, Relevance Feedback Hybrid image and text indexing and retrieval: Future Applications Biodiversity: Pollen database indexing and retrieval (INRA) Remote sensing image collection - QuerySat Design Trends (FP6 Strep – TREND, start January 2006) Audi-visual: INFOMAGIC (“Pôle de compétitivité” IdF IMVN) SIGMUND (RIAM with INA) Security IRFACE: : jointly with Liama and INT on Iris-face biometry, Information filtering with “Ministère de l’Intérieur” Future Plan A common project between IMEDIA and the Database Research Group VERTIGO of the Cedric/CNAM Lab is planned Planned Joint IMEDIA Project INRIA/CNAM composition
Summary Promising scientific results Smooth evolution of current research directions Important application impact Highly competitive context Support for INRIA research scientist hiring highly appreciated (major risk) Thanks for your attention http://www-rocq.inria.fr/imedia/
Dostları ilə paylaş:
