"Are Low Level Features Too Low for Indexing?"
Edward J. Delp
Video and Image Processing Laboratory
School of Electrical and Computer Engineering
West Lafayette, Indiana, USA
This talk will discuss issues related to the use of simple low level features for indexing image and video content. These types of features are attractive due to their simplicity and may be useful for mobile applications.
The real question that needs to be addressed is what is the limitations of this approach and can semantic information really be provided.
Edward J. Delp was born in Cincinnati, Ohio. He received the B.S.E.E. (cum laude) and M.S. degrees from the University of Cincinnati, and the Ph.D. degree from Purdue University. In May 2002 he received an Honorary Doctor of Technology from the Tampere University of Technology in Tampere, Finland.
Since August 1984, he has been with the School of Electrical and Computer Engineering and the School of Biomedical Engineering at Purdue University, West Lafayette, Indiana.
In 2002 he received a chaired professorship and currently is The Silicon Valley Professor of Electrical and Computer Engineering and Professor of Biomedical Engineering.
His research interests include image and video compression, multimedia security, medical imaging, multimedia systems, communication and information theory.
Dr. Delp is a Fellow of the IEEE, a Fellow of the SPIE, a Fellow of the Society for Imaging Science and Technology (IS&T), and a Fellow of the American Institute of Medical and Biological Engineering. In 2004 he received the Technical Achievement Award from the IEEE Signal Processing Society for his work in image and video compression and multimedia security.
Wednesday 30 November
|EWIMT Technical Symposium|
|09:10-10:50||Oral session (1) : Semantic multimedia analysis
Chair: Paola Hobson, Motorola
|A. Hanjalic, J. Nesvadba, J. Benois-Pineau "Moving away from narrow-scope solutions in multimedia content analysis"
A. Garcia-Rojas, D. Thalmann, F. Vexo, L. Moccozet, N. Magnenat-Thalmann, M. Mortara, M. Spagnuolo, M. Gutierrez "An ontology of virtual humans : incorporating semantics into human shapes"
V.M. Viitaniemi, J.T. Laaksonen "Keyword-detection approach to automatic image annotation"
E. Spyrou, G. Stamou, Y. Avrithis, S. Kollias "Fuzzy Support Vector Machines for Image Classification fusing MPEG-7 Visual Descriptors"
L. J. B. Nixon "Integrating knowledge, semantics and digital media into the multimedia generation process"
|11:00-11:45||Keynote speech : Edward J. DelpPurdue University, Indiana, USA||"Are Low Level Features Too Low for Indexing?"|
|11:45-13:00||Poster session (1) : Semantic multimedia analysis||
J. Vompras, S. Conrad "Generating semantic templates to support the image annotation process"
A. Hogan, A. Harth, J. G. Breslin "Podcast Pinpointer : a multimedia Semantic Web application"
J. Calic, N. Campbell, S. Dasiopoulou, Y. Kompatsiaris "An overview of multimodal video representation for semantic analysis"
A. Bamidele, F.W.M. Stentiford "An attention based similarity measure used to identify image clusters"
N. K. Shukla, S. Sengupta, M. Chakraborty "Intermediate view synthesis in wide-baseline stereoscopic video for immersive telepresence"
G Y Jin, L M Tao, G Y Xu "Cues extraction and hierarchical HMM based events inference in soccer video"
P. Nair, L. Zou, A. Cavallaro "Facial scan change detection"
M. Delakis, G. Gravier, P. Gros "Audiovisual fusion with segment models for video structure analysis"
N.E. O'Connor, E. Cooke, H. Le Borgne, M. Blighe, T. Adamek "The aceToolbox : low-level audiovisual feature extraction for retrieval and classification"
|13:00-14:0||Lunch||Continuation of poster session and networking|
|14:00-15:20||Oral session (2) : technology enablers for semantic multimedia applications
Chair: Edward J. Delp, Purdue University, Indiana, USA
F. Obermeier, K. Diepold "Semantic interpretation of video subspaces in the motion domain"
C. Millet, I. Bloch, P. Hede, P.-A. Moellic "Using relative spatial relationships to improve individual region recognition"
A. Mariappan, M. Igarta, C. Taskiran, B. Gandhi, E. J. Delp "A low-level approach to semantic classification of mobile multimedia content"
M. T. Coimbra, P. Campos, J. P. Silva Cunha "Extracting clinical information from endoscopic capsule exams using MPEG-7 Visual Descriptors"
|15:20-16:20||Poster session (2) : technology enablers for semantic multimedia applications||
Y. Bachvarova, N. Elouazizi "Integrating knowledge about modalities to a multimedia knowledge representation framework"
Jing Zhang, Anthony T.S. Ho "An efficient authentication method for H.264/AVC"
O. K. Oyekoya, F. W. M. Stentiford "A performance comparison of eye tracking and mouse interfaces in a target image identification task"
P. Astrelli, M. Di Bono, M. Martinelli, O. Salvetti, M. Catasta, C. Morbidoni, F. Piazza, G. Tummarello, O. Signore "Toward a scalable multimedia metadata infrastructure using distributed computing and Semantic Web technologies"
T. Zgaljic, N. Sprljan, E. Izquierdo "Bitstream syntax description based adaptation of scalable video"
N. Adami, M. Corvaglia, R. Leonardi "Integrating descriptions to characterize multimedia collections"
N. Thomos, S. Argyropoulos, N. V. Boulgouris, M. G. Strintzis "Error resilient transmission of H.264/AVC streams using flexible macroblock ordering"
A. Matellanes, A. May, P. Villegas, F. Snijder, A. Kobzhev, E. Dijk "An architecture for multimedia content management"
F. Souvannavong, B. Huet "Hierarchical genetic fusion of possibilities"
Sam H. Minelli, Domenico Loschiavo, Andrea de Polo "A proposal for a distributed archiving architecture using intelligent automated tools"
|16:35-17:55||Oral session (3) : Semantic multimedia applications
Chair: Mark Sandler, Queen Mary University of London
K. Yoshii, M. Goto, H. Okuno, "INTER:D: a drum sound equalizer for
controlling volume and timbre of drums"
D. Baggi, A. Barate, L.A. Ludovico, G. Haus "A computer tool to enjoy and understand music"
T. Di Noia, E. Di Sciascio, F.M. Donini "Non-standard inferences for knowledge-based image retrieval"
V. Valdes, J.M. Martinez "Fast image adaptation driven by people presence"
|17:55-19:30||Poster session (3) : Semantic multimedia applications
(co-located with concluding drinks reception)
D. Djordjevic, Q. Zhang, E. Izquierdo "Fusion of semantic and visual
information for automatic indexing and annotation of key frame images"
B. Grilheres, C. Beauce, S. Canu, S. Brunessaux "Benchmarking of semantic annotation with conditional random fields"
Fardin Akhlaghian Tab, Golsha Naghdy "Knowledge-Based Semantic Image Segmentation and Global Precedence Effect"
C. U. Ng, G. R. Martin, "Experience-based relevance feedback for image retrieval"
G. Qiu, M. Yang, J. W. Huang "Information selective image retrieval"
C. Catton, S. Sparks, D. M. Shotton "The Imagestore ontology and the bioimage database : Semantic Web tools for biological research images"
Hui-Yu Huang, Tai-Ch Wei "Fast locating detection of covering region in image mosaic"
T. Koizumi, Y. Kameda, Y. Nakamura "Retrieval of personal experience records using relevance feedback with a structuring filter"
Erbug Celebi, Adil Alpkocak "Combining textual and visual clusters for semantic image retrieval and auto annotation"
J. R. van Ossenbruggen, L. Hardman "Semantic timeline interfaces for annotated multimedia assets"
P. Wilkins, P. Ferguson, A.F. Smeaton, C. Gurrin "Text Based Approaches for Content-Based Image Retrieval on Large Image Collections"
V. Fernandez-Carbajales, J.M. Martinez, F. Moran "Description- driven generation of 3D humanoids within Authoring744"
|08:30-09:00||Coffee and late registrations|
|09:00-09:05||Opening remarks||Ebroul Izquierdo, Queen Mary University of London|
|09:05-09:30||FP6 State of Play||Stefano Bertolo, European Commission|
|09:30-10:15||Back to the drawing board: options and directions for FP7 research||Roberto Cencioni, European Commission|
|10:15-10:30||UK Information Society National Contact Point||Peter Walters, FP6UK /IS|
|11:05-12:05||National and IST Projects special session oral papers
Chair: Yannis Avrithis, National Technical University of Athens
F. Bry, M. Marchiori, "Reasoning on the semantic web : beyond ontology
languages and reasoners"
N. O'Hare, C. Gurrin, A. F. Smeaton, G.J.F Jones "Combination of content analysis and context features for digital photograph retrieval"
H. Vinet, "The SEMANTICHIFI project, content-based management and manipulation of musical recordings"
|12:05-13:00||National and IST Projects poster session I and demos||
C. Mac Williams, R. Wages "Virtual personalised channels : video conducting
of future TV broadcasting"
W. Haas, G. Thallinger "SALERO - Semantic audiovisual entertainment reusable objects"
G. Kienast, H. Stiegler, W. Bailer, H. Rehatschek, S. Busemann, T. Declerck "Sponsorship Tracking Using Distributed Multi-modal Analysis (DIRECT-INFO)"
V. Sabol, M. Granitzer, K. Tochtermann, W. Sarka "MISTRAL - Measurable intelligent and reliable semantic extraction and retrieval of multimedia data"
C.D. Spyropoulos, G. Paliouras, V. Karkaletsis "BOEMIE: Bootstrapping ontology evolution with multimedia information extraction"
Tobias Burger, Georg Guntner "SMART CONTENT FACTORY - Semantic knowledge based indexing of audiovisual archives"
D. L. Williams, M. Thomas "The Perceived role of Automatic Content recognition Systems in the Production of Audio-Visual Media"
C. Ursu, V. Tablan, H Cunningham "Semantic analysis for tomorrow's audio-visual digital archives"
G. Vasilakis, M. Pitikakis, E. Vavalis, C. Houstis "A semantic based search engine for 3D shapes : Design and Early Prototype Implementation"
J. Meessen, C. Parisot, D. Agrafiotis, C. Le Barz, Y. Sadourny, J.-F. Delaigle, D. Bull, D. Nicholson "WCAM: content-based video coding and securing of motion JPEG 2000 and H.264 for wireless surveillance transmission"
H. Mayer, W. Haas, S. Lindstaedt, K. Tochtermann "APOSDLE - Advanced process-oriented self-directed learning environment"
Herwig Rehatschek "MEDIACAMPAIGN - discovering, inter-relating and navigating cross-media campaign knowledge"
E.J. Pauwels "FP6 Network of Excellence MUSCLE: Multimedia Understanding through Semantics, Computation and Learning"
|13:00-14:00||Lunch||Continuation of the poster session|
Chair: Adrian Matellanes, Motorola
|"Industrial Applications of Knowledge-Based Systems in Video Surveillance and Monitoring Markets". Francisco Gomez-Molinero. Visual Tools S.A.
"Content handling and intelligent Interactions in a future of Seamless Mobility". Nicolas Demassieux. Motorola SAS.
"Towards Distributed and Generic Multimedia Content Analysis Solutions". Jan Nesvadba. Storage Systems & Applications. Philips Research.
"Knowledge Technologies in Newsroom Automation and Archiving Systems" Nikos Sarris. Nikos Sarris, Athens Technology Center S.A.
|15:20-16:20||National and IST projects poster session II||
L. Vasiliu, S. Harand "The DIP project : putting semantics into Web
L. Zapf, N. Fernandez-Garcia, L. Sanchez-Fernandez "The NEWS Project - Semantic Web technologies for the news domain"
S. Piperidis, H. Papageorgiou" REVEAL THIS : Retrieval of multimedia multilingual content for the home user in an information society"
P. Warren "Building semantic applications with SEKT"
P. Herrera, J. Bello, G. Widmer, M. Sandler, F. Vignoli, E. Pampalk, P. Cano, X. Serra "SIMAC: semantic interaction with music audio contents"
P. Villegas, N. Sarris, J. Picault, I. Kompatsiaris "Creating a MESH of multimedia news feeds"
E. Izquierdo "Knowledge Space of semantic inference for automatic annotation and retrieval of multimedia content"
V. Tzouvaras, S. Dasiopoulou, F.M. Recuerda, G. Stoilos, Y. Kompatsiaris, G. Stamou "Multimedia Analysis and Annotation Requirements for the Semantic Web"
M. Dzbor, E. Motta, R. Studer, Y. Sure, A. Gomez-Perez, W. Waterfeld, V. Pevtschin, R.V. Benjamins, P. Haase "NeOn - Lifecycle Support for Networked Ontologies"
F. Ciravegna, S. Staab "Large scale cross-media knowledge acquisition, sharing and reuse in X-MEDIA"
P. Sinclair, M. Addis, D. Fina, P. Lewis, K. Martinez, D. Prideaux, G. Da Bormida "eCHASE: Sustainable Exploitation of electronic Cultural Heritage"
G. Stoll "porTiVity: new Rich Media iTV Services for handheld TV"
A. Metellanes, "aceMedia - Creating Intelligent Multimedia Content"
|16:35-17:35||Panel session "Bridging industrial and academic research for the new Digital Media in
Chair: Thomas Sikora (Technische Universität Berlin)
Lynda Hardman (CWI, Amsterdam)
Stefan Rueger (Imperial College)
Alyson Evans (Motorola)
Doug Williams (BT)
|17:35-18:00||Discussion Q&A||Panellists and IST people|