Wiamis 2010 : Preliminary Programme
12 April 2010
| 8.00 - 9.00 | Registration, posters up on boards |
| 9.00 - 9.15 | Welcome |
| 9.15 - 10.15 | Keynote 1 (Prof. D. Taubman) - Efficient Interactive Access to Large Volume Media |
| 10.15 - 10.45 | break |
| 10.45 - 11.30 | Oral Session 1 - Multimedia content analysis |
| 11.30 - 12.00 | Short oral introduction to today's posters 1 |
| 12.00 - 13.30 | Lunch |
| 13.30 - 14.30 | Poster Sessions Day 1- slot for poster session only |
| 14.30 - 16.00 | Tutorial 1 (Prof. Nicu Sebe) - Human-centered computing: Challenges and Perspectives |
| 16.00 - 16.30 | break |
| 16.30 - 17.15 | Oral Session 2 - 3D and multi-view |
| 17.15 - 18.15 | WIAMIS Panel - Multimedia & User Interaction |
| 18.15 | Reception |
13 April 2010
| 8.00 - 9.00 | Registration, posters up on boards |
| 9.00 - 9.15 | Announcements |
| 9.15 - 10.15 | Keynote 2 (Prof. A. del Bimbo) - About faces and 3D data |
| 10.15 - 10.45 | break |
| 10.45 - 11.30 | Oral Session 3 - High-level descriptors and video retrieval |
| 11.30 - 12.00 | Short oral introduction to today's posters 2 |
| 12.00 - 13.30 | Lunch |
| 13.30 - 14.30 | Poster Sessions Day 2 - slot for poster session only |
| 14.30 - 15.00 | Overview talk (Dr. G. Cordara) - Visual Search: A Telecom Operator Perspective |
| 15.00 - 16.00 | Oral Session 4 - Multimedia delivery |
| 16.00 | Departure for Banquet |
14 April 2010
| 8.00 - 9.00 | Registration, posters up on boards |
| 9.00 - 10.00 | Oral Session 5 - Motion analysis and tracking |
| 10.00 - 10.30 | break |
| 10.30 - 11.45 | Special Session A - Interactive MM in Social Networks |
| 11.45 - 12.15 | Short oral introduction to today's posters |
| 12.15 - 13.30 | Lunch |
| 13.30 - 14.30 | Poster Sessions Day 3- slot for poster session only |
| 14.30 - 16.00 | Tutorial 2 (Prof. M. Tagliasacchi) - Compressive Sensing: basic principles and appl. in image and video processing |
| 16.00 - 16.30 | break |
| 16.30 - 17.15 | Special Session B - Semantic digital libraries for cross-discipline retrieval |
| 17.15 - 17.30 | Best student paper award ceremony and concluding remarks |
Oral Session 1 - Multimedia content analysis, Session chair: David Taubman
On the use of audio events for improving video scene segmentation
Panagiotis Sidiropoulos, Vasileios Mezaris, Ioannis Kompatsiaris, Hugo Meinedo, Miguel Bugalho and Isabel Trancoso.
Region-based caption text extraction
Miriam León, Veronica Vilaplana, Antoni Gasull and Ferran Marques.
k-nn boosting prototype learning for object classification
Paolo Piro, Michel Barlaud, Richard Nock and Frank Nielsen.
Oral Session 2 - 3D and multi-view, Session chair: Nicu Sebe
A New Evaluation Criterion for Point Correspondences in Stereo Images
Michael Unger and Aleksandar Stojanovic
Local homography estimation using keypoint descriptors
Alberto Del Bimbo, Fernando Franco and Federico Pernici.
A Cognitive Source Coding Scheme for Multiple Description 3DTV Transmission
Simone Milani and Giancarlo Calvagno
Oral Session 3 - High-level descriptors and video retrieval, Session chair: Vasileios Mezaris
Forensic reasoning upon pre-obtained surveillance metadata using uncertain spatio-temporal rules and subjective logic
Seunghan Han, Bonjung Koo, Andreas Hutter and Walter Stechele.
AIR: Architecture for Interoperable Retrieval on distributed and heterogeneous Multimedia Repositories
Florian Stegmaier, Mario Doeller, Harald Kosch, Andreas Hutter and Thomas Riegel.
Local invariant feature tracks for high-level video feature extraction
Vasileios Mezaris, Anastasios Dimou and Ioannis Kompatsiaris
Oral Session 4 - Multimedia delivery, Session chair: Nicola Adami
An efficient prefetching strategy for remote browsing of JPEG 2000 image sequences
Juan Pablo Garcia Ortiz, Vicente González Ruiz, Inmaculada García and Daniel Müller.
Comparing spatial masking modelling in just noticeable distortion controlled H.264/AVC video coding
Matteo Naccari and Fernando Pereira
Blind estimation of the QP parameter in H.264/AVC decoded video
Marco Tagliasacchi and Stefano Tubaro.
Coherent video reconstruction with motion estimation at the decoder
Claudia Tonoli, Marco Dalai and Riccardo Leonardi.
Oral Session 5 - Motion analysis and tracking, Session chair: Marco Tagliasacchi
Semi-automatic object tracking in video sequences by extension of the mrsst algorithm
Marko Esche, Thomas Sikora and Mustafa Karaman.
A multi-resolution particle filter tracking with a dual consistency check for model update in a multi-camera environment
Yifan Zhou, Jenny Benois-Pineau anfd Henri Nicolas.
Activity detection using regular expressions
Mattia Daldoss, Nicola Piotto, Nicola Conci and Francesco G.B. De Natale.
Shape adaptive Mean Shift Object Tracking using Gaussian Mixture Models
Katharina Quast and André Kaup.
Special session A: Interactive Multimedia in Social Networks, Session chair: Naeem Ramzan
Exploring temporal aspects in user-tag co- clustering
Eirini Giannakidou, Vassiliki Koutsonikola, Athena Vakali and Yiannis Kompatsiaris.
Gaze movement inference for implicit image annotation
S Navid Haji Mirza and Ebroul Izquierdo.
3D Object Duplicate Detection for Video Retrieval
Peter Vajda, Ivan Ivanov, Lutz Goldmann, Jong-Seok Lee and Touradj Ebrahimi.
Improving Scalable Video Adaptation in a Knowledge-Based Framework
Fernando López, Gokce Nur, Safak Dogan, Hemantha Kodikara Arachchi, Marta Mrak, José M. Martínez and Narciso García, Ahmet Kondoz.
Special session B: Semantic Digital Libraries for Cross - Discipline Retrieval, Session chair: Ioannis Kompatsiaris
Wikipedia based semantic metadata annotation of audio transcripts
Giulio Paci, Giorgio Pedrazzi and Roberta Turra.
User study of the Free-Eye photo browsing interface
Kan Ren, Janko Calic and Risto Sarvas.
Browsing news archives from the perspective of history: the papyrus browser historiographical issues view
Manolis Platakis, Charalampos Nikolaou, Akrivi Katifori, Manolis Koubarakis and Yannis Ioannidis.
Poster session Monday
The MUG Facial Expression Database
Niki Aifanti, Christos Papachristou and Anastasios Delopoulos.
Adaptive image classification based on visual features and folksonomy
Esin Guldogan and Moncef Gabbouj.
Eye tracking as an accessible assistive tool
Alfredo Armanini and Nicola Conci.
Exploiting implicit user feedback in interactive video retrieval
Stefanos Vrochidis, Ioannis Kompatsiaris and Ioannis Patras.
Bag-of-words Classification of Miniature Illustrations
Costantino Grana, Daniele Borghesani, Giovanni Gualdi and Rita Cucchiara.
K-Nearest Neighbors Directed Synthetic Images Injection
Luca Piras and Giogio Giacinto.
Increasing the user experience of multimedia presentations with sensory effects
Markus Waltl, Christian Timmerer and Hermann Hellwagner.
Identification versus CBCD: a comparison of different evaluation techniques
Marzia Corvaglia, Fabrizio Guerrini, Riccardo Leonardi and Eliana Rossi.
Attention-based dense crowds analysis
Matei Mancas.
Poster session Tuesday
Multi-video summarization based on video-mmr
Yingbo Li and Bernard Merialdo.
Automatic adaptation decision making in the MPEG-21 framework: mechanisms and complementary description tools
Fernando López, José M. Martínez and Narciso García.
Retrieval of video scenes by structural descriptors
Ugo Ciracì, Luca Buriano and Riccardo Leonardi.
Constant quality variable bit-rate control for svc
Tea Anselmo and Daniele Alfonso.
Error Concealment of Intra Coded Video Frames
Riccardo Bernardini, Luca Celetto, Gianluca Gennari, Matteo Petrani and Roberto Rinaldo.
H.264/AVC Stereo Video Compression Benchmarking
Subarna Tripathi, Emiliano Piccinelli and Davide Aliprandi.
Region-based video object segmentation robust to illumination
Marcos Escudero and Jesús Bescós.
An adaptive system for real-time scalable video streaming with end- to-end qos control
Beilu Shao, Daniele Renzi, Peter Amon, George Xilouris, Nikolaos Zotos, Stefano Stefano Battista, Anastasios Kourtis and Marco Mattavelli.
Poster session Wednesday
Detecting points of focus using color radial symmetry
Lakehal Elkhamssa and Yahiaoui Itheri.
A DSP Multiprocessor Architecture for Live Camera Calibration
Federico Pedersini and Paolo Milani.
A multiscale feature extraction approach for 3d range images
Francesco Bonarrigo, Alberto Signoroni, Riccardo Leonardi and Matteo Carocci.
Segment-Based Depth Maps Extraction from Stereo Video Content
Alberto La Martina, Davide Aliprandi and Emiliano Piccinelli.
High-level semantic video annotation based on 3d scene structure analysis
Oliver Schreer, Sara Brodin, Ingo Feldmann and Wolfgang Waizenegger.
Multi-source model for multiple search result clustering
Amel Hamzaoui, Alexis Joly and Nozha Boujemaa.
Performance Analysis of the Edge Pixel Orientations Histogram
Antonio Pinheiro.
Another look at the retina as an image dithered scalar quantizer
Khaled MASMOUDI, Marc Antonini and Pierre Kornprobst.
