Conference program

Each full paper has allocated 25 minutes for presentation and 5 minutes for discussion.

June 10 (Wednesday)
8:30-9:30 Registration
9:30-9:40 Welcome talk
9:40-10:40 Invited talk 1
10:40-11:00 Coffee break
11:00-12:30 Session 1: Content
12:30-14:00 Lunch
14:00-15:30 Session 2: Concepts
15:30-17:00 Demo session (+ Coffee break)
18:30-? Welcome party
June 11 (Thursday)
9:00-10:30 Session 3: Learning
10:30-11:00 Coffee break
11:00-12:30 Session 4: Large scale
12:30-14:00 Lunch
14:00-16:00 Session 5: Retrieval
16:00-18:00 Poster session (+ Coffee break)
19:30-22:30 Social event (Steamboat Cruise on Labe boat, best paper and CBMI 2016 announcement)
June 12 (Friday)
9:30-10:30 Invited talk 2
10:30-11:00 Coffee break
11:00-12:30 Special Session on Medical Multimedia Processing
12:30-14:00 Lunch
14:00-15:00 Special Session on High Performance Multimedia Indexing
15:00-15:15 Farewell


Session 1 - Content

  • Jordi Pont-Tuset, Miquel Farré and Aljoscha Smolic. Semi-Automatic Video Object Segmentation by Advanced Manipulation of Segmentation Hierarchies
  • Cyril Gaudefroy, Hélène Papadopoulos and Matthieu Kowalski. A Multi-Dimensional Meter-Adaptive Method for Automatic Segmentation Of Music
  • Lukas Diem and Maia Zaharieva. Interpretable Video Representation

Session 2 - Concepts

  • Esra Acar, Frank Hopfgartner and Sahin Albayrak. Fusion of Learned Multi-Modal Representations and Dense Trajectories for Emotional Analysis in Videos
  • Markus Schedl, Mats Sjöberg, Ionut Mironica, Bogdan Ionescu, Vu Lam, Yu-Gang Jiang and Claire-Helene Demarty. VSD2014: A Dataset for Violent Scenes Detection in Hollywood Movies and Web Videos
  • Hassan Wehbe, Bassem Haidar and Philippe Joly. Automatic Detection of Repetitive Actions in a Video

Session 3 - Learning

  • Omar Seddati, Stéphane Dupont and Saïd Mahmoudi. DeepSketch: deep convolutional neural networks for sketch recognition and similarity search
  • Phong Vo, Alexandru Ginsca, Herve Le Borgne and Adrian Popescu. Effective Training of Convolutional Networks using Noisy Web Images
  • Nicolas Voiron, Alexandre Benoit, Andrei Filip, Patrick Lambert and Bogdan Ionescu. Semi-supervised Spectral Clustering with automatic propagation of pairwise constraints

Session 4 - Large scale

  • Katerina Andreadou, Symeon Papadopoulos and Yiannis Kompatsiaris. Web image size prediction for efficient focused image crawling
  • Bahjat Safadi and Georges Quénot. A Factorized Model for Multiple SVM and Multi-Label Classification for Large Scale Multimedia Indexing
  • Cassio Elias Dos Santos Junior, Ewa Kijak, Guillaume Gravier and William Robson Schwartz. Learning to Hash Faces Using Large Feature Vectors

Session 5 - Retrieval

  • Aikaterini Iliakopoulou, Symeon Papadopoulos and Yiannis Kompatsiaris. News-oriented multimedia search over multiple social networks
  • Bogdan Boteanu, Ionuț Mironică and Bogdan Ionescu. Hierarchical Clustering Pseudo-Relevance Feedback for Social Image Search Result Diversification
  • Etienne Gadeski, Hervé Le Borgne and Adrian Popescu. Duplicate image detection in a stream of web visual data
  • Takahiko Furuya, Shigeru Kuriyama and Ryutarou Ohbuchi. An Unsupervised Approach for Comparing Styles of Illustrations

Special Session on Medical Multimedia Processing

  • Manfred Jürgen Primus, Klaus Schoeffmann and Laszlo Böszörmenyi. Instrument Classification in Laparoscopic Videos
  • Ashok Dahal, Junghwan Oh, Wallapak Tavanapong, Johnny Wong and Piet C. de Groen. Detection of Ulcerative Colitis Severity in Colonoscopy Video Frames
  • Jennifer Roldan Carlos, Mathias Lux, Xavier Giro-I-Nieto, Pia Muñoz and Nektarios Anagnostopoulos. Visual Information Retrieval in Endoscopic Video Archives

Special Session on High Performance Multimedia Indexing

  • Martin Kruliš, Hasmik Osipyan and Stephane Marchand-Maillet. Permutation Based Indexing for High Dimensional Data on GPU Architectures
  • Hannes Fassold, Harald Stiegler, Jakub Rosner, Marcus Thaler and Werner Bailer. A GPU-Accelerated Two Stage Visual Matching Pipeline for Image and Video Retrieval

Demo session

  • Tomáš Grošup, Juraj Moško and Přemek Čech. Continuous Hierarchical Exploration of Multimedia Collections
  • Jennifer Roldan Carlos, Mathias Lux, Xavier Giro-I-Nieto, Pia Munoz and Nektarios Anagnostopoulos. Event Video Retrieval using Global and Local Descriptors in Visual Domain
  • Klamer Schutte, Henri Bouma, John Schavemaker, Laura Daniele, Maya Sappelli, Gijs Koot, Pieter Eendebak, George Azzopardi, Martijn Spitters, Maaike de Boer, Maarten Kruithof and Paul Brandt. Interactive detection of incrementally learned concepts in images with ranking and semantic query interpretation
  • Alejandro Ramirez, Jenny Benois-Pineau, Mireya Saraí García Vázquez, Andrei Stoian, Michel Crucianu, Mariko Nakano, Francisco Garcia Ugalde, Jean-Luc Rouas, Henri Nicolas and Jean Carrive. The Mex-Culture multimedia platform Preservation and dissemination of the Mexican Culture

Poster session

  • Chahid Ouali, Pierre Dumouchel and Vishwa Gupta. GPU Implementation of an Audio Fingerprints Similarity Search Algorithm
  • Abdelkader Hamadi, Philippe Mulhem and Georges Quénot. Temporal re-scoring vs. temporal descriptors for semantic indexing of videos
  • Michele Svanera, Sergio Benini, Nicola Adami, Riccardo Leonardi and András Bálint Kovács. Over-the-Shoulder Shot Detection in Art Films
  • Faranak Sobhani, Nur Farhan Kahar and Qianni Zhang. An Ontology Framework for Automated Visual Surveillance System
  • Robert Gregor, Andreas Lamprecht, Ivan Sipiran, Tobias Schreck and Benjamin Bustos. Empirical Evaluation of Dissimilarity Measures for 3D Object Retrieval with Application to Multi-Feature Retrieval
  • Rémi Auguste, Pierre Tirilly and Jean Martinet. Introducing FoxPersonTracks: a Benchmark for Person Re-Identification from TV Broadcast Shows
  • Tomáš Grošup and Premysl Cech. Comparison of metric space browsing strategies for efficient image exploration
  • Zeyd Boukhers, Kimiaki Shirahama, Frédéric Li and Marcin Grzegorzek. Object Detection and Depth Estimation for 3D Trajectory Extraction
  • Merih Seran Uysal, Christian Beecks and Thomas Seidl. On Efficient Content-based Near-duplicate Video Detection
  • Navid Rekabsaz, Ralf Bierig, Bogdan Ionescu, Allan Hanbury and Mihai Lupu. On the Use of Statistical Semantics for Metadata-based Social Image Retrieval
  • Taner Danisman, Jean Martinet and Ioan Marius Bilasco. Pruning near-duplicate images for mobile landmark identification: a graph theoretical approach
  • Nikos Zikos and Anastasios Delopoulos. Fast Geometric Consistency Test for Real Time Logo Detection
  • Mateusz Budnik, Efrain-Leonardo Gutierrez-Gomez, Bahjat Safadi and Georges Quénot. Learned features versus engineered features for semantic video indexing