Schedule & author guidelines for oral presentations

Final Program:

Wednesday 12 December 2018

  • 8.30 am: Registration
  • 9.30 am: Welcome ceremony & Opening & Coffee Break
  • 10.30 am: Plenary talk by Jean Marc Odobez (Switzerland)
  • 11.30 pm: Oral sessions O2 and O7
  • 12.30 pm: Lunch
  • 2.00 pm: Oral sessions O1 and O3
  • 3.30 pm: Coffee break
  • 4.00 pm: Special Session SS1
  • 5.00 pm: Panel discussion

Thursday 13 December 2018

  • 8.30 am: Plenary talk by Josiane Zerubia
  • 9.30 am: Plenary talk by Vittorio Murino (Italy)
  • 10.30 am: Coffee break
  • 11.00 am: Oral sessions O6
  • 12.30 pm: Lunch
  • 2.00 pm-3.15 pm : Oral sessions O4 and O5
  • 3.15 pm-8.00 pm: Industrial Exhibition & Social Event & Gala Dinner

Friday 14 December 2018

  • 8.30 am: Plenary talk by François Bremond ( France)
  • 9.30 am: Special Session SS2
  • 10.30 am: Coffee break
  • 11.00 pm: Oral sessions O8 and O9
  • 12.30 pm:  Closing session

Detailed Sessions:

Session O1:  Image  Understanding & Semantic Analysis 

  • Ya Wang and Andreas Zell, Improving Feature-based Visual SLAM by Semantics, Germany
  • Paria Yousefi and Ludmila Kuncheva, Selective Keyframe Summarisation for Egocentric Videos Based on Semantic Concept Search, United Kingdom and Iran
  • Pierluigi Zama Ramirez, Alessio Tonioni and Luigi Di Stefano, Exploiting Semantics in Adversarial Training for Image-Level Domain Adaptation, Italy
  • Stefano Allegretti, Federico Bolelli, Michele Cancilla and Costantino Grana, Optimizing GPU-Based Connected Components Labeling Algorithms, Italy
  • Francesco Verrini, Carlos Fernando Crispim-Junior, Manuela Chessa, Fabio Solari and Francois Bremond, Recognition of Daily Activities by embedding hand-crafted features within a semantic language, Italy
  • Jaewon Jung and Jongyoul Park, Visual Relationship Detection with Language prior and Softmax, South Korea

Session O2: Image Processing and Pattern Recognition 

  • Zheng Cui, Sasan Mahmoodi and Michael Bennett,  A Robust and High-performance Shape Registration Technique Using Characteristic Functions, United Kingdom
  • Baljit Singh Khehra, Arjan Singh, Gurdeep Singh Hura and Lovepreet Kaur, Fuzzy 2-Partition Kapur Entropy for Image Segmentation Using Teaching-Learning-Based Optimization Algorithm, India
  • Przemysław Skurowski and Paweł Kasprowski, Evaluation of Saliency Maps in a Hard Case – Images of Camouflaged Animals, Poland
  • Guoan Yang, An Optimization Approach of Compressive Sensing Recovery Using Split Quadratic Bregman Iteration with Smoothed ℓ0 Norm, China

Session O3:  Image Understanding and Activity Recognition

  • Soumia Jabri, Mustapha Saidallah, Abdelbaki El Belrhiti El Alaoui and El Fergougui Abdeslam, Mono-vision based moving vehicle detection, Morocco
  • Anwaar Ulhaq, Action Recognition in The Dark via Deep Multi-view Learning, Australia
  • Anwaar Ulhaq, Deep Cross-view Convolutional Features for View-invariant Action Recognition, Australia
  • Kaustubh Sakhalkar and Francois Bremond, Learning to Represent Spatio-Temporal Features for Fine Grained Action Recognition, India
  • Sungwoo Jun and Yoonsik Choe, Deep Batch-Normalized LSTM networks with Auxiliary classifier for Skeleton based Action Recognition, South Korea
  • Abhishek Goel, Abdelrahman Abubakr, Michal Koperski, Francois Bremond and Gianpiero Francesca, Online temporal detection of daily-living human activities in long untrimmed video streams, India

Session O4: Image Processing and Biometrics

  • Jake Burton, David Frank, Mahdi Saleh, Nassir Navab and Helen L. Bear, The speaker-independent lipreading play-off; a benchmarking survey for lipreading machines, Germany
  • Sana Boujnah, Sami Jaballah and Mohamed Lassaad Ammari, Smartphone-Captured Ear and Voice Database in Degraded Conditions, Tunisia
  • Ahmed Fnaiech, Sami Bouzaiane, Mounir Sayadi, Nicolas Nicolas Louis and Philippe Gorce, Real Time 3D Facial Emotion Classification using a Digital Signal PIC Microcontroller Signal PIC Microcontroller, Tunisia
  • Ignacio Viedma and Juan Tapia, Deep Gender Classification and Visualization of Near-Infra-Red Periocular-Iris images, Chile

Session O5: 3D Image Processing and Understanding

  • Okan Köpüklü and Gerhard Rigoll, Analysis on Temporal Dimension of Inputs for 3D Convolutional Neural Networks, Germany
  • Julius Schöning and Gunther Heidemann, Image-based 3D Reconstruction: Neural Networks vs. Multiview Geometry, Germany
  • Tuan Anh Nguyen and Sukhan Lee, 3D Orientation and Object Classification from Partial Model Point Cloud based on PointNet, South Korea
  • Laura Krieger, Gunther Heidemann and Julius Schöning, Object of Interest Segmentation in Video Sequences with Gaze Data, Germany
  • Isabel Patino Mejia and Andreas Zell, 3D Reconstructions with KinFu Using Different RGBD Sensors, Germany

Session O6:  Deep Learning and Image Understanding

  • Alessio Tonioni, Eugenio Serra and Luigi Di Stefano, A deep learning pipeline for product recognition in store shelves, Italy
  • Amgad Muhammad and Mohamed Moustafa, Improving region based CNN object detector using Bayesian Optimization, Egypt
  • Ying Deng and Hong Zheng, Memory Network for Tracking with Deep Regression, China
  • Rémi Dufour, Cyril Meurie and Amaury Flancquart, An intuitive semi-automatic video database annotation software designed for hazardous user behavior in guided mountain transport, France
  • Siddharth Balakrishnan, David Langerman, Evan Gretok and Alan George, Deep Learning for Hyperspectral Image Classification on Embedded Platforms, United States
  • Abdelouahid Ben Tamou, Abdesslam Benzinou, Kamal Nasreddine and Lahoucine Ballihi, Transfer Learning with deep Convolutional Neural Network for Underwater Live Fish Recognition, France

Session O7: Low level Image Processing

  • Sanghyun Ko and Sukhan Lee, 3D Point Cloud Matching and Odometry Based on its 2D Representation, South Korea
  • Wael Ahmed, John Shi and Wenbin Xu, Modeling Complex Building Structure (LoD2) using image-based point cloud, Hong Kong
  • Manuela Chessa and Fabio Solari, A geometric model of spatial distortions in virtual and augmented environments, Italy
  • Bertil Grelsson, Andreas Robinson, Michael Felsberg and Fahad Khan, HorizonNet for visual terrain navigation, Sweden

Session O8: Image processing and applications: Medical Diagnosis and Augmented Reality

  • Hanene Sahli, Aymen Mouelhi, Mounir Sayadi and Radhouane Rachdi, Discriminant Textural Feature Selection and Classification for a Computerized Fetal Hydrocephalus Detection, Tunisia
  • Dibash Basukala, Dr. Ramakrishnan Mukundan, Dr. Tracy Melzer and Dr. Ross Keenan, Segmentation of Substantia Nigra for the Automated Characterization of Parkinson’s Disease, New Zealand
  • Chun Xie, Hidehiko Shishido, Mika Oki, Yoshinari Kameda, Kenji Suzuki and Itaru Kitahara, A Calibration Method of Floor Projection System for Learning Aids at School Gym, Japan
  • Mohamed Elkhouly, Stuart James and Alessio Del Bue, Multi-view Aggregation for Color Naming with Shadow Detection and Removal, Italy
  • Jie Yan, An Animated Virtual Agent Based Tutoring System for Improving Student Engagement, United States

Session O9: Image Processing and Smart Applications

  • Zoltan Rozsa and Tamas Sziranyi, Street object classification via LIDARs with only a single or a few layers, Hungary
  • Dzenana Alagic and Jürgen Pilz, Unsupervised Algorithm to Detect Damage Patterns in Microstructure Images of Metal Films, Austria
  • Federico Bolelli, Lorenzo Baraldi and Costantino Grana, A Hierarchical Quasi-Recurrent approach to Video Captioning, Italy
  • David Langerman, Sebastian Sabogal, Barath Ramesh and Alan George, Accelerating Real-Time, High-Resolution Depth Up-sampling on FPGAs, United States
  • Saadia Batool, Muhammad Moazam Fraz and Muhammad Zeeshan Ali, End to End Person Re-Identification for Automated Visual Surveillance, Pakistan

special Session SS1: Circuits and Systems for Self-organizing Maps 

       Chairs: Prof. Hassan Rabah & Prof. Slavisa Jovanovic

  • Hiroomi Hikawa, Hidetaka Ito and Yutaka , Maeda, A New Hardware Self-Organizing Map Architecture with High Expandability. Japan
  • Laurent Rodriguez, Lyes Khacef and Benoît Miramond, A distributed cellular approach of large scale SOM models for hardware implementation, France
  • Slavisa Jovanovic, Hassan Rabah and Serge Weber, High performance scalable hardware SOM architecture for real-time vector quantization, France
  • Khaled Ben Khalifa and Mohamed Hedi Bedoui, A Systolic Hardware Architecture of Self-Organizing Map, Tunisia

Special session SS2:  Deep learning for Computer-Aided Diagnosis (CAD) systems

       Chairs: Prof. Nawres Khalifa &  Prof. Ramzi Guetari

  • Mohammad Faizal Ahmad Fauzi, Mohammad Fareed Jamaluddin, Jenny T. H. Lee, Kean H. Teoh and Lai M. Looi, Tumor Region Localization in H&E Breast Carcinoma Images Using Deep Convolutional Neural Network, Malaysia
  • Yibao Sun, Zhaoyang Xu, Carina Strell, Carlos Fernández Moro, Fredrik Wärnberg, Le Dong and Qianni Zhang, Detection of Breast Tumour Tissue Regions in Histopathological Images using Convolutional Neural Networks, United Kingdom
  • Hajer Khachnaoui, Ramzi Guetari and Nawres Khlifa, A review on Deep Learning in thyroid ultrasound Computer-Assisted Diagnosis systems, Tunisia
  • Ines Rahmany, Ramzi Guetari and Nawres Khlifa, A Fully Automatic based Deep Learning Approach for Aneurysm Detection in DSA Images, Tunisia

Author guidelines for oral presentations:

Oral presenters will have 15 minutes for their presentations (approximately 13 minutes for the talk, and 2 minutes for questions). Please make sure you introduce yourself to the session chair and you upload your presentation in the lecture room where your talk will take place, at least 10 minutes prior to the beginning of your session.

A computer and a data projector will be available. Please bring your presentation on a USB memory stick. Accepted file formats are MS-Power Point PPT and Adobe PDF.

Speakers  can  use  their  own  computers  for  the  presentation.  This  option  is  not  recommended  if  the presentation is a standard PPT or PDF file.

The registration desk will be available for speakers requiring assistance with format conversions, file upload etc.

When your session is over, your presentation will be deleted from all computers, no copies or backups will be made.