IEEE/ISPRS 4th Joint Workshop on Multi-Sensor Fusion for Dynamic Scene Understanding
October 23, 2017, Venice, Italy
in conjunction with International Conference on Computer Vision

The venue for the Workshop and ICCV 2017 will be the PALAZZO DEL CINEMA , VENICE CONVENTION CENTER in Venice, Italy.

Keynote Speaker

    HTML5 Icon

  • Radu Horaud, INRIA Grenoble, France
  • Radu Horaud holds a position of director of research at INRIA Grenoble. Radu’s research interests cover computational vision, audio signal processing, audio-visual scene analysis, machine learning, and robotics. He is an associated editor for IJCV and was program co-chair of ICCV’01.
  • HTML5 Icon

  • Bodo Rosenhahn, University of Hannover, Germany
  • Bodo Rosenhahn is Full Professor at the University of Hannover, heading a group on automated image interpretation. His main research interest is computer vision and human motion capture. He published more than 180 research papers. He is general chair of GCPR’16.
  • HTML5 Icon

  • Andreas Geiger, MPI-Tübingen, Germany
  • Andreas Geiger is a Research Group Leader at MPI and a Visiting Professor at ETH Zürich. His main research interests are in computer vision and machine learning with a focus on 3D scene understanding for autonomous intelligent systems such as self-driving cars. He is an associate-editor for PAMI and serves as an area chair for CVPR’17.
  • HTML5 Icon

  • Konrad Schindler, ETH Zurich, Switzerland
  • Konrad Schindler has been Associate Professor of Photogrammetry at ETH Zurich since 2010. He researches in the fields of photogrammetry, remote sensing, computer vision and image understanding. He is an associated editor for ISPRS journal.

  • 08:20-08:30 - Introduction: Michael Ying Yang (University of Twente)

  • 08:30-09:30 - Keynote talk: Konrad Schindler (ETH Zurich)
    Title: Image-based mapping and monitoring of the urban tree population

  • 09:30-09:50 - Ekrem Yurdakul, Yücel Yemez.
    Title: Semantic Segmentation of RGBD Videos with Recurrent Fully Convolutional Neural Networks

  • 09:50-10:10 - Pierre-Luc St-Charles, Guillaume-Alexandre Bilodeau, Robert Bergevin.
    Title: Mutual Foreground Segmentation with Multispectral Stereo Pairs

  • 10:10-10:50 Coffee break

  • 10:50-11:50 - Keynote talk: Bodo Rosenhahn (University of Hannover)
    Title: Multi-Sensor Fusion for Dynamic Human Motion Understanding

  • 11:50-12:10 - Wentong Liao, Michael Ying Yang, Ni Zhan, Bodo Rosenhahn.
    Title: Triplet-based Deep Similarity Learning for Person Re-Identification

  • 12:10-12:30 - Zoltán Pusztai, Levente Hajder.
    Title: Accurate Calibration of LiDAR-Camera Systems using Ordinary Boxes

  • 12:30-14:00 Lunch Break

  • 14:00-15:00 - Keynote talk: Andreas Geiger (MPI-Tübingen)
    Title: Generating Training Data for Deep Neural Networks by exploiting LIDAR, Cameras and Maps

  • 15:00-15:20 - Ryohei Kuga, Asako Kanezaki, Masaki Samejima, Yusuke Sugano, Yasuyuki Matsushita.
    Title: Multi-task Learning using Multi-modal Encoder-Decoder Networks with Shared Skip Connections

  • 15:20-15:40 - Konstantinos Avgerinakis, Panagiotis Giannakeris, Alexia Briassouli, Anastasios Karakostas, Stefanos Vrochidis, Yiannis Kompatsiaris.
    Title: LBP-flow and hybrid encoding for real-time water and fire classification

  • 15:40-16:00 - Trong Phuc Truong, Masahiro Yamaguchi, Shohei Mori, Vincent Nozick, Hideo Saito.
    Title: Registration of RGB and thermal point clouds generated by structure from motion

  • 16:00-16:30 Coffee Break

  • 16:30-17:30 - Keynote talk: Radu Horaud (INRIA Grenoble)
    Title: Exploiting the Complementarity Between Vision and Audio for the Dynamic Analysis of People

  • 17:30-17:40 - Remarks: Alper Yilmaz (Ohio State University)
  • Affiliations