Programme

The workshop day is scheduled on 29 August 2017.

09:00 – 09:10       Organizers Welcome Speech

09:10 – 09:30       Talk from Nvidia (Serge Palaric)

09:30 – 10:30

Holistic Recognition of Low Quality License Plates by CNN using Track Annotated Data – Jakub Špaňhel, Jakub Sochor, Roman Juránek, Adam Herout, Lukáš Maršík, Pavel Zemčík,

Park Smart – Daniele Di Mauro, Marco Moltisanti Giovanni Patanè, Sebastiano Battiato, GiovanniMaria Farinella

Abnormal Crowd Behavior Detection Using Novel Optical Flow-Based Features – Cem Direkoglu, Melike Sah, Noel O’Connor

 

10:30 – 11:00       Caffè Break

11:00 – 13:00

Spatial Pyramid Context-Aware Moving Vehicle Detection and Tracking in Urban Aerial Imagery – Mahdieh Poostchi, Kannappan Palaniappan, Guna Seetharaman

Online pedestrian tracking with multi-stage re-identification – Yifan Jiang, Hyunhak Shin, Jaeyong Ju, Hanseok Ko

Multi-Pedestrian Detection and Tracking using Unified Multi-channel Features – Young Chul Lim, Min Sung Kang

Deep Trajectory Representation-Based Clustering for Motion Pattern Extraction in Videos – Jonathan Boyle, Tahir Nawaz, James Ferryman

Semantic Labeling for improved Vehicle Detection in Aerial Imagery – Lars Sommer, Kun Nie, Arne Schumann, Tobias Schuchert, Jürgen Beyerer

14:00 – 15:30

Dynamic representations for autonomous driving – Juan Sebastian Olier, Pablo Marín-Plaza, David Martín, Lucio Marcenaro, Emilia Barakova, Matthias Rauterberg, Carlo Regazzoni

Combining LiDAR Space Clustering and Convolutional Neural Networks for Pedestrian Detection – Damien Matti, Hazım Kemal Ekenel, Jean-Philippe Thiran

An Open-data, Agent-based Model of Alcohol Related Crime – Joseph Redfern, Kirill Sidorov, Paul L. Rosin, Simon C. Moore, Padraig Corcoran, David Marshall

Multimodal Vehicle Type Classification Using Convolutional Neural Network and Statistical Representations of MFCC – Berkay Selbes, Mustafa Sert

 

15:30 – 16:00       Caffè Break

16:00 – 16:20       Challenge Presentation (Siwei Lyu)

16:20 – 17:30       Challenge spotlight presentations (12 oral presentation supported by slides 5 minutes each. Each presentation will provide only method and results)

17:30 – 19:00       Poster session for challenge works (12 posters)

Robust Multi-object Tracking with Semantic Color Correlation – Noor Al-Shakarji, Filiz Bunyak, Guna Seetharaman, Kannappan Palaniappan

Joint Tracking with Event Grouping and Temporal Constraints – Wei Tian, Martin Lauer

High-Speed Tracking-by-Detection Without Using Image Information – Erik Bochinski, Volker Eiselein, Thomas Sikora

Sequential Sensor Fusion Combining Probability Hypothesis Density and Kernelized Correlation Filters for Multi-Object Tracking in Video Data – Tino Kutschbach, Erik Bochinski, Volker Eiselein, Thomas Sikora

Geometric Proposals for Faster R-CNN – Sikandar Amin, Fabio Galasso

Vehicle Detection with Sub-Class Training using R-CNN for the DETRAC Benchmark – Sitapa Rujikietgumjorn, Nattachai Watcharapinchai

Evolving boxes for fast vehicle detection (E-B) – Li Wang, Yao Lu, Hong Wang, Yingbin Zheng,Hao Ye, Xiangyang Xue.

Towards lightweight convolutional neural networks for object detection (SSDR) – Dimitriy Anisimov, Tatiana Khanova

Faster R-CNN with ResNet101 (FRCNN-Res) – Nenghui Song, Yi Wei, Ming-Ching Chang

Region-based Deformable Fully Convolu-tional Network (DFCN) – Shuo Wang, Koray Ozcan

Higher-order Graph and Flow network based Tracker (HGFT) – Xiaoyi Yu, Guang Han

E Multi-task Deep Learning for Fast Online Multiple Object Tracking (MTT) – Yuqi Zhang, Yongzhen Huang, Liang Wang

 

Annunci