9:25 – 9:30 – Welcome by the organisers
9:30 – 10:30 – Oral session I: Video Features and Scene Analysis
Video Scene Classification based on Natural Language Description
Lei Zhang (Harbin engineering university),
Muhammad Usman Ghani Khan (The University of Sheffield),
Yoshihiko Gotoh (University of Sheffield)
On Improving the Robustness of Differential Optical Flow
Hatem Ibrahim Mahmoud (Roviria i Virgili University),
Domenec Valls (Universitat de Roivira i Virgili),
Miguel Garcia (Universidad Autónoma de Madrid)
10:30 – 11:30 – Coffee break / poster presentations / demo
11:30 – 13:00 – Oral session II: Crowd analysis
Detecting Individual in Crowd with Moving Feature’s Structure Consistency
Yuanhao Yu (NLPR,CASIA),
Zhen Lei (NLPR,CASIA),
Dong Yi (NLPR,CASIA),
Stan Z. Li (NLPR,CASIA)
Automatic Crowd Density and Motion Analysis in Airborne Image Sequences Based on a Probabilistic Framework
Beril Sirmacek (German Aerospace Center (DLR)),
Peter Reinartz (German Aerospace Center (DLR))
Spatiotemporally Localized New Event Detection in Crowds
Alexia Briassouli (CERTH ITI),
Yannis Kompatsiaris (CERTH-ITI)
13:00 – 14:00 – Lunch break
14:00 – 16:00 – Oral Session III: Human activity and gesture analysis
On the Effect of Temporal Information on Monocular 3D Human Pose Estimation
Jürgen Brauer (Fraunhofer IOSB),
Wenjuan Gong (Computer Vision Center),
Jordi Gonzalez (CVC),
Michael Arens (Fraunhofer IOSB)
People appearance tracing in videos by spectral graph transduction
Dalia Coppi (University of Modena and RE),
Simone Calderara (University of Modena and RE),
Rita Cucchiara (University of Modena and RE)
Learning Temporal Signatures for Lip Reading
Eng-Jon Ong (University of Surrey),
Richard Bowden (University of Surrey)
Reading the Signs : A Video Based Sign Dictionary
Helen Cooper (University of Surrey),
Richard Bowden (University of Surrey),
Nicolas Pugeault (University of Surrey)
16:00 – 16:30 – Coffee break / poster presentations / demo
16:30 – 18:00 – Oral session IV: Activity recognition
Automatic Analysis of Composite Activities in Video Sequences Using Key Action Discovery and Hierarchical Graphical Models
Ioannis Kaloskampis (Cardiff University),
Yulia Hicks (Cardiff University),
David Marshall (Cardiff University)
High-Level Situation Recognition Using Fuzzy Metric Temporal Logic, Case Studies in Surveillance and Smart Environments
David Muench (Fraunhofer IOSB),
Joris IJsselmuiden (Fraunhofer IOSB),
Michael Arens (Fraunhofer IOSB),
Rainer Stiefelhagen (Karlsruhe Institue of Technology, Fraunhofer IOSB)
Video summarization guiding evaluative rectification for industrial activity recognition
Athanasios Voulodimos (NTUA),
Anastasios Doulamis (Technical University of Crete),
Dimitrios Kosmopoulos (University of Texas at Arlington),
Theodora Varvarigou (NTUA)
18:00 – 18:15 – Closing remarks