THEMIS'2008

Programme

September 5th, 2008

  • 09.00 - 9.05 Welcome by the oganisers

  • 09.05 - 10.00 Keynote Address: François Brémond

  • 10:00 - 10:30 Poster Presentations (5 min. each)

    • Paper 21: A Simple Real-time Approach for Action Separation into Action Primitives

    • Paper 20: Building Temporal Templates for Human Behaviour Classification

    • Paper 16: Tracking Stick Figures with Hierarchical Articulated ICP

    • Paper 22: On the Evaluation of a Face Vision-Based Interface

    • Paper 14: Real-time video-based eye blink analysis for detection of low blink-rate during computer use

  • 10.30 – 11.00 Coffee Break + Poster Session

  • 11.00 - 12.30 Oral Session I: From pixels to trajectories

    • Paper 5: Human Intrusion Detection using Texture Classification in Real- Time

    • Paper 17: AD-HOC: Appearance Driven Human tracking with Occlusion Handling

    • Paper 10: Tracking Face Localization with a Hierarchical Progressive Face Model

  • 12.30 - 13.30 Lunch Break

  • 13.30 - 15.00 Oral Session II: From trajectories to behaviours

    • Paper 9: String-based Spectral Clustering for Understanding Human Behaviours

    • Paper 12: Finding Prototypes to Estimate Trajectory Development in Outdoor Scenarios

    • Paper 4: Automatic primitive finding for action modeling

  • 15.00 - 15.30 Coffee Break + Poster Session

  • 15.30 - 16.30 Oral Session III: From behaviours to cognition

    • Paper 19: Abduction for human behaviour analysis in video surveillance scenarios

    • Paper 15: Cognitive-Guided Semantic Exploitation in Video Surveillance Interfaces

  • 16.30 - 16.45 Closing remarks + Best Paper award


Invited Speaker

François Brémond, INRIA Sophia Antipolis, France

Abstract: Scene understanding is influenced by cognitive vision and it requires at least the melding of three areas: computer vision, cognition and software engineering. Scene understanding can achieve four levels of generic computer vision functionality of detection, localization, recognition and understanding. But scene understanding systems go beyond the detection of visual features such as corners, edges and moving regions to extract information related to the physical world which is meaningful for human operators. Its requirement is also to achieve more robust, resilient, adaptable computer vision functionalities by endowing them with a cognitive faculty: the ability to learn, adapt, weigh alternative solutions, and develop new strategies for analysis and interpretation. The key characteristic of a scene understanding system is its capacity to exhibit robust performance even in circumstances that were not foreseen when it was designed. Furthermore, a scene understanding system should be able to anticipate events and adapt its operation accordingly. Ideally, a scene understanding system should be able to adapt to novel variations of the current environment to generalize to new context and application domains and interpret the intent of underlying behaviors to predict future configurations of the environment, and to communicate an understanding of the scene to other systems, including humans.