We address the problem of dynamic event recognition in videos. This is motivated by increasing needs for contentbased exploitation of video footage, as encouraged in numerous applications, e.g., retrieving video sequences in large TV archives, creating automatic video summarization of sport TV programs, or detecting specific actions or activities in video-surveillance. It implies to tackle the well-known semantic gap between computed low-level features and high-level concepts. Considering 2D trajectories is attractive since they form computable image features which capture elaborated spatio-temporal information on the viewed actions. Methods for tracking moving objects in an image sequence are now available to get reliable enough 2D t...
This thesis explores motion trajectory-based approaches to recognize human actions in real-world, un...
The exploitation of video data requires to extract information at a rather semantic level, and then,...
In this paper, we address the problem of motion recognition using event-based local motion represent...
This paper focuses on evaluation of motion of objects through classification of their trajectories. ...
Motion is an important cue for video understanding and is widely used in many semantic video analyse...
This paper focuses on evaluation of motion of objects through classification of their trajectories. ...
The growing number of video data makes often difficult, even impossible, any attemptof watching them...
This paper presents a method for statistical modeling and classifi-cation of motion trajectories usi...
This thesis focuses on monitoring non-specific and unconstrained activities and events in videos in ...
We present new probabilistic motion models of interest for the detection of meaningful dynamic conte...
The exploitation of video data requires methods able to extract high-level information from the imag...
International audienceThe exploitation of video data requires methods able to extract high-level inf...
International audienceThe exploitation of video data requires methods able to extract high-level inf...
Abstract—Society is rapidly accepting the use of video cameras in many new and varied locations, but...
International audienceThe exploitation of video data requires methods able to extract high-level inf...
This thesis explores motion trajectory-based approaches to recognize human actions in real-world, un...
The exploitation of video data requires to extract information at a rather semantic level, and then,...
In this paper, we address the problem of motion recognition using event-based local motion represent...
This paper focuses on evaluation of motion of objects through classification of their trajectories. ...
Motion is an important cue for video understanding and is widely used in many semantic video analyse...
This paper focuses on evaluation of motion of objects through classification of their trajectories. ...
The growing number of video data makes often difficult, even impossible, any attemptof watching them...
This paper presents a method for statistical modeling and classifi-cation of motion trajectories usi...
This thesis focuses on monitoring non-specific and unconstrained activities and events in videos in ...
We present new probabilistic motion models of interest for the detection of meaningful dynamic conte...
The exploitation of video data requires methods able to extract high-level information from the imag...
International audienceThe exploitation of video data requires methods able to extract high-level inf...
International audienceThe exploitation of video data requires methods able to extract high-level inf...
Abstract—Society is rapidly accepting the use of video cameras in many new and varied locations, but...
International audienceThe exploitation of video data requires methods able to extract high-level inf...
This thesis explores motion trajectory-based approaches to recognize human actions in real-world, un...
The exploitation of video data requires to extract information at a rather semantic level, and then,...
In this paper, we address the problem of motion recognition using event-based local motion represent...