Daniel Collobert

Learn More
A new hand gesture recognition method based on Input– Output Hidden Markov Models is presented. This method deals with the dynamic aspects of gestures. Gestures are extracted from a sequence of video images by tracking the skin–color blobs corresponding to the hand into a body– face space centered on the face of the user. Our goal is to recognize two(More)
Recently, a lot of papers have been published in the field of time series prediction using connectionist models. Nevertheless we think that one of the major problem with is rarely treated in the literature is related to the choice of input parameters (embedding dimension and delay). In this paper, we propose two modular approaches to this problem and apply(More)
Both visual and acoustical informations provide effec– tive means of telecommunication between persons. In this context, the face is the most important part of the person both visually and acoustically. We describe how the co– operation of image and audio processing allows to track a person’s face and to collect the audio information it pro– duces. We(More)
A generative neural network model, constrained by non-face examples chosen by an iterative algorithm, is applied to face detection. To improve the generalization ability of the model, another constraint based on the minimum description length is added. This model is tested and compared with another state-of-the-art face detection system on a large image(More)
A real time system is described for automatic detection and tracking of multiple persons, in the context of video-conferencing systems. This system, called MULTRAIl (MUltiperson Locating and TRacking Automatic Iiernel), is able to continuously detect and track the position of faces in its field of view. The heart of the system is a modular neural network(More)
Abs t r ac t . We present a neural network approach to human face detection. Using a modular system, a conditional mixture of networks, we a r e able to detect front view faces as well as turned faces (up to 50 degrees) with excellent performances. This modular network is integrated into LISTEN, our face tracking system. It enables this system to detect and(More)
A new method to maximize the margin of MLP classifier in classification problems is described. Thismethod is based on a new cost function which minimizes the variance ofthe mean squared error. We show that with this cost function the generalizationperformance increase. This method is tested and compared with the standard mean square errorand is applied to a(More)
Using real traac data, we show that neural network-based prediction techniques can be used to predict the queuing behaviour of highly bursty traacs typical of LAN interconnection in a way accurate enough so as to allow dynamical renegotiation of a DBR traac contract at the edge of an ATM network. The performances of predictor-based in service renegotiation(More)
  • 1