VASC Seminar

Event Location: NSH 1507Bio: Olivier Duchenne received the M.S. degree in Computer Science and Applied Mathematics in École Normale Supérieure (ENS), in Paris in 2008. He then joined as a phD candidate the research team, WILLOW in the same university under the supervision of professor Jean Ponce. He received the best student paper, honorable mention, [...]

Abstract: We consider the problem of quantizing data generated from disparate sources, e.g. subjects performing actions with different styles, movies with particular genre bias, various conditions in which images of objects are taken, etc. These are scenarios where unsupervised clustering produces inadequate codebooks because algorithms like K-means tend to cluster samples based on data biases [...]

Event Location: NSH 1507Abstract: In this talk, I will present a method to reconstruct an articulated trajectory in 3D given the 2D projection of the articulated trajectory, the 3D parent trajectory, and the camera pose at each time instant. This is a core challenge in reconstructing the 3D motion of articulated structures such as the [...]

Event Location: NSH 1507Abstract: We propose an approach to identify and segment objects from scenes that a person (or robot) encounters in Activities of Daily Living (ADL). Images collected in those cluttered scenes contain multiple objects. Each image provides only a partial, possibly very different view of each object. An object instance discovery program must [...]

Event Location: NSH 1507Abstract: Progress in action recognition has been in large part due to advances in the features that drive learning-based methods. However, the relative sparsity of training data and the risk of overfitting have made it difficult to directly search for good features. In this work we suggest using synthetic data to search [...]