M
Marcin Marszalek
Researcher at French Institute for Research in Computer Science and Automation
Publications - 19
Citations - 10691
Marcin Marszalek is an academic researcher from French Institute for Research in Computer Science and Automation. The author has contributed to research in topics: Support vector machine & Cognitive neuroscience of visual object recognition. The author has an hindex of 16, co-authored 19 publications receiving 10246 citations. Previous affiliations of Marcin Marszalek include University of Oxford.
Papers
More filters
Proceedings ArticleDOI
Learning realistic human actions from movies
TL;DR: A new method for video classification that builds upon and extends several recent ideas including local space-time features,space-time pyramids and multi-channel non-linear SVMs is presented and shown to improve state-of-the-art results on the standard KTH action dataset.
Proceedings ArticleDOI
A Spatio-Temporal Descriptor Based on 3D-Gradients
TL;DR: This work presents a novel local descriptor for video sequences based on histograms of oriented 3D spatio-temporal gradients based on regular polyhedrons which outperform the state-of-the-art.
Journal ArticleDOI
Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study
TL;DR: A large-scale evaluation of an approach that represents images as distributions of features extracted from a sparse set of keypoint locations and learns a Support Vector Machine classifier with kernels based on two effective measures for comparing distributions, the Earth Mover’s Distance and the χ2 distance.
Proceedings ArticleDOI
Actions in context
TL;DR: This paper automatically discover relevant scene classes and their correlation with human actions, and shows how to learn selected scene classes from video without manual supervision and develops a joint framework for action and scene recognition and demonstrates improved recognition of both in natural video.
Proceedings ArticleDOI
Semantic Hierarchies for Visual Object Recognition
Marcin Marszalek,Cordelia Schmid +1 more
TL;DR: The semantics of image labels are used to integrate prior knowledge about inter-class relationships into the visual appearance learning and to build and train a semantic hierarchy of discriminative classifiers and how to use it to perform object detection.