M
Michal Irani
Researcher at Weizmann Institute of Science
Publications - 163
Citations - 28616
Michal Irani is an academic researcher from Weizmann Institute of Science. The author has contributed to research in topics: Motion estimation & Computer science. The author has an hindex of 73, co-authored 150 publications receiving 25714 citations. Previous affiliations of Michal Irani include IEEE Computer Society & Hebrew University of Jerusalem.
Papers
More filters
Proceedings ArticleDOI
Actions as space-time shapes
TL;DR: The method is fast, does not require video alignment and is applicable in many scenarios where the background is known, and the robustness of the method is demonstrated to partial occlusions, non-rigid deformations, significant changes in scale and viewpoint, high irregularities in the performance of an action and low quality video.
Journal ArticleDOI
Improving resolution by image registration
Michal Irani,Shmuel Peleg +1 more
TL;DR: In this paper, the relative displacements in image sequences are known accurately, and some knowledge of the imaging process is available, and the proposed approach is similar to back-projection used in tomography.
Proceedings ArticleDOI
Super-resolution from a single image
TL;DR: This paper proposes a unified framework for combining the classical multi-image super-resolution and the example-based super- resolution, and shows how this combined approach can be applied to obtain super resolution from as little as a single image (with no database or prior examples).
Journal ArticleDOI
Actions as Space-Time Shapes
TL;DR: The method is fast, does not require video alignment, and is applicable in many scenarios where the background is known, and the robustness of the method is demonstrated to partial occlusions, nonrigid deformations, significant changes in scale and viewpoint, high irregularities in the performance of an action, and low-quality video.
Proceedings ArticleDOI
In defense of Nearest-Neighbor based image classification
TL;DR: It is argued that two practices commonly used in image classification methods, have led to the inferior performance of NN-based image classifiers: Quantization of local image descriptors (used to generate "bags-of-words ", codebooks) and Computation of 'image-to-image' distance, instead of ' image- to-class' distance.