The proliferation of low-cost infrared cameras gives us a new angle for attacking many unsolved vision problems by leveraging a larger range of the electromagnetic spectrum. A fir...
Nigel J. W. Morris, Shai Avidan, Wojciech Matusik,...
In this paper we present two contributions to improve accuracy and speed of an image search system based on bag-of-features: a contextual dissimilarity measure (CDM) and an effici...
In visual 3-D reconstruction tasks with mobile cameras, one wishes to move the cameras so that they provide the views that lead to the best reconstruction result. When the camera ...
Stefan Wenhardt, Benjamin Deutsch, Elli Angelopoul...
The compositional nature of visual objects significantly limits their representation complexity and renders learning of structured object models tractable. Adopting this modeling ...
Current approaches to motion category recognition typically focus on either full spatiotemporal volume analysis (holistic approach) or analysis of the content of spatiotemporal in...