— A good motion model is a prerequisite for many approaches to simultaneous localization and mapping. Without an absolute reference, it is however difficult to prevent drift whe...
This paper regards images with captions as a cross-media parallel corpus, and presents a corpus-based relevance feedback approach to combine the results of visual and textual runs....
Given a large repository of geotagged imagery, we seek to automatically find visual elements, e.g. windows, balconies, and street signs, that are most distinctive for a certain g...
Carl Doersch, Saurabh Singh, Abhinav Gupta, Josef ...
Experimental structure analysis of biological molecules (e.g, proteins) or macromolecular complexes (e.g, viruses) can be used to generate three-dimensional density maps of these e...
Stefan Burkhardt, Kimmo Fredriksson, Tuomas Ojamie...
Survey knowledge of spatial environments can be successfully conveyed by visual maps. For visually impaired people, tactile maps have been proposed as a substitute. The latter are ...