This work provides a framework for learning sequential attention in real-world visual object recognition, using an architecture of three processing stages. The first stage rejects...
Recent progress in information extraction has shown how to automatically build large ontologies from high-quality sources like Wikipedia. But knowledge evolves over time; facts ha...
Yafang Wang, Mingjie Zhu, Lizhen Qu, Marc Spaniol,...
People generally remember locations in visual spaces with respect to spatial features and landmarks. Geographical maps provide many spatial features and hence are easy to remember...
Chorems are schematized representations of territories, and so they can represent a good visual summary of spatial databases. Indeed for spatial decision-makers, it is more importa...
Vincenzo Del Fatto, Robert Laurini, Karla Lopez, R...
We study the problem of event detection from realistic videos with repetitive sequential human activities. Despite the large body of work on event detection and recognition, very ...
Lei Ding, Quanfu Fan, Jen-Hao Hsiao, Sharath Panka...