Multiple Instance Learning (MIL) has been widely exploited in many computer vision tasks, such as image retrieval, object tracking and so on. To handle ambiguity of instance label...
Huge amount of manual efforts are required to annotate large image/video archives with text annotations. Several recent works attempted to automate this task by employing supervis...
Abstract: Collaborative learning systems can be constructed following the serviceoriented computing paradigm. This allows educators to integrate external tools, offered as services...
Guillermo Vega-Gorgojo, Miguel L. Bote-Lorenzo, Ed...
— While robot mapping has seen massive strides , higher level abstractions in map representation are still not widespread. Maps containing semantic concepts such as objects and l...
As semantic markup becomes ubiquitous, it will become important to be able to ask queries and obtain answers, using natural language (NL) expressions, rather than the keyword-based...