Page
%P
-
Chapter and Conference Paper
Modular Graph Attention Network for Complex Visual Relational Reasoning
Visual Relational Reasoning is crucial for many vision-and-language based tasks, such as Visual Question Answering and Vision Language Navigation. In this paper, we consider reasoning on complex referring expr...
-
Chapter and Conference Paper
Extremely Randomized Forest with Hierarchy of Multi-label Classifiers
Hierarchy Of multi-label classifiERs (HOMER) is one of the most popular multi-label classification approaches. However, it is limited in its applicability to large-scale problems due to the high computational ...