This paper proposes an incremental multiple-object recognition and localization (IMORL) method. The objective of IMORL is to adaptively learn multiple interesting objects in an ima...
We develop an optical flow estimation framework that focuses on motion estimation over time formulated in a Dynamic Bayesian Network. It realizes a spatiotemporal integration of ...
Volker Willert, Marc Toussaint, Julian Eggert, Edg...
Real-world, multiple-typed objects are often interconnected, forming heterogeneous information networks. A major challenge for link-based clustering in such networks is its potent...
This paper integrates expectancy disconfirmation theory and justice theory to construct a model for investigating the motivations behind people’s knowledge sharing in open profe...
Chao-Min Chiu, Eric T. G. Wang, Fu-Jong Shih, Yi-W...
Non-negative tensor factorization (NTF) is a relatively new technique that has been successfully used to extract significant characteristics from polyadic data, such as data in s...