2 Hits in 1.2 sec

Learning Language-Visual Embedding for Movie Understanding with Natural-Language [article]

Atousa Torabi, Niket Tandon, Leonid Sigal
2016 arXiv   pre-print
elements in "Predicate + Object" (PO) phrases based on "Knowlywood", an activity knowledge mining model.  ...  This test facilitate automatic evaluation of visual-language models for natural language video annotation based on human activities.  ...  , N., de Melo, G., De, A., Weikum, G.: Knowlywood: Mining activity knowledge from hollywood narratives. In: Proc. CIKM (2015) 23.  ... 
arXiv:1609.08124v1 fatcat:4nzwhzuvizej3e7ll36gq5pvie

Commonsense knowledge acquisition and applications [article]

Niket Tandon, Universität Des Saarlandes, Universität Des Saarlandes
We develop Knowlywood, a method based on semantic parsing and probabilistic graphical models to compile activity knowledge.  ...  Thus, they cannot produce large-scale, semantically organized commonsense knowledge.  ...  Knowlywood: Mining activity knowledge from hollywood narratives. In Proceedings of the ACM Conference on Information and Knowledge Management (CIKM).  ... 
doi:10.22028/d291-26668 fatcat:6xadpi4sivhi3izn2gpmbca5tu