Humans spend a large amount of time listening, watching, and reading stories. We argue that the ability to model, analyze, and create new stories is a stepping stone towards strong AI. We thus work on teaching AI to understand stories in films and TV series. To obtain a holistic view of the story, we align videos with plot synopses and books; visualize character interactions as a chart; and finally, test machine understanding of stories by asking it to answer questions
The primary objective of this thesis is to develop a method that uses machine learning algorithms to...
This paper describes our research-in-progress which integrates several domains, in particular natura...
Abstract. Computational storytelling systems have mainly focused on the con-struction and evaluation...
Books are a rich source of both fine-grained information, how a character, an object or a scene look...
Computerized systems capable of generating high-level story descriptions have many potential real-li...
We study a fundamental question for developing storytelling machines: what vocabulary is suited for ...
Automatic understanding of stories is a long-time goal of artificial intelligence and natural langua...
Books are a rich source of both fine-grained information, how a character, an object or a scene look...
ii Intelligent multimedia information retrieval deals with massive unstructured data, especially dig...
Intelligent multimedia information retrieval deals with massive unstructured data, especially digita...
We introduce the MovieQA dataset which aims to evaluate automatic story comprehension from both vide...
Thesis (Ph. D.)--University of Rochester. Department of Computer Science, 2017.Building systems that...
| openaire: EC/H2020/780069/EU//MeMADThis chapter focuses on the recent surge of interest in automat...
We summarize recent developments in our platform for symbolically representing and reasoning over hu...
Our work has focused on support for film or television scriptwriting. Since this involves potentiall...
The primary objective of this thesis is to develop a method that uses machine learning algorithms to...
This paper describes our research-in-progress which integrates several domains, in particular natura...
Abstract. Computational storytelling systems have mainly focused on the con-struction and evaluation...
Books are a rich source of both fine-grained information, how a character, an object or a scene look...
Computerized systems capable of generating high-level story descriptions have many potential real-li...
We study a fundamental question for developing storytelling machines: what vocabulary is suited for ...
Automatic understanding of stories is a long-time goal of artificial intelligence and natural langua...
Books are a rich source of both fine-grained information, how a character, an object or a scene look...
ii Intelligent multimedia information retrieval deals with massive unstructured data, especially dig...
Intelligent multimedia information retrieval deals with massive unstructured data, especially digita...
We introduce the MovieQA dataset which aims to evaluate automatic story comprehension from both vide...
Thesis (Ph. D.)--University of Rochester. Department of Computer Science, 2017.Building systems that...
| openaire: EC/H2020/780069/EU//MeMADThis chapter focuses on the recent surge of interest in automat...
We summarize recent developments in our platform for symbolically representing and reasoning over hu...
Our work has focused on support for film or television scriptwriting. Since this involves potentiall...
The primary objective of this thesis is to develop a method that uses machine learning algorithms to...
This paper describes our research-in-progress which integrates several domains, in particular natura...
Abstract. Computational storytelling systems have mainly focused on the con-struction and evaluation...