Open-domain Question Answering (OpenQA) is an important task in Natural Language Processing (NLP), which aims to answer a question in the form of natural language based on large-scale unstructured documents.
Existing work cannot well represent the heterogeneous relations and capture the discontinuous event segments that are common in the event chain.
Automatic facial action unit (AU) recognition has attracted great attention but still remains a challenging task, as subtle changes of local facial muscles are difficult to thoroughly capture.
We introduce the concept of interaction and propose a two-perspective interaction representation, that encapsulates a local and a global interaction representation.
As a result, our approach is robust, stable and is able to efficiently recover high quality of surface details even starting with a coarse MVS.