Search Results for author:
Found 3 papers, 1 papers with code
Can I Trust Your Answer? Visually Grounded Video Question Answering
We study visually grounded VideoQA in response to the emerging trends of utilizing pretraining techniques for video-language understanding.
RDU: A Region-based Approach to Form-style Document Understanding
Key Information Extraction (KIE) is aimed at extracting structured information (e. g. key-value pairs) from form-style documents (e. g. invoices), which makes an important step towards intelligent document understanding.
Revisit Automatic Error Detection for Wrong and Missing Translation -- A Supervised Approach
While achieving great fluency, current machine translation (MT) techniques are bottle-necked by adequacy issues.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
