Visual Dialog requires an AI agent to hold a meaningful dialogue with humans in natural, conversational language about visual content. Specifically, given an image, a dialogue history, and a follow-up question about the image, the task is to answer the question.
Dataset stats:
120k images from COCO
1 dialog / image
10 rounds of question-answers /dialogue
Total 1.2M dialogue question-answers
http://demo.visualdialog.org Abhishek Das, Satwik Kottur, Deshraj Yadav, Prithvijit Chattopadhyay, Viraj Prabhu, Arjun Chandrasekaran, Nirbhay Modhe, Khushi Gupta, Avi Singh, José M. F. Moura, Stefan Lee, Devi Parikh, Dhruv Batra
