Interactive Visual Grounding of Referring Expressions for Human-Robot Interaction
Mohit Shridhar, David Hsu · 2018
Interactive visual grounding of referring expressions.(a) Ground self-referential expressions.(b) Ground relational expressions.(c) Ask questions to resolve ambiguity.Red boxes indicate referred objects.Blue dashed boxes indicate candidate objects.See also the accompanying video at http://bit.ly/INGRESSvid.