most citedInteractive Reinforcement Learning for Object Grounding via Self-Talking

9 citations · 9 across the 1 of their papers we have counts for

collaborators

1 paper

cs.AI2017★ 9 cited

Interactive Reinforcement Learning for Object Grounding via Self-Talking

Yan Zhu, Shaoting Zhang, Dimitris Metaxas

Humans are able to identify a referred visual object in a complex scene via a few rounds of natural language communications. Success communication requires both parties to engage a…