no code implementations • 19 Nov 2019 • Daesik Kim, Gyujeong Lee, Jisoo Jeong, Nojun Kwak
In the source domain, we fully train an object detector and the RRPN with full supervision of HOI.
no code implementations • 11 Nov 2018 • John Yang, Gyujeong Lee, Minsung Hyun, Simyung Chang, Nojun Kwak
We tackle the blackbox issue of deep neural networks in the settings of reinforcement learning (RL) where neural agents learn towards maximizing reward gains in an uncontrollable way.