Goto

Collaborating Authors

 Country





LearningAboutObjects byLearningtoInteractwithThem-SupplementaryMaterial-1 Modeldetails

Neural Information Processing Systems

There is a force magnituder (r = 0,1,2) associated to each successful interaction (namely the magnitude predicted at the time of interaction), and feedback reflecting whether this force was: 1. just right, 2. too small, or 3. too large.


LearningAboutObjects byLearningtoInteractwithThem

Neural Information Processing Systems

Much of the remarkable progress in computer vision has been focused around fully supervised learning mechanisms relying on highly curated datasets for a variety of tasks. In contrast, humans often learn about their world with little to no external supervision.




Supplementary: AligningSilhouetteTopologyfor Self-Adaptive3DHumanPoseRecovery

Neural Information Processing Systems

It decodes a plausible pose when sampled inU[ 1,1]32 (green region) while sampling outside this bound may lead to implausible poses(redregion). Here, the Eq. 2 denotes generative adversarial loss on decoderΨ and the Eq. 3 specifies the loss ontheposediscriminatorDisc. Yellow ellipses highlight the region of articulation errors. We obtain pre-adaptation results of the source trained networks via direct inference on the shifted target (column 2 and 4 in panel A and B of Fig 3). We show these in order to qualitatively compare the improvement.