Relating Things and Stuff via ObjectProperty Interactions

23 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Panoptic Segmentation (2018, methodology): “[50, 41, 42, 40]).”
Higher Order Conditional Random Fields in Deep Neural Networks (2015, methodology): “Object detectors have also been used by [46,51], who also modelled variables that describe the degree to which an object hypothesis is accepted.”
Learning to Fuse Things and Stuff (2018, methodology): “[34] use a CRF over image segments to model geometric and semantic relations.”
Bottom-up Instance Segmentation using Deep Higher-Order CRFs (2016, methodology): “ls [18], using higher order potentials encouraging consistency over cliques larger than two pixels [17,35], modelling the co-occurrence of labels [20,35] and utilising the results of object detectors [21,33,36]. Using CNNs for semantic segmentation can greatly improve the unary, per-pixel prediction”
DeeperLab: Single-Shot Image Parser (2019, background): “Since then, there have been several works aiming to jointly perform detection and segmentation for whole scene understanding with AND-OR graphs [9, 10], Exemplars [11, 12, 13], or Conditional Random Fields [14, 15, 16, 17, 18, 19].”
Higher Order Potentials in End-to-End Trainable Conditional Random Fields (2015, methodology): “Object detectors have also been employed by [44] and [40], who also modelled variables which describe the degree to which an object hypothesis is accepted or not.”