Amortized Initialization Versus Langevin Refinement for Motion-Guided Segmentation: A Controlled Study of Conditional Energy-Based Models (EBMs)

This publication has 13 references indexed in Scilit:

• Self-supervised Video Object Segmentation by Motion Grouping
  2021
• RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
  2020
• On the Anatomy of MCMC-Based Maximum Likelihood Learning of Energy-Based Models
  Proceedings of the AAAI Conference on Artificial Intelligence, 2020
• Semantic Segmentation with Boundary Neural Fields
  2016
• A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation
  2016
• Segmentation of Moving Objects by Long Term Video Analysis
  IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
• Video Segmentation by Tracking Many Figure-Ground Segments
  2013
• Training restricted Boltzmann machines using approximations to the likelihood gradient
  2008
• Training Products of Experts by Minimizing Contrastive Divergence
  Neural Computation, 2002
• A Threshold Selection Method from Gray-Level Histograms
  IEEE Transactions on Systems, Man, and Cybernetics, 1979