An Investigation of Potential Function Designs for Neural CRF.
Zechuan HuYong JiangNguyen BachTao WangZhongqiang HuangFei HuangKewei TuPublished in: CoRR (2020)
Keyphrases
- potential functions
- markov random field
- conditional random fields
- maximum entropy
- pairwise
- random fields
- weighted sums
- network architecture
- superpixels
- iterative conditional
- neural network
- graphical models
- long range
- higher order
- graph cuts
- image segmentation
- information extraction
- crf model
- parameter estimation
- hidden markov models
- energy function