DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptation.
Zuxuan WuXintong HanYen-Liang LinMustafa Gökhan UzunbasTom GoldsteinSer-Nam LimLarry S. DavisPublished in: CoRR (2018)
Keyphrases
- dual channel
- d scene
- multiple images
- pairwise
- single image
- image alignment
- network structure
- unsupervised learning
- input image
- video sequences
- complex scenes
- scene understanding
- scene analysis
- indoor and outdoor
- real world scenes
- supervised learning
- d objects
- neural network
- image sequences
- network analysis
- three dimensional
- scene images
- manifold alignment
- social networks