Unsupervised Deep Non-rigid Alignment by Low-Rank Loss and Multi-input Attention.
Takanori AsanomiKazuya NishimuraHeon SongJunya HayashidaHiroyuki SekiguchiTakayuki YagiImari SatoRyoma BisePublished in: MICCAI (6) (2022)
Keyphrases
- low rank
- semi supervised
- non rigid structure from motion
- missing data
- singular value decomposition
- linear combination
- matrix factorization
- convex optimization
- low rank matrix
- matrix completion
- rank minimization
- matrix decomposition
- kernel matrix
- high order
- unsupervised learning
- high dimensional data
- trace norm
- low rank matrices
- machine learning
- singular values
- input data
- data matrix
- minimization problems
- robust principal component analysis
- small number
- motion estimation
- pairwise
- supervised learning
- least squares
- active learning
- computer vision
- data sets