Evaluation of manually created ground truth for multi-view people localization.
Ákos KissTamás SzirányiPublished in: VIGTA@ICVS (2013)
Keyphrases
- multi view
- ground truth
- manually created
- single view
- multiple views
- depth map
- automatically generated
- three dimensional
- d objects
- multi view reconstruction
- automatically extracted
- multi view clustering
- semi supervised
- multiple viewpoints
- domain specific
- multi view images
- multi view face detection
- multi view learning
- depth information
- visual hull
- pairwise
- object recognition
- high quality