Using multiple segmentations to discover objects and their extent in image collections
Given a large dataset of images, we seek to automatically determine the visually similar object and scene classes together with their image segmentation. To achieve this we combine two ideas: (i) that a set of segmented objects can be partitioned into visual object classes using topic discovery mode...
Main Authors: | Russell, BC, Efros, AA, Sivic, J, Freeman, WT, Zisserman, A |
---|---|
Format: | Conference item |
Language: | English |
Published: |
IEEE
2006
|
Similar Items
-
Discovering objects and their location in images
by: Sivic, J, et al.
Published: (2005) -
Unsupervised discovery of visual object class hierarchies
by: Sivic, J, et al.
Published: (2008) -
Discovering thematic objects in image collections and videos
by: Katsaggelos, Aggelos K., et al.
Published: (2013) -
Object mining using a matching graph on very large image collections
by: Philbin, J, et al.
Published: (2009) -
Deep learning for object detection and image segmentation
by: Tan, Yan Hwa
Published: (2020)