Discriminative tasks, including object categorization and detection, are central components of high-level computer vision. However, sometimes we are interested in a finer-grained characterization of the object's properties, such as its pose or articulation. In this paper we develop a probabilistic method (LOOPS) that can learn a shape and appearance model for a particular object class, and be used to consistently localize constituent elements (landmarks) of the object's outline in test images. This localization effectively projects the test image into an alternative representational space that makes it particularly easy to perform various descriptive tasks. We apply our method to a range of object classes in cluttered images and demonstrate its effectiveness in localizing objects and performing descriptive classification, descriptive ranking, and descriptive clustering.
Bibliographical noteFunding Information:
Acknowledgements This work was supported by the DARPA Transfer Learning program under contract number FA8750-05-2-0249. We would also like to thank Vittorio Ferrari and Pawan Kumar for providing us code and helping us to get their methods working on our data.
- Deformable shape models
- Markov random fields
- Object recognition
- Probabilistic graphical models