Abstract | ||
---|---|---|
Most object classes share a considerable amount of local appearance and often only a small number of features are discriminative. The traditional approach to represent an object is based on a summarization of the local characteristics by counting the number of feature occurrences. In this paper we propose the use of a recently developed technique for summarizations that, rather than looking into the quantity of features, encodes their quality to learn a description of an object. Our approach is based on extracting and aggregating only the essential characteristics of an object class for a task. We show how the proposed method significantly improves on previous work in 3D object categorization. We discuss the benefits of the method in other scenarios such as robot grasping. We provide extensive quantitative and qualitative experiments comparing our approach to the state of the art to justify the described approach. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/IROS.2013.6696670 | 2013 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) |
Keywords | Field | DocType |
feature extraction | Viola–Jones object detection framework,Computer science,Pose,Artificial intelligence,Discriminative model,Computer vision,Object detection,Automatic summarization,Categorization,Pattern recognition,Object model,Feature extraction,Machine learning | Conference |
ISSN | Citations | PageRank |
2153-0858 | 2 | 0.38 |
References | Authors | |
25 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Marianna Madry | 1 | 58 | 3.15 |
Heydar Maboudi Afkham | 2 | 8 | 2.90 |
carl henrik ek | 3 | 327 | 30.76 |
Stefan Carlsson | 4 | 1702 | 122.65 |
Danica Kragic | 5 | 2070 | 142.17 |