Name
Abstract | ||
|---|---|---|
This work is about scene interpretation in the sense of detecting and localizing instances from multiple object classes. We concentrate on object indexing: generate an over-complete interpretation - a list with extra detections but none missed. Pruning such an index to a final interpretation involves a global, often intensive, contextual analysis. We propose a tree-structured hierarchy as a framework for indexing; each node represents a subset of interpretations. This unifies object representation, scene parsing, and sequential learning (modifying the hierarchy as new samples, poses and classes are encountered). Then, we specialize to learning-designing and refining a binary classifier at each node of the hierarchy dedicated to the corresponding subset of interpretations. The whole procedure is illustrated by experiments in reading license plates. |
Year | DOI | Venue |
|---|---|---|
2004 | 10.1109/ICPR.2004.1334470 | ICPR (3) |
Keywords | DocType | Volume |
scene parsing,corresponding subset,tree structured hierarchy,sequential learning,trees (mathematics),learning (artificial intelligence),final interpretation,license plates,pattern classification,unifies object representation,scene interpretation,hierarchical object indexing,multiple object classes,multiple object class,over-complete interpretation,object detection,tree-structured hierarchy,object indexing,binary classifier,object representation,hierarchical sequential learning,learning artificial intelligence,tree structure,contextual analysis,indexation | Conference | 3 |
ISSN | ISBN | Citations |
1051-4651 | 0-7695-2128-2 | 3 |
PageRank | References | Authors |
0.47 | 5 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Xiaodong Fan | 1 | 125 | 13.05 |
| Donald Geman | 2 | 1868 | 495.62 |