Learning Kinematic Structure Correspondences Using Multi-Order Similarities
In this paper, we present a novel framework for finding the kinematic structure correspondences between two articulated objects in videos via hypergraph matching. In contrast to appearance and graph alignment based matching methods, which have been applied among two similar static images, the propos...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 40(2018), 12 vom: 28. Dez., Seite 2920-2934
|
|---|
| 1. Verfasser: |
Chang, Hyung Jin
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Fischer, Tobias,
Petit, Maxime,
Zambelli, Martina,
Demiris, Yiannis |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2018
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article
Research Support, Non-U.S. Gov't |
|---|