Artikel ; Online: DAN: Deep-Attention Network for 3D Shape Recognition.
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
2021 Band 30, Seite(n) 4371–4383
Abstract: ... attention network (DAN) for 3D shape representation based on multiview information. More specifically ... aspects: 1) information selection, in which DAN utilizes the self-attention mechanism to update ... in which DAN applies attention mechanism that can save more effective information by considering ...
Abstract | Due to the wide applications in a rapidly increasing number of different fields, 3D shape recognition has become a hot topic in the computer vision field. Many approaches have been proposed in recent years. However, there remain huge challenges in two aspects: exploring the effective representation of 3D shapes and reducing the redundant complexity of 3D shapes. In this paper, we propose a novel deep-attention network (DAN) for 3D shape representation based on multiview information. More specifically, we introduce the attention mechanism to construct a deep multiattention network that has advantages in two aspects: 1) information selection, in which DAN utilizes the self-attention mechanism to update the feature vector of each view, effectively reducing the redundant information, and 2) information fusion, in which DAN applies attention mechanism that can save more effective information by considering the correlations among views. Meanwhile, deep network structure can fully consider the correlations to continuously fuse effective information. To validate the effectiveness of our proposed method, we conduct experiments on the public 3D shape datasets: ModelNet40, ModelNet10, and ShapeNetCore55. Experimental results and comparison with state-of-the-art methods demonstrate the superiority of our proposed method. Code is released on https://github.com/RiDang/DANN. |
---|---|
Sprache | Englisch |
Erscheinungsdatum | 2021-04-21 |
Erscheinungsland | United States |
Dokumenttyp | Journal Article |
ISSN | 1941-0042 |
ISSN (online) | 1941-0042 |
DOI | 10.1109/TIP.2021.3071687 |
Datenquelle | MEDical Literature Analysis and Retrieval System OnLINE |
Zusatzmaterialien
Kategorien
Über subito bestellen
Dieser Service ist kostenpflichtig (siehe Lieferbedingungen von subito). Bestellungen, die einen Artikel nebst Supplementary Material umfassen, werden grundsätzlich wie mehrfache Bestellungen bearbeitet. Gebühren fallen in diesen Fällen für jede einzelne Bestellung an.
Fernleihe an ZB MED
Sie können sich den gewünschten Titel als lokale Nutzerin oder lokaler Nutzer von ZB MED direkt an den Standort Köln schicken lassen.