Learning reliable modal weight with transformer for robust RGBT tracking

Many Siamese-based RGBT trackers have been prevalently designed in recent years for fast-tracking. However, the correlation operation in them is a local linear matching process, which may easily lose semantic information required inevitably by high-precision trackers. In this paper, we propose a str...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Knowledge-based systems 2022-08, Vol.249, p.108945, Article 108945
Hauptverfasser:	Feng, Mingzheng, Su, Jianbo
Format:	Artikel
Sprache:	eng
Schlagworte:	Feature extraction RGBT tracking Robustness Semantic features Semantics Tracking Transformer Transformers
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!