NAMED ENTITY RECOGNITION VISUAL CONTEXT AND CAPTION DATA

NAMED ENTITY RECOGNITION VISUAL CONTEXT AND CAPTION DATA

A caption of a multimodal message (e.g., social media post) can be identified as a named entity using an entity recognition system. The entity recognition system can use a visual attention based mechanism to generate a visual context representation from an image and caption. The system can use the v...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Carvalho, Vitor Rocha de, Neves, Leonardo Ribas Machado das, Lu, Di, Zhang, Ning
Format: Patent
Sprache:eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:A caption of a multimodal message (e.g., social media post) can be identified as a named entity using an entity recognition system. The entity recognition system can use a visual attention based mechanism to generate a visual context representation from an image and caption. The system can use the visual context representation to identify one or more terms of the caption as a named entity.