PWS-DVC: Enhancing Weakly Supervised Dense Video Captioning with Pretraining Approach

In recent times, there has been a notable increase in efforts to simultaneously comprehend vision and language, driven by the availability of video-related datasets and advancements in language models within the domain of natural language processing. Dense video captioning poses a significant challe...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE access 2023-01, Vol.11, p.1-1
Hauptverfasser:	Choi, Wangyu, Chen, Jiasi, Yoon, Jongwon
Format:	Artikel
Sprache:	eng
Schlagworte:	Context modeling Cross-modal video-text comprehension Datasets Dense video captioning Dogs Effectiveness event localization in videos fine-tuning for dense captioning Location awareness Natural language processing natural language processing in videos Pretraining Task analysis Training Transformers Uncertainty Weakly supervised
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!