Dense Video Captioning: A Survey of Techniques, Datasets and Evaluation Protocols
ACM Computing Surveys · 30.06.2025 · 57 (6) · 1-36
DOI: 10.1145/3712059 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 10.02.2025. Verfasst von Iqra Qasim und 2 weiteren Autor:innen. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 156 Literaturangaben.
Abstract (Originalsprache)
Untrimmed videos have interrelated events, dependencies, context, overlapping events, object-object interactions, domain specificity, and other semantics that are worth highlighting while describing a video in natural language. Owing to such a vast diversity, a single sentence can only correctly describe a portion of the video. Dense Video Captioning (DVC) aims to detect and describe different events in a given video. The term DVC originated in the 2017 ActivityNet challenge, after which considerable effort has been made to address the challenge. DVC is divided into three sub-tasks: (1) Video Feature Extraction, (2) Temporal Event Localization, and (3) Dense Caption Generation. In this survey, we discuss all of the studies that claim to perform DVC along with its sub-tasks and summarize their results. We also discuss all of the datasets that have been used for DVC. Last, current challenges in the field are highlighted along with observatory remarks and future trends in the field.
Zitieren
APA
Qasim, I., Horsch, A., & Prasad, D. (2025). Dense Video Captioning: A Survey of Techniques, Datasets and Evaluation Protocols. ACM Computing Surveys, 57(6), 1-36. https://doi.org/10.1145/3712059
Vancouver
Qasim I, Horsch A, Prasad D. Dense Video Captioning: A Survey of Techniques, Datasets and Evaluation Protocols. ACM Computing Surveys. 2025;57(6):1-36. doi:10.1145/3712059
BibTeX
@article{Qasim2025,
author = {Qasim, Iqra and Horsch, Alexander and Prasad, Dilip},
title = {Dense Video Captioning: A Survey of Techniques, Datasets and Evaluation Protocols},
journal = {ACM Computing Surveys},
year = {2025},
volume = {57},
number = {6},
pages = {1--36},
doi = {10.1145/3712059}
}
EUVIMED