paper-with-me

Papers

Event and Entity Extraction from Generated Video Captions

2022-11-05 · Johannes Scherer, Ansgar Scherp, Deepayan Bhowmik

Annotation of multimedia data by humans is time-consuming and costly, while reliable automatic generation of semantic metadata is a major challenge. We propose a framework to extract semantic metadata from automatically generated video captions. As metadata, we consider entities, the entities' properties, relations between entities, and the video category. We employ two state-of-the-art dense video captioning models with masked transformer (MT) and parallel decoding (PVDC) to generate captions for videos of the ActivityNet Captions dataset. Our experiments show that it is possible to extract entities, their properties, relations between entities, and the video category from the generated captions. We observe that the quality of the extracted information is mainly influenced by the quality of the event localization in the video as well as the performance of the event caption generation.

📄 PDF Abstract BibTeX arXiv:2211.02982

Code (1)

josch14/semantic-metadata-extraction-from-videos 공식 구현

Tasks

Caption GenerationDense Video CaptioningVideo Captioning

Similar Papers 제목 키워드 기반

Identity-Aware Human-Object Interaction Motion Captioning

2026-08-21 · Yiming Wang, Yonghao Dang, Huilai Li, Jiawei Tu 외 arxiv

Existing human-object interaction (HOI) motion captioning methods typically describe what happens while referring to the subject using generic terms such as "a person" or "someone", without grounding the caption in subje…

Motion Captioning

Optimizing Latency for Online Video CaptioningUsing Audio-Visual Transformers

2021-08-04 · Chiori Hori, Takaaki Hori, Jonathan Le Roux

Video captioning is an essential technology to understand scenes and describe events in natural language. To apply it to real-time monitoring, a system needs not only to describe events accurately but also to produce the…

Video Captioning

Implicit Location-Caption Alignment via Complementary Masking for Weakly-Supervised Dense Video Captioning

2024-12-17 · Shiping Ge, Qiang Chen, Zhiwei Jiang, Yafeng Yin 외

Weakly-Supervised Dense Video Captioning (WSDVC) aims to localize and describe all events of interest in a video without requiring annotations of event boundaries. This setting poses a great challenge in accurately locat…

Dense Video CaptioningDescriptiveVideo CaptioningVideo Description

Video Summarization: Towards Entity-Aware Captions

2023-12-01 · Hammad A. Ayyubi, Tianqi Liu, Arsha Nagrani, Xudong Lin 외

Existing popular video captioning benchmarks and models deal with generic captions devoid of specific person, place or organization named entities. In contrast, news videos present a challenging setting where the caption…

Image CaptioningVideo CaptioningVideo SummarizationWorld Knowledge

TA-Prompting: Enhancing Video Large Language Models for Dense Video Captioning via Temporal Anchors

2026-01-06 · Wei-Yuan Cheng, Kai-Po Chang, Chi-Pin Huang, Fu-En Yang 외 arxiv

Dense video captioning aims to interpret and describe all temporally localized events throughout an input video. Recent state-of-the-art methods leverage large language models (LLMs) to provide detailed moment descriptio…

Dense Video CaptioningMoment Retrieval