Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.08335 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913730092072960 |
|---|---|
| author | Jahagirdar, Soumya Shamarao Saha, Jayasree Jawahar, C V |
| author_facet | Jahagirdar, Soumya Shamarao Saha, Jayasree Jawahar, C V |
| contents | Learning multimodal video understanding typically relies on datasets comprising video clips paired with manually annotated captions. However, this becomes even more challenging when dealing with long-form videos, lasting from minutes to hours, in educational and news domains due to the need for more annotators with subject expertise. Hence, there arises a need for automated solutions. Recent advancements in Large Language Models (LLMs) promise to capture concise and informative content that allows the comprehension of entire videos by leveraging Automatic Speech Recognition (ASR) and Optical Character Recognition (OCR) technologies. ASR provides textual content from audio, while OCR extracts textual content from specific frames. This paper introduces a dataset comprising long-form lectures and news videos. We present baseline approaches to understand their limitations on this dataset and advocate for exploring prompt engineering techniques to comprehend long-form multimodal video datasets comprehensively. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_08335 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Prompt2LVideos: Exploring Prompts for Understanding Long-Form Multimodal Videos Jahagirdar, Soumya Shamarao Saha, Jayasree Jawahar, C V Computer Vision and Pattern Recognition Learning multimodal video understanding typically relies on datasets comprising video clips paired with manually annotated captions. However, this becomes even more challenging when dealing with long-form videos, lasting from minutes to hours, in educational and news domains due to the need for more annotators with subject expertise. Hence, there arises a need for automated solutions. Recent advancements in Large Language Models (LLMs) promise to capture concise and informative content that allows the comprehension of entire videos by leveraging Automatic Speech Recognition (ASR) and Optical Character Recognition (OCR) technologies. ASR provides textual content from audio, while OCR extracts textual content from specific frames. This paper introduces a dataset comprising long-form lectures and news videos. We present baseline approaches to understand their limitations on this dataset and advocate for exploring prompt engineering techniques to comprehend long-form multimodal video datasets comprehensively. |
| title | Prompt2LVideos: Exploring Prompts for Understanding Long-Form Multimodal Videos |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.08335 |