HLTCHKUST/VG-GPLMs

The code repository for EMNLP 2021 paper "Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive Summarization".

31
/ 100
Emerging

This project helps researchers and academics working with large collections of online videos and their transcripts to automatically generate concise summaries. You provide videos and their corresponding text transcripts, and it produces a brief, coherent summary that captures the essential information from both modalities. This tool is ideal for anyone analyzing or abstracting insights from multimodal content, such as media analysts or content researchers.

No commits in the last 6 months.

Use this if you need to quickly create abstractive summaries from videos and their associated transcripts, leveraging the combined power of visual and textual information.

Not ideal if you only have text or video data, or if you need extractive summaries that directly pull sentences from the original transcript rather than generating new ones.

multimodal-content-analysis video-summarization academic-research information-extraction content-briefing
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

57

Forks

9

Language

Python

License

Last pushed

Jan 14, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/HLTCHKUST/VG-GPLMs"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.