KaiyangZhou/pytorch-vsumm-reinforce
Unsupervised video summarization with deep reinforcement learning (AAAI'18)
This tool helps video editors, content creators, or researchers automatically create short, representative summaries from longer videos. You feed it a video or its extracted image features, and it produces a condensed highlight reel, saving you hours of manual editing. The end-user is anyone who needs to quickly create concise video summaries without extensive human oversight.
503 stars. No commits in the last 6 months.
Use this if you have a large collection of videos and need an automated way to generate concise, diverse summaries that capture the most important moments.
Not ideal if you require highly specific, artistic, or context-aware summaries that demand human creative judgment or nuanced scene understanding.
Stars
503
Forks
152
Language
Python
License
MIT
Category
Last pushed
Dec 11, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/KaiyangZhou/pytorch-vsumm-reinforce"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
open-mmlab/mmpretrain
OpenMMLab Pre-training Toolbox and Benchmark
facebookresearch/mmf
A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)
HuaizhengZhang/Awsome-Deep-Learning-for-Video-Analysis
Papers, code and datasets about deep learning and multi-modal learning for video analysis
adambielski/siamese-triplet
Siamese and triplet networks with online pair/triplet mining in PyTorch
kuanghuei/SCAN
PyTorch source code for "Stacked Cross Attention for Image-Text Matching" (ECCV 2018)