How to render the video from the summary frame position?

e-apostolidis / PGL-SUM

A PyTorch Implementation of PGL-SUM from "Combining Global and Local Attention with Positional Encoding for Video Summarization" (IEEE ISM 2021)

Other

86 stars 32 forks source link

How to render the video from the summary frame position? #13

Open running-machin opened 10 months ago

running-machin commented 10 months ago

Hi,

I see in your implementation of modelscope on the website, generates the summary from the video. But the library have issues working. Do u have implementation where you use the frame positions of the video obtained from generate_summaries.py and cut the videos and generate the video summary?