SumMe

Introduced by Gygli et al. in Creating Summaries from User Videos

The SumMe dataset is a video summarization dataset consisting of 25 videos, each annotated with at least 15 human summaries (390 in total).

Source: https://gyglim.github.io/me/vsum/index.html

Homepage

Task	Dataset Variant	Best Model
Supervised Video Summarization	SumMe	PGL-SUM
Unsupervised Video Summarization	SumMe	TAC-SUM
Video Summarization	SumMe	PGL-SUM

Paper	Code	Results	Date	Stars

455

Video2GIF

Source: https://gyglim.github.io/me/vsum/index.html.