ImagesVideosAudio

SumMe

Introduced in Creating Summaries from User Videos2013

About this Dataset

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

Source: Creating Summaries from User Videos

Dataset Variants

SumMe

Papers1

Creating Summaries from User Videos

This paper proposes a novel approach and a new benchmark for video summarization, which focuses on user videos, which are raw videos containing a set of interesting events, and generates high-quality results, comparable to manual, human-created summaries.

Dataset Loaders

EDIT

🔥

KaiyangZhou/pytorch-vsumm-reinforce

pytorch

🔥

e-apostolidis/CA-SUM

pytorch

Tasks

EDIT

Video Summarization Unsupervised Video Summarization Supervised Video Summarization

Similar Datasets