Datasets › SumMe

SumMe

Introduced by Michael Gygli et al. in Creating Summaries from User Videos1 Jan 2014 archive 2025-07-28

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

Benchmarks archive 2025-07-28

All 3 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

Papers archive 2025-07-28

24 shown of 24 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 146. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
Integrate the temporal scheme for unsupervised video summarization via attention mechanism 1 1 26 Feb 2025 not harvested
CSTA: CNN-based Spatiotemporal Attention for Video Summarization 1 2 20 May 2024 ran 7 of 8 samples (1 unverified)
Cluster-based Video Summarization with Temporal Context Awareness 1 1 6 Apr 2024 not harvested
Adopting Self-Supervised Learning into Unsupervised Video Summarization through Restorative Score. 1 1 11 Sep 2023 not harvested
Align and Attend: Multimodal Summarization with Dual Contrastive Losses 2 1 13 Mar 2023 not harvested
Summarizing Videos using Concentrated Attention and Considering the Uniqueness and Diversity of the Video Frames 1 1 29 Jun 2022 not harvested
Relational Reasoning Over Spatial-Temporal Graphs for Video Summarization 0 2 6 Apr 2022 not harvested
Progressive Video Summarization via Multimodal Self-supervised Learning 2 2 7 Jan 2022 not harvested
Joint Video Summarization and Moment Localization by Cross-Task Sample Transfer 0 1 1 Jan 2022 not harvested
Video Joint Modelling Based on Hierarchical Transformer for Co-summarization 2 1 27 Dec 2021 not harvested
Combining Global and Local Attention with Positional Encoding for Video Summarization 1 3 1 Dec 2021 not harvested
Hierarchical Multimodal Transformer to Summarize Videos 0 1 22 Sep 2021 not harvested
CLIP-It! Language-Guided Video Summarization 1 1 1 Jul 2021 not harvested
Supervised Video Summarization via Multiple Feature Sets with Parallel Attention 3 6 23 Apr 2021 not harvested
DSNet: A Flexible Detect-to-Summarize Network for Video Summarization 1 2 1 Dec 2020 not harvested
AC-SUM-GAN: Connecting Actor-Critic and Generative Adversarial Networks for Unsupervised Video Summarization 1 1 16 Nov 2020 not harvested
Query Twice: Dual Mixture Attention Meta Learning for Video Summarization 0 1 19 Aug 2020 not harvested
Unsupervised Video Summarization via Attention-Driven Adversarial Learning 1 1 24 Dec 2019 not harvested
A Stepwise, Label-based Approach for Improving the Adversarial Training in Unsupervised Video Summarization 1 1 21 Oct 2019 not harvested
Cycle-SUM: Cycle-consistent Adversarial LSTM Networks for Unsupervised Video Summarization 0 1 17 Apr 2019 not harvested
Summarizing Videos with Attention 5 1 5 Dec 2018 ran 1 of 15 samples (14 unverified)
Discriminative Feature Learning for Unsupervised Video Summarization 1 2 24 Nov 2018 not harvested
Deep Reinforcement Learning for Unsupervised Video Summarization with Diversity-Representativeness Reward 6 2 29 Dec 2017 ran 1 of 1 samples (0 unverified)
Video Summarization with Attention-Based Encoder-Decoder Networks 0 1 31 Aug 2017 not harvested

Dataset loaders archive 2025-07-28

2 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

Custom (research-only, non-commercial)

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • SumMe

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections