Browse State-of-the-Art › Unsupervised Video Summarization
Unsupervised Video Summarization
19 papers with code · 2 benchmarks · 3 datasets archive 2025-07-28
Unsupervised video summarization approaches overcome the need for ground-truth data (whose production requires time-demanding and laborious manual annotation procedures), based on learning mechanisms that require only an adequately large collection of original videos for their training. Specifically, the training is based on heuristic rules, like the sparsity, the representativeness, and the diversity of the utilized input features/characteristics.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
2 leaderboard tables shown for this task, 2 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| SumMe (10 rows) | TAC-SUM | Cluster-based Video Summarization with Temporal Context Awareness | code | — | Compare |
| TvSum (8 rows) | SegSum | Integrate the temporal scheme for unsupervised video summarization... | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
3 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Most implemented papers archive 2025-07-28
19 shown of 19 papers with code (31 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.
-
29 Dec 2017 6 repositories listed Syntology ran 1 of 1 samples · 0 unverifiedVideo summarization aims to facilitate large-scale video browsing by producing short, concise summaries that are diverse and representative of original videos.
-
10 Oct 2019 3 repositories listedVideo is one of the robust sources of information and the consumption of online and offline videos has reached an unprecedented level in the last few years.
-
26 Feb 2025 1 repository listedIn this work, we present a novel unsupervised scheme named SegSum, designed for video summarization through the creation of video skims.
-
6 Apr 2024 1 repository listedDespite the importance of video summarization, there is a lack of diverse and representative datasets, hindering comprehensive evaluation and benchmarking of algorithms.
-
6 Apr 2024 1 repository listedIn this paper, we present TAC-SUM, a novel and efficient training-free approach for video summarization that addresses the limitations of existing cluster-based models by incorporating temporal context.
-
7 Nov 2023 1 repository listedThis paper introduces a new, unsupervised method for automatic video summarization using ideas from generative adversarial networks but eliminating the discriminator, having a simple loss function, and separating…
-
11 Sep 2023 1 repository listedWe show that the reconstruction loss of the model for a video with masked frames correlates with the representativeness of the remaining frames in the video.
-
11 Sep 2023 1 repository listedWe show that the reconstruction loss of the model for a video with masked frames correlates with the representativeness of the remaining frames in the video.
-
18 Nov 2022 1 repository listedVideo summarization aims to select the most informative subset of frames in a video to facilitate efficient video browsing.
-
29 Jun 2022 1 repository listedInstead of simply modeling the frames' dependencies based on global attention, our method integrates a concentrated attention mechanism that is able to focus on non-overlapping blocks in the main diagonal of the…
-
6 Sep 2021 1 repository listedThis type of methods includes a summarizer and a discriminator.
-
9 Jun 2021 1 repository listedWith the exponential growth of video data, video summarization techniques are urgently needed for reducing people’s efforts in the videos' content exploration by generating succinct but informative summaries from…
-
26 May 2021 1 repository listedOur evaluation shows that we obtain state-of-the-art results on both datasets, while also highlighting the shortcomings of previous work with regard to the evaluation methodology.
-
16 Nov 2020 1 repository listedThis paper presents a new method for unsupervised video summarization.
-
24 Dec 2019 1 repository listedExperimental evaluation on two datasets (SumMe and TVSum) documents the contribution of the attention auto-encoder to faster and more stable training of the model, resulting in a significant performance improvement with…
-
8 Dec 2019 1 repository listedWe consider shot-based video summarization where the summary consists of a subset of the video shots which can be of various lengths.
-
21 Oct 2019 1 repository listedIn this paper we present our work on improving the efficiency of adversarial training for unsupervised video summarization.
-
24 Nov 2018 1 repository listedThe proposed variance loss allows a network to predict output scores for each frame with high discrepancy which enables effective feature learning and significantly improves model performance.
-
1 Jul 2017 1 repository listedThe summarizer is the autoencoder long short-term memory network (LSTM) aimed at, first, selecting video frames, and then decoding the obtained summarization for reconstructing the input video.
Syntology lines on 1 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.
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