Papers › CSTA: CNN-based Spatiotemporal Attention for Video Summarization

CSTA: CNN-based Spatiotemporal Attention for Video Summarization

20 May 2024CVPR 2024 1arXiv:2405.11905archive 2025-07-28

Jaewon Son, Jaehun Park, Kwangsu Kim

Video summarization aims to generate a concise representation of a video, capturing its essential content and key moments while reducing its overall length. Although several methods employ attention mechanisms to handle long-term dependencies, they often fail to capture the visual significance inherent in frames. To address this limitation, we propose a CNN-based SpatioTemporal Attention (CSTA) method that stacks each feature of frames from a single video to form image-like frame representations and applies 2D CNN to these frame features. Our methodology relies on CNN to comprehend the inter and intra-frame relations and to find crucial attributes in videos by exploiting its ability to learn absolute positions within images. In contrast to previous work compromising efficiency by designing additional modules to focus on spatial importance, CSTA requires minimal computational overhead as it uses CNN as a sliding window. Extensive experiments on two benchmark datasets (SumMe and TVSum) demonstrate that our proposed approach achieves state-of-the-art performance with fewer MACs compared to previous methods. Codes are available at https://github.com/thswodnjs3/CSTA.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2405.11905")

Code

Syntology Ran 7 of 8 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 7 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

thswodnjs3/CSTA officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

8 samples harvested; 7 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

7ran
1unverified

Licence: 0 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from thswodnjs3/CSTA. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

BasicBlock thswodnjs3/CSTA/models/ResNet.py official repository ran MIT (permissive) · 296ce13d2909cb38 · report
Bottleneck thswodnjs3/CSTA/models/ResNet.py official repository ran MIT (permissive) · 2b5c8002b738f378 · report
ConditionalPositionalEncoding thswodnjs3/CSTA/models/ResNet.py official repository ran MIT (permissive) · abd4c1235b0f54ba · report
FixedPositionalEncoding thswodnjs3/CSTA/models/ResNet.py official repository ran MIT (permissive) · 21b3939f0ce86110 · report
LearnablePositionalEncoding thswodnjs3/CSTA/models/ResNet.py official repository ran MIT (permissive) · dcdf2add2e19b043 · report
RelativePositionalEncoding thswodnjs3/CSTA/models/ResNet.py official repository ran MIT (permissive) · cd1a86bd4a6df8fb · report
ResNet_Att thswodnjs3/CSTA/models/ResNet.py official repository ran MIT (permissive) · 3649f620d04fd589 · report
CSTA_ResNet thswodnjs3/CSTA/models/ResNet.py official repository unverified MIT (permissive) · cb8636daf2db9a73 · report

Tasks

Supervised Video SummarizationVideo Summarization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Supervised Video Summarization SumMe CSTA Kendall's Tau 0.246 #21 of 21 Archive leaderboard report
Supervised Video Summarization SumMe CSTA Spearman's Rho 0.274 #21 of 21 Archive leaderboard report
Supervised Video Summarization TvSum CSTA Kendall's Tau 0.194 #21 of 21 Archive leaderboard report
Supervised Video Summarization TvSum CSTA Spearman's Rho 0.255 #21 of 21 Archive leaderboard report
Video Summarization SumMe CSTA Kendall's Tau 0.246 #6 of 6 Archive leaderboard report
Video Summarization SumMe CSTA Spearman's Rho 0.274 #6 of 6 Archive leaderboard report
Video Summarization TvSum CSTA Kendall's Tau 0.194 #6 of 6 Archive leaderboard report
Video Summarization TvSum CSTA Spearman's Rho 0.255 #6 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Adaptive Feature PoolingAverage PoolingDense ConnectionsDropoutFocusGoogLeNetLayer NormalizationPositional Encoding GeneratorRoIAlignSelf-Attention GuidanceSoftmax

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