Papers › Discriminative Feature Learning for Unsupervised Video Summarization

Discriminative Feature Learning for Unsupervised Video Summarization

24 Nov 2018arXiv:1811.09791archive 2025-07-28

Yunjae Jung, Donghyeon Cho, Dahun Kim, Sanghyun Woo, In So Kweon

In this paper, we address the problem of unsupervised video summarization that automatically extracts key-shots from an input video. Specifically, we tackle two critical issues based on our empirical observations: (i) Ineffective feature learning due to flat distributions of output importance scores for each frame, and (ii) training difficulty when dealing with long-length video inputs. To alleviate the first problem, we propose a simple yet effective regularization loss term called variance loss. The 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. For the second problem, we design a novel two-stream network named Chunk and Stride Network (CSNet) that utilizes local (chunk) and global (stride) temporal view on the video features. Our CSNet gives better summarization results for long-length videos compared to the existing methods. In addition, we introduce an attention mechanism to handle the dynamic information in videos. We demonstrate the effectiveness of the proposed methods by conducting extensive ablation studies and show that our final model achieves new state-of-the-art results on two benchmark datasets.

PaperPDFCode

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

Code

wildoctopus/SADNet mentioned 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Supervised Video SummarizationUnsupervised Video SummarizationVideo Summarization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Supervised Video Summarization SumMe CSNet F1-score (Augmented) 48.7 #14 of 21 Archive leaderboard report
Supervised Video Summarization SumMe CSNet F1-score (Canonical) 48.6 #14 of 21 Archive leaderboard report
Supervised Video Summarization TvSum CSNet F1-score (Augmented) 57.1 #19 of 21 Archive leaderboard report
Supervised Video Summarization TvSum CSNet F1-score (Canonical) 58.5 #19 of 21 Archive leaderboard report
Unsupervised Video Summarization SumMe CSNet F1-score 51.3 #4 of 10 Archive leaderboard report
Unsupervised Video Summarization SumMe CSNet Parameters (M) 100.76 #4 of 10 Archive leaderboard report
Unsupervised Video Summarization SumMe CSNet training time (s) 568.6 #4 of 10 Archive leaderboard report
Unsupervised Video Summarization TvSum CSNet F1-score 58.8 #4 of 8 Archive leaderboard report
Unsupervised Video Summarization TvSum CSNet Kendall's Tau 0.025 #4 of 8 Archive leaderboard report
Unsupervised Video Summarization TvSum CSNet Parameters (M) 100.76 #4 of 8 Archive leaderboard report
Unsupervised Video Summarization TvSum CSNet Spearman's Rho 0.034 #4 of 8 Archive leaderboard report
Unsupervised Video Summarization TvSum CSNet training time (s) 1797 #4 of 8 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.

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