Research map / Video / Video segmentation and tracking
Cycle-SUM: Cycle-Consistent Adversarial LSTM Networks for Unsupervised Video Summarization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use Cycle-SUM instead of SUM-GAN | unsupervised video summarization · SumMe | F-score: 39.1 -> 41.9 | Helped |
| use Cycle-SUM instead of SUM-GAN | unsupervised video summarization · TVSum | F-score: 51.7 -> 57.6 | Helped |
| add forward and backward adversarial losses (ablation) | Cycle-SUM · SumMe | F-score: 34.8 -> 41.9 | Helped |
| add forward and backward adversarial losses (ablation) | Cycle-SUM · TVSum | F-score: 49.5 -> 57.6 | Helped |
| add a backward GAN while retaining the forward GAN (ablation) | Cycle-SUM · SumMe | F-score: 38.2 -> 39.7 | Helped |
| add a backward GAN while retaining the forward GAN (ablation) | Cycle-SUM · TVSum | F-score: 51.4 -> 53.6 | Helped |
| add forward and backward cycle-consistent losses (ablation) | Cycle-SUM · SumMe | F-score: 39.7 -> 41.9 | Helped |
| add forward and backward cycle-consistent losses (ablation) | Cycle-SUM · TVSum | F-score: 53.6 -> 57.6 | Helped |
| add the backward cycle-consistent loss while keeping the forward cycle loss (ablation) | Cycle-SUM · SumMe | F-score: 40.3 -> 41.9 | Helped |
| add the backward cycle-consistent loss while keeping the forward cycle loss (ablation) | Cycle-SUM · TVSum | F-score: 55.2 -> 57.6 | Helped |
| add the forward cycle-consistent loss while keeping the backward cycle loss (ablation) | Cycle-SUM · SumMe | F-score: 39.9 -> 41.9 | Helped |
| add the forward cycle-consistent loss while keeping the backward cycle loss (ablation) | Cycle-SUM · TVSum | F-score: 55.0 -> 57.6 | Helped |
Closest papers by meaning
- Unsupervised Video Summarization With Adversarial LSTM Networks (CVPR 2017 · similarity 0.94)
- Discriminative Feature Learning for Unsupervised Video Summarization (AAAI 2019 · similarity 0.88)
- Video Summarization Using Denoising Diffusion Probabilistic Model (AAAI 2025 · similarity 0.83)
- V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning (AAAI 2025 · similarity 0.83)
- Video Summarization with Large Language Models (CVPR 2025 · similarity 0.82)
- Scaling Up Video Summarization Pretraining with Large Language Models (CVPR 2024 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.