Research map / Video / Video-language understanding
Video Summarization with Long Short-Term Memory
Ke Zhang, Wei-Lun Chao, Fei Sha, Kristen Grauman
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add DPP on top of vsLSTM (dppLSTM) (ablation) | vsLSTM · SumMe (Augmented) | F-score: 41.6 -> 42.9 | Improved |
| add DPP on top of vsLSTM (dppLSTM) (ablation) | vsLSTM · TVSum (Augmented) | F-score: 57.9 -> 59.6 | Improved |
| add DPP on top of vsLSTM (dppLSTM) (ablation) | vsLSTM · TVSum (Canonical) | F-score: 54.2 -> 54.7 | Improved |
| augment training with other summarization datasets | dppLSTM · TVSum | F-score: 54.7 -> 59.6 | Improved |
| augment training with other summarization datasets | dppLSTM · SumMe | F-score: 38.6 -> 42.9 | Improved |
| use LSTM instead of MLP-Shot with little data (ablation) | vsLSTM · SumMe (Canonical) | F-score: 39.8 -> 37.6 | Hurt |
| use LSTM instead of MLP-Shot with augmented data (ablation) | vsLSTM · SumMe (Augmented) | F-score: 40.7 -> 41.6 | Improved |
| use LSTM instead of MLP-Frame with augmented data (ablation) | vsLSTM · TVSum (Augmented) | F-score: 56.1 -> 57.9 | Improved |
| use deep GoogLeNet features instead of shallow features (ablation) | dppLSTM · SumMe (Transfer) | F-score: 40.7 -> 41.8 | Improved |
| use deep GoogLeNet features instead of shallow features (ablation) | dppLSTM · TVSum (Canonical) | F-score: 54.0 -> 54.7 | Improved |
| train with frame-level importance scores instead of binary labels (ablation) | vsLSTM · SumMe (Canonical) | F-score: 37.2 -> 37.6 | Improved |
| train with frame-level importance scores instead of binary labels (ablation) | vsLSTM · TVSum (Canonical) | F-score: 53.7 -> 54.2 | Improved |
Closest papers by meaning
- Video Summarization by Learning From Unpaired Data (CVPR 2019 · similarity 0.91)
- Summary Transfer: Exemplar-Based Subset Selection for Video Summarization (CVPR 2016 · similarity 0.90)
- Video Summarization with Large Language Models (CVPR 2025 · similarity 0.89)
- Scaling Up Video Summarization Pretraining with Large Language Models (CVPR 2024 · similarity 0.88)
- Video Summarization Using Denoising Diffusion Probabilistic Model (AAAI 2025 · similarity 0.87)
- V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning (AAAI 2025 · similarity 0.87)
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.
