Research map / Video / Video segmentation and tracking
HSA-RNN: Hierarchical Structure-Adaptive RNN for 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 a sliding bidirectional LSTM rather than a sliding single LSTM for boundary detection (ablation) | HSA-RNN · SumMe, CoSum, and VTW shot boundary detection | F-measure: 0.841 -> 0.864; 0.732 -> 0.774; 0.872 -> 0.891 | Helped |
| Use a sliding bidirectional LSTM rather than a sliding single LSTM with deep features (ablation) | HSA-RNN · SumMe, CoSum, and VTW shot boundary detection | F-measure: 0.845 -> 0.887; 0.750 -> 0.792; 0.875 -> 0.902 | Helped |
| Use HSA-RNN rather than the strongest listed baseline | Video summarization · SumMe, TVsum, CoSum, and VTW | F-measure: SumMe: 0.429 -> 0.441; TVsum: 0.596 -> 0.598; CoSum: 0.663 -> 0.692; VTW: 0.465 -> 0.491 | Helped |
| Use deep rather than shallow visual features | HSA-RNN · SumMe, TVsum, and CoSum summarization | F-measure: SumMe: 0.425 -> 0.441; TVsum: 0.584 -> 0.598; CoSum: 0.682 -> 0.692 | Helped |
| Increase the sliding bidirectional LSTM length beyond the stable range (ablation) | HSA-RNN shot boundary detection · SumMe, CoSum, and VTW | F-measure | Hurt |
Closest papers by meaning
- Query-Focused Video Summarization: Dataset, Evaluation, and a Memory Network Based Approach (CVPR 2017 · similarity 0.88)
- Video Summarization Using Denoising Diffusion Probabilistic Model (AAAI 2025 · similarity 0.85)
- Scaling Up Video Summarization Pretraining with Large Language Models (CVPR 2024 · similarity 0.85)
- Video Summarization with Large Language Models (CVPR 2025 · similarity 0.85)
- CSTA: CNN-based Spatiotemporal Attention for Video Summarization (CVPR 2024 · similarity 0.83)
- MMSum: A Dataset for Multimodal Summarization and Thumbnail Generation of Videos (CVPR 2024 · similarity 0.83)
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.