Research map / Video / Video-language understanding
Convolutional Hierarchical Attention Network for Query-Focused Video Summarization
Shuwen Xiao, Zhou Zhao, Zijian Zhang, Xiaohui Yan, Min Yang
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 |
|---|---|---|---|
| Use CHAN rather than TPAN | query-focused video summarization · UTE average | F1: 46.05 -> 46.94 | Improved |
| Use CHAN rather than the strongest baseline | query-focused video summarization · UTE Vid1 | F1: 48.74 -> 49.14 | Improved |
| Use CHAN rather than the strongest baseline | query-focused video summarization · UTE Vid2 | F1: 45.30 -> 46.53 | Improved |
| Use CHAN rather than the strongest baseline | query-focused video summarization · UTE Vid3 | F1: 56.47 -> 58.65 | Improved |
| Use CHAN rather than TPAN | query-focused video summarization · UTE Vid4 | F1: 33.64 -> 33.42 | Hurt |
| Use parallel CHAN inference rather than the cited comparison timing | per-video inference · UTE | Inference time: 1.614s -> 134.4ms | Improved |
| Add local self-attention (ablation) | CHAN · UTE query-focused video summarization | F1: 43.26 -> 46.94 | Improved |
| Add query-aware global attention (ablation) | CHAN · UTE query-focused video summarization | F1: 38.09 -> 46.94 | Improved |
Closest papers by meaning
- Query-Focused Video Summarization: Dataset, Evaluation, and a Memory Network Based Approach (CVPR 2017 · similarity 0.90)
- Video Summarization Using Fully Convolutional Sequence Networks (ECCV 2018 · similarity 0.90)
- Video Summarization via Semantic Attended Networks (AAAI 2018 · similarity 0.88)
- HAS: Highlight-guided Attention Steering for Multimodal LLM Video Summarization (ECCV 2026 · similarity 0.88)
- Video Summarization with Large Language Models (CVPR 2025 · similarity 0.87)
- CSTA: CNN-based Spatiotemporal Attention for Video Summarization (CVPR 2024 · similarity 0.86)
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.
