Research map / Video / Video-language understanding
Weakly-supervised Video Summarization using Variational Encoder-Decoder and Web Prior
Sijia Cai, Wangmeng Zuo, Larry S. Davis, Lei Zhang
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 30 web videos per topic under weak supervision (ablation) | VESD · CoSum | top-5 mAP: 0.616 -> 0.684 | Improved |
| add 60 web videos per topic under weak supervision (ablation) | VESD · CoSum | top-5 mAP: 0.616 -> 0.701 | Improved |
| add 30 web videos per topic under weak supervision (ablation) | VESD · TVSum | top-5 mAP: 0.352 -> 0.407 | Improved |
| add 60 web videos per topic under weak supervision (ablation) | VESD · TVSum | top-5 mAP: 0.352 -> 0.423 | Improved |
| add 30 web videos per topic under strong supervision (ablation) | VESD · CoSum | top-5 mAP: 0.712 -> 0.755 | Improved |
| increase web videos from 30 to 60 per topic under strong supervision (ablation) | VESD · CoSum | top-5 mAP: 0.755 -> 0.764 | Improved |
| add 30 web videos per topic under strong supervision (ablation) | VESD · TVSum | top-5 mAP: 0.437 -> 0.481 | Improved |
| increase web videos from 30 to 60 per topic under strong supervision (ablation) | VESD · TVSum | top-5 mAP: 0.481 -> 0.498 | Improved |
| add importance-score supervision to topic labels (ablation) | VESD · CoSum | top-5 mAP: 0.616 -> 0.712 | Improved |
| add importance-score supervision to topic labels (ablation) | VESD · TVSum | top-5 mAP: 0.352 -> 0.437 | Improved |
| replace GoogLeNet features with ResNet101 (ablation) | VESD · CoSum | top-5 mAP: 0.755 -> 0.767 | Improved |
| replace GoogLeNet features with C3D (ablation) | VESD · CoSum | top-5 mAP: 0.755 -> 0.765 | Improved |
Closest papers by meaning
- Weakly Supervised Summarization of Web Videos (ICCV 2017 · similarity 0.91)
- Retrospective Encoders for Video Summarization (ECCV 2018 · similarity 0.90)
- V2Xum-LLM: Cross-Modal Video Summarization with Temporal Prompt Instruction Tuning (AAAI 2025 · similarity 0.87)
- Video Summarization with Large Language Models (CVPR 2025 · similarity 0.87)
- Scaling Up Video Summarization Pretraining with Large Language Models (CVPR 2024 · similarity 0.87)
- Video Summarization Using Denoising Diffusion Probabilistic Model (AAAI 2025 · 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.
