Research map / Video / Video segmentation and tracking
Video Summarization Using Fully Convolutional Sequence Networks
Mrigank Rochan, Linwei Ye, Yang Wang
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 |
|---|---|---|---|
| replace bilinear upsampling with learnable deconvolution (ablation) | SUM-DeepLab · TVSum (transfer) | F-score: 57.4 -> 58.8 | Improved |
| replace bilinear upsampling with learnable deconvolution (ablation) | SUM-DeepLab · SumMe (transfer) | F-score: 45.0 -> 45.1 | Improved |
| augment training data with other datasets | SUM-FCN · SumMe | F-score: 47.5 -> 51.1 | Improved |
| augment training data with other datasets | SUM-FCN · TVSum | F-score: 56.8 -> 59.2 | Improved |
| sample videos to T=640 frames instead of 320 (ablation) | SUM-FCN · SumMe (transfer) | F-score: 44.1 -> 45.6 | No clear effect |
| sample videos to T=640 frames instead of 320 (ablation) | SUM-FCN · TVSum (transfer) | F-score: 58.2 -> 57.4 | No clear effect |
| sample videos to T=640 frames instead of 320 (ablation) | SUM-DeepLab · SumMe (transfer) | F-score: 45.0 -> 44.5 | No clear effect |
| process variable-length videos without sampling (ablation) | SUM-FCN · SumMe (transfer) | F-score: 44.1 -> 46.0 | Improved |
| process variable-length videos without sampling (ablation) | SUM-FCN · TVSum (transfer) | F-score: 58.2 -> 56.7 | No clear effect |
| use SUM-DeepLab instead of SUM-FCN | SUM-FCN · SumMe (standard supervised) | F-score: 47.5 -> 48.8 | Improved |
| use SUM-DeepLab instead of SUM-FCN | SUM-FCN · TVSum (transfer) | F-score: 58.2 -> 57.4 | Hurt |
| use fully convolutional sequence network instead of LSTM-based dppLSTM | dppLSTM · SumMe (standard supervised) | F-score: 38.6 -> 47.5 | Improved |
Closest papers by meaning
- Query-Focused Video Summarization: Dataset, Evaluation, and a Memory Network Based Approach (CVPR 2017 · similarity 0.91)
- Video Summarization via Semantic Attended Networks (AAAI 2018 · similarity 0.90)
- SumGraph: Video Summarization via Recursive Graph Modeling (ECCV 2020 · similarity 0.90)
- Convolutional Hierarchical Attention Network for Query-Focused Video Summarization (AAAI 2020 · 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 0.87)
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.
