Research map / Video / Video-language understanding
Reconstructive Sequence-Graph Network for Video Summarization
Bin Zhao, Haopeng Li, Xiaoqiang Lu, Xuelong Li
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 graph-based shot encoder instead of sequence encoder (Enc(S) -> Enc(G)) (ablation) | RSGN without reconstructor · SumMe | F-score: 0.397 -> 0.419 | Improved |
| add graph-based shot encoder instead of sequence encoder (Enc(S) -> Enc(G)) (ablation) | RSGN without reconstructor · TVsum | F-score: 0.556 -> 0.564 | Improved |
| replace second-level sequence encoder with graph encoder (Enc(S,S) -> Enc(S,G)) (ablation) | RSGN without reconstructor · SumMe | F-score: 0.416 -> 0.428 | Improved |
| replace second-level sequence encoder with graph encoder (Enc(S,S) -> Enc(S,G)) (ablation) | RSGN without reconstructor · TVsum | F-score: 0.583 -> 0.587 | Improved |
| use hierarchical encoder instead of plain graph encoder (Enc(G) -> Enc(S,G)) (ablation) | RSGN without reconstructor · SumMe | F-score: 0.419 -> 0.428 | Improved |
| add content reconstructor Rec(C) (ablation) | Enc(S,G) · TVsum | F-score: 0.587 -> 0.597 | Improved |
| add dependency reconstructor Rec(D) (ablation) | Enc(S,G) · TVsum | F-score: 0.587 -> 0.599 | Improved |
| add both reconstructors, full RSGN, over Enc(S,G) without reconstructor (ablation) | Enc(S,G) · SumMe | F-score: 0.428 -> 0.450 | Improved |
| add supervision to RSGN (RSGN_uns -> RSGN) (ablation) | RSGN · SumMe | F-score: 0.423 -> 0.450 | Improved |
| edge weight by dot product vs Gaussian (ablation) | graph encoder · SumMe | F-score: 0.413 -> 0.419 | No clear effect |
| edge weight by dot product vs concatenation (ablation) | graph encoder · TVsum | F-score: 0.566 -> 0.564 | No clear effect |
| add reconstructors to graph-only encoder on VTW (ablation) | RSGN Enc(G) · VTW | F-score: 0.450 -> 0.468 | Improved |
Closest papers by meaning
- SumGraph: Video Summarization via Recursive Graph Modeling (ECCV 2020 · similarity 0.91)
- Language-Guided Graph Representation Learning for Video Summarization (TPAMI 2025 · similarity 0.90)
- Language-guided Recursive Spatiotemporal Graph Modeling for Video Summarization (IJCV 2025 · similarity 0.90)
- Video Summarization Using Fully Convolutional Sequence Networks (ECCV 2018 · similarity 0.89)
- Video Summarization with Long Short-Term Memory (ECCV 2016 · similarity 0.87)
- Fine-Grained Captioning of Long Videos through Scene Graph Consolidation (ICML 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.
