Research map / Video / Video segmentation and tracking
Cut-Based Graph Learning Networks to Discover Compositional Structure of Sequential Video Data
Kyoung-Woon On, Eun-Sol Kim, Yu-Jung Heo, Byoung-Tak 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 |
|---|---|---|---|
| use CB-GLNs with temporally constrained graph-cut and message passing instead of self-attention | video sequence modeling · YouTube-8M validation | GAP: 0.8553 -> 0.8597 | Improved |
| add layer normalization (ablation) | CB-GLNs · YouTube-8M validation | GAP: 0.8486 -> 0.8597 | Improved |
| add residual connection (ablation) | CB-GLNs · YouTube-8M validation | GAP: 0.8447 -> 0.8597 | Improved |
| add residual connection and layer normalization (ablation) | CB-GLNs · YouTube-8M validation | GAP: 0.8370 -> 0.8597 | Improved |
| apply graph-cut before representation learning rather than after it (ablation) | CB-GLNs · YouTube-8M validation | GAP: 0.8576 -> 0.8597 | Improved |
Closest papers by meaning
- Language-Guided Graph Representation Learning for Video Summarization (TPAMI 2025 · similarity 0.89)
- Compositional Video Understanding with Spatiotemporal Structure-based Transformers (CVPR 2024 · similarity 0.87)
- Variational Cross-Graph Reasoning and Adaptive Structured Semantics Learning for Compositional Temporal Grounding (TPAMI 2023 · similarity 0.87)
- Reconstructive Sequence-Graph Network for Video Summarization (TPAMI 2021 · similarity 0.87)
- Language-guided Recursive Spatiotemporal Graph Modeling for Video Summarization (IJCV 2025 · similarity 0.86)
- Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding (NeurIPS 2025 · similarity 0.84)
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.
