Research map / Video / Video segmentation and tracking
Learned Video Compression via Joint Spatial-Temporal Correlation Exploration
Haojie Liu, Han Shen, Lichao Huang, Ming Lu, Tong Chen, Zhan Ma
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 the proposed video compression method instead of DVC | Video compression · HEVC test sequences (Average) | BD-Rate vs H.264/AVC: -29.73% -> -50.36% | Improved |
| Use the proposed video compression method instead of H.265/HEVC | Video compression · UVG dataset | BD-Rate vs H.264/AVC: -37.25% -> -51.67% | Improved |
| Remove ConvLSTM temporal priors from flow context modeling (ablation) | Proposed video compression framework · Video compression test sequences | quality: 2% to 10% | Hurt |
| Add ConvLSTM temporal priors to flow context modeling (ablation) | Proposed video compression framework · Video compression test sequences | quality: 2% to 10% | Improved |
| Remove non-local attention modules from intra and residual coding (ablation) | Proposed video compression framework · Intra and residual coding | coding efficiency | Hurt |
| Add non-local attention modules to intra and residual coding (ablation) | Proposed video compression framework · Intra and residual coding | coding efficiency | Improved |
Closest papers by meaning
- Learned Video Compression (ICCV 2019 · similarity 0.88)
- HyTIP: Hybrid Temporal Information Propagation for Masked Conditional Residual Video Coding (ICCV 2025 · similarity 0.88)
- Augmented Deep Contexts for Spatially Embedded Video Coding (CVPR 2025 · similarity 0.87)
- ECVC: Exploiting Non-Local Correlations in Multiple Frames for Contextual Video Compression (CVPR 2025 · similarity 0.86)
- Neural Video Compression with Context Modulation (CVPR 2025 · similarity 0.86)
- FLAVC: Learned Video Compression with Feature Level Attention (CVPR 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.
