Research map / Video / Video segmentation and tracking
Overfitting the Data: Compact Neural Video Delivery via Content-Aware Feature Modulation
Jiaming Liu, Ming Lu, Kaixin Chen, Xiaoqi Li, Shizun Wang, Zhaoqing Wang, Enhua Wu, Yurong Chen, Chuang Zhang, Ming Wu
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 content-aware (overfitted) training instead of external learning | EDSR · Vid4 average | PSNR: 25.76 -> 28.32 | Improved |
| add CaFM with joint training, replacing separate per-chunk models | EDSR-M · VSD4K game-45s x4 | PSNR: 34.32 -> 34.61 | Improved |
| add CaFM with joint training, replacing separate per-chunk models | EDSR-M · VSD4K inter-45s x4 | PSNR: 32.67 -> 32.35 | Hurt |
| add CaFM with joint training, replacing separate per-chunk models | EDSR-M · Vimeo-90K video 72549854 x3 | PSNR: 35.47 -> 35.40 | Hurt |
| add joint training instead of finetuning only CaFM on frozen M0 (ablation) | EDSR-M CaFM · VSD4K game-15s x4 | PSNR: 33.49 -> 34.47 | Improved |
| use larger depthwise kernel in CaFM (1x1 to 7x7) (ablation) | EDSR-M CaFM · VSD4K game-15s x4 | PSNR: 34.47 -> 34.54 | No clear effect |
| use 7x7 CaFM kernel instead of 1x1 (ablation) | EDSR-M CaFM · EDSR parameter overhead | parameter percentage: 0.60% -> 7.40% | Hurt |
| apply CaFM joint training to VDSR backbone | VDSR · VSD4K game-45s x4 | PSNR: 31.28 -> 33.16 | Improved |
| compare CaFM with H.265 at same storage | EDSR-M CaFM · VSD4K game-45s x2 | PSNR: 39.77 -> 43.32 | Improved |
| compare CaFM with H.265 at same storage | EDSR-M CaFM · VSD4K game-45s x4 | PSNR: 36.42 -> 34.61 | Hurt |
| use larger content-aware model (EDSR-L vs EDSR-M) (ablation) | content-aware EDSR · Vid4 average | PSNR: 28.32 -> 29.88 | Improved |
Closest papers by meaning
- Neural Video Compression with Feature Modulation (CVPR 2024 · similarity 0.85)
- DeNC: Unleash Neural Codecs in Video Streaming with Diffusion Enhancement (AAAI 2025 · similarity 0.84)
- Fast and Memory-Efficient Video Diffusion Using Streamlined Inference (NeurIPS 2024 · similarity 0.84)
- Combining Frame and GOP Embeddings for Neural Video Representation (CVPR 2024 · similarity 0.84)
- VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation (NeurIPS 2024 · similarity 0.84)
- Offline and Online Optical Flow Enhancement for Deep Video Compression (AAAI 2024 · similarity 0.83)
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.
