Research map / Video / Video segmentation and tracking
Perceptual Video Coding for Machines via Satisfied Machine Ratio Modeling
Qi Zhang, Shanshe Wang, Xinfeng Zhang, Chuanmin Jia, Zhao Wang, Siwei Ma, Wen Gao
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 the SMR-difference auxiliary task (model Q over G) (ablation) | SMR prediction model · COCO-HEVC classification SMR-top1 | BD-rate (%): -29.2 -> -30.4 | Improved |
| add the SMR-difference auxiliary task (ablation) | SMR prediction model · COCO-HEVC classification SMR-top5 | BD-rate (%): -43.4 -> -44.6 | Improved |
| add the SMR-difference auxiliary task (ablation) | SMR prediction model · COCO-HEVC classification SMR-top1 | |dQP|: 1.40 -> 1.22 | Improved |
| add the SMR-difference auxiliary task (ablation) | SMR prediction model · COCO-HEVC detection (T_IOU 0.5, T_S 0.5) | BD-rate (%): -10.3 -> -12.3 | Improved |
| add the SMR-difference auxiliary task on an unseen codec (ablation) | SMR prediction model · COCO-VVC detection (T_IOU 0.5, T_S 0.5) | BD-rate (%): -4.8 -> -4.9 | No clear effect |
| add the SMR-difference auxiliary task on an unseen codec (ablation) | SMR prediction model · COCO-VVC detection (T_IOU 0.6, T_S 0.6) | BD-rate (%): -3.2 -> -0.2 | Hurt |
| use ground-truth SMR to choose QP per image instead of constant QP | HEVC · COCO classification SMR-top1 | BD-rate (%): -39.2 | Improved |
| use ground-truth SMR to choose QP | HEVC · COCO detection | BD-rate (%): -23.8, -23.2, -23.2 for three threshold pairs | Improved |
| use predicted SMR on unseen machines (v2 library) | SMR model G · COCO-HEVC classification SMR-top1 | BD-rate (%): -29.2 -> -30.2 | No clear effect |
| apply SMR models to unseen codec VVC instead of HEVC | SMR model Q · COCO classification SMR-top1 | BD-rate (%): -30.4 -> -21.3 | Hurt |
| use more machines to compute SMR (Nm 10 -> 70) against full v2 library | SMR ground truth · COCO classification (v2 library) | MAE of SMR-top1: 0.051 -> 0.004 | Improved |
| predict SMR-top5 instead of SMR-top1 | SMR model G · COCO-HEVC classification | |dSMR|: 0.0463 -> 0.0217 | Improved |
Closest papers by meaning
- Video Coding for Machines: Compact Visual Representation Compression for Intelligent Collaborative Analytics (TPAMI 2024 · similarity 0.89)
- Rate-Distortion Theory in Coding for Machines and Its Applications (TPAMI 2025 · similarity 0.89)
- Unified Coding for Both Human Perception and Generalized Machine Analytics with CLIP Supervision (AAAI 2025 · similarity 0.86)
- Universal Rate-Distortion-Perception Representations for Lossy Compression (NeurIPS 2021 · similarity 0.85)
- Benchmarking and Enhancing VLM for Compressed Image Understanding (ICML 2026 · similarity 0.84)
- Towards image compression with perfect realism at ultra-low bitrates (ICLR 2024 · 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.
