Research map / Video / Video segmentation and tracking
Budget-Aware Deep Semantic Video Segmentation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 learned LSTM frame selection and CNN interpolation instead of uniform selection and optical-flow propagation | Budget-aware segmentation with SegNet · CamVid, 0.1 · Bmax | Class Avg: 34.1 -> 44.7 | Helped |
| Use learned LSTM frame selection and CNN interpolation instead of uniform selection and optical-flow propagation | Budget-aware segmentation with SegNet · CamVid, 0.25 · Bmax | Class Avg: 52.5 -> 60.7 | Helped |
| Use learned LSTM frame selection and CNN interpolation instead of uniform selection and optical-flow propagation | Budget-aware segmentation with SegNet · CamVid, 0.5 · Bmax | Class Avg: 62.2 -> 62.7 | Helped |
| Use learned LSTM frame selection and CNN interpolation instead of uniform selection and optical-flow propagation | Budget-aware segmentation with BayesianSegNet · CamVid, 0.1 · Bmax | Class Avg: 41.3 -> 51.5 | Helped |
| Use learned LSTM frame selection and CNN interpolation instead of uniform selection and optical-flow propagation | Budget-aware segmentation with BayesianSegNet · CamVid, 0.25 · Bmax | Class Avg: 58.4 -> 72.3 | Helped |
| Use learned LSTM frame selection and CNN interpolation instead of uniform selection and optical-flow propagation | Budget-aware segmentation with BayesianSegNet · CamVid, 0.5 · Bmax | Class Avg: 71.9 -> 72.9 | Helped |
| Use learned LSTM frame selection and CNN interpolation instead of uniform selection and optical-flow propagation | Budget-aware segmentation with SegNet · KITTI, 0.25 · Bmax | Class Avg: 78.2 -> 88.4 | Helped |
| Use learned LSTM frame selection and CNN interpolation instead of uniform selection and optical-flow propagation | Budget-aware segmentation with SegNet · KITTI, 0.5 · Bmax | Class Avg: 91.6 -> 92.7 | Helped |
| Add learned LSTM frame selection rather than uniform frame selection (ablation) | CNN interpolation with SegNet · CamVid, 0.1 · Bmax | Class Avg: 34.4 -> 44.7 | Helped |
| Add learned LSTM frame selection rather than uniform frame selection (ablation) | CNN interpolation with SegNet · CamVid, 0.25 · Bmax | Class Avg: 52.8 -> 60.7 | Helped |
| Add learned LSTM frame selection rather than uniform frame selection (ablation) | CNN interpolation with SegNet · CamVid, 0.5 · Bmax | Class Avg: 61.7 -> 62.7 | Helped |
| Add CNN interpolation rather than optical-flow propagation (ablation) | LSTM frame selection with SegNet · CamVid, 0.1 · Bmax | Class Avg: 39.7 -> 44.7 | Helped |
Closest papers by meaning
- Semantic Video Segmentation by Gated Recurrent Flow Propagation (CVPR 2018 · similarity 0.89)
- Low-Latency Video Semantic Segmentation (CVPR 2018 · similarity 0.88)
- Dynamic Face Video Segmentation via Reinforcement Learning (CVPR 2020 · similarity 0.88)
- VidSeg: Training-free Video Semantic Segmentation based on Diffusion Models (CVPR 2025 · similarity 0.88)
- Exploiting Temporal State Space Sharing for Video Semantic Segmentation (CVPR 2025 · similarity 0.87)
- LiVOS: Light Video Object Segmentation with Gated Linear Matching (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.