Research map / Video / Video segmentation and tracking
Synthesizing Dynamic Patterns by Spatial-Temporal Generative ConvNet
Jianwen Xie, Song-Chun Zhu, Ying Nian Wu
Check 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 a spatial-temporal generative ConvNet instead of MRF-ℓ1 for recovery | Video recovery · Salt and pepper masks, Avg. | recovery error: 5.3048 vs 10.1071 | Improved |
| Use a spatial-temporal generative ConvNet instead of MRF-ℓ1 for recovery | Video recovery · Single region masks, Avg. | recovery error: 6.3484 vs 12.2856 | Improved |
| Use a spatial-temporal generative ConvNet instead of MRF-ℓ1 for recovery | Video recovery · 50% missing frames, Avg. | recovery error: 6.7285 vs 15.0085 | Improved |
Closest papers by meaning
- Learning Energy-Based Spatial-Temporal Generative ConvNets for Dynamic Patterns (TPAMI 2019 · similarity 0.97)
- Learning Dynamic Generator Model by Alternating Back-Propagation through Time (AAAI 2019 · similarity 0.91)
- Generating Long Videos of Dynamic Scenes (NeurIPS 2022 · similarity 0.87)
- Generative Image Dynamics (CVPR 2024 · similarity 0.87)
- Generating Videos with Scene Dynamics (NeurIPS 2016 · similarity 0.87)
- GenRec: Unifying Video Generation and Recognition with Diffusion Models (NeurIPS 2024 · similarity 0.85)
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.
