Research map / 3D vision / 3D generation
Scene-Centric Joint Parsing of Cross-View Videos
Hang Qi, Yuanlu Xu, Tao Yuan, Tianfu Wu, Song-Chun Zhu
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 |
|---|---|---|---|
| Jointly parse cross-view proposals into scene-centric predictions | View-centric action proposals · CAMPUS | Overall action accuracy: 0.82 -> 0.90 | Improved |
| Jointly parse cross-view proposals into scene-centric predictions | View-centric action proposals · TUM Kitchen | Overall action accuracy: 0.59 -> 0.70 | Improved |
| Jointly parse cross-view proposals into scene-centric predictions | View-centric attribute proposals · CAMPUS | mAP: 0.59 -> 0.63 | Improved |
| Jointly parse cross-view proposals into scene-centric predictions | View-centric attribute proposals · TUM Kitchen | mAP: 0.76 -> 0.84 | Improved |
| Use joint parsing rather than Xu et al. | Multi-object detection · CAMPUS-S1 | DA (%): 49.30 -> 56.00 | Improved |
| Use joint parsing rather than Xu et al. | Multi-object detection · CAMPUS-S2 | DA (%): 27.81 -> 28.24 | Improved |
| Use joint parsing rather than Xu et al. | Multi-object detection · CAMPUS-S3 | DA (%): 49.71 -> 50.60 | Improved |
| Use joint parsing rather than Xu et al. | Multi-object detection · CAMPUS-S4 | DA (%): 24.46 -> 24.81 | Improved |
| Use joint parsing rather than Xu et al. | Multi-object detection · TUM Kitchen | DA (%): 86.53 -> 89.13 | Improved |
| Use joint parsing to aggregate observations across cameras | Multi-object tracking · CAMPUS-S1 | TA (%): 56.15 -> 55.95 | No clear effect |
| Use joint parsing to aggregate observations across cameras | Multi-object tracking · CAMPUS-S2 | TA (%): 28.74 -> 27.91 | Hurt |
| Use joint parsing to aggregate observations across cameras | Multi-object tracking · CAMPUS-S3 | TA (%): 49.68 -> 50.55 | Improved |
Closest papers by meaning
- Temporal Pixel-Level Semantic Understanding Through the VSPW Dataset (TPAMI 2023 · similarity 0.87)
- Unsupervised Vision-Language Parsing: Seamlessly Bridging Visual Scene Graphs With Language Structures via Dependency Relationships (CVPR 2022 · similarity 0.86)
- Graphical Contrastive Losses for Scene Graph Parsing (CVPR 2019 · similarity 0.86)
- Universal Scene Graph Generation (CVPR 2025 · similarity 0.86)
- EAGLE: Efficient Adaptive Geometry-based Learning in Cross-view Understanding (NeurIPS 2024 · similarity 0.85)
- SCENIR: Visual Semantic Clarity through Unsupervised Scene Graph Retrieval (ICML 2025 · 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.
