Research map / Video / Video segmentation and tracking
VSPW: A Large-scale Dataset for Video Scene Parsing in the Wild
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 |
|---|---|---|---|
| add temporal object-context blending with memory | OCRNet-based video scene parsing · VSPW validation | mIoU: 36.68% -> 37.82% | Helped |
| add temporal object-context blending with memory | OCRNet-based video scene parsing · VSPW test | mIoU: 34.02% -> 35.62% | Helped |
| add temporal object-context blending with memory | OCRNet-based video scene parsing · VSPW validation | TC: +7.42% | Helped |
| add temporal object-context blending with memory | OCRNet-based video scene parsing · VSPW validation | mVC8: +3.89% | Helped |
| add temporal object-context blending with memory | OCRNet-based video scene parsing · VSPW test | TC: +4.78% | Helped |
| add temporal object-context blending with memory | OCRNet-based video scene parsing · VSPW test | mVC8: +3.26% | Helped |
| add memory aggregation to TCB st-ocr (ablation) | TCB st-ocr · VSPW validation | mIoU: +0.42% | Helped |
| add memory aggregation to TCB st-ocr (ablation) | TCB st-ocr · VSPW validation | TC: +1.43% | Helped |
| add memory aggregation to TCB st-ocr (ablation) | TCB st-ocr · VSPW validation | mVC8: +0.98% | Helped |
| use support-frame dilation 3, 6, 9 instead of 1, 2, 3 (ablation) | TCB st-ppm · VSPW validation | mIoU: 37.40% -> 37.46% | Helped |
| use support-frame dilation 3, 6, 9 instead of 1, 2, 3 (ablation) | TCB st-ppm · VSPW validation | TC: 74.12% -> 70.30% | Hurt |
| use support-frame dilation 3, 6, 9 instead of 1, 2, 3 (ablation) | TCB st-ppm · VSPW validation | mVC8: 86.31% -> 86.95% | Helped |
Closest papers by meaning
- Dense Video Object Captioning from Disjoint Supervision (ICLR 2025 · similarity 0.86)
- V-CAST: Video Curvature-Aware Spatio-Temporal Pruning for Efficient Video Large Language Models (NeurIPS 2026 · similarity 0.86)
- FastVID: Dynamic Density Pruning for Fast Video Large Language Models (NeurIPS 2025 · similarity 0.86)
- ViCaS: A Dataset for Combining Holistic and Pixel-level Video Understanding using Captions with Grounded Segmentation (CVPR 2025 · similarity 0.86)
- Demystifying CLIP Data (ICLR 2024 · similarity 0.86)
- The Scene Language: Representing Scenes with Programs, Words, and Embeddings (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.