Research map / Video / Video segmentation and tracking
LVOS: A Benchmark for Large-Scale Long-Term Video Object Segmentation
Lingyi Hong, Zhongying Liu, Wenchao Chen, Chenzhi Tan, Yuang Feng, Xinyu Zhou, Pinxue Guo, Jinglun Li, Zhaoyu Chen, Shuyong Gao, Wei Zhang, Wenqiang Zhang
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 LVOS training videos to training data | DeAOT-B · LVOS val semi-supervised | J&F: 63.3 -> 67.3 | Improved |
| add LVOS training videos to training data | DeAOT-L · LVOS val semi-supervised | J&F: 63.9 -> 67.1 | Improved |
| add LVOS training videos to training data | XMem · LVOS val semi-supervised | J&F: 64.5 -> 67.4 | Improved |
| add LVOS training videos to training data | AFB-URR · LVOS val semi-supervised | J&F: 44.1 -> 49.8 | Improved |
| add LVOS training videos to training data | RDE · LVOS val semi-supervised | J&F: 62.2 -> 65.1 | Improved |
| add LVOS training videos to training data | LWL · LVOS val semi-supervised | J&F: 60.6 -> 61.4 | Improved |
| add LVOS training videos to training data | CFBI · LVOS val semi-supervised | J&F: 55.0 -> 54.6 | No clear effect |
| add LVOS training videos to training data | LWL · LVOS test semi-supervised | J&F: 60.9 -> 59.8 | Hurt |
| add LVOS training videos to training data | SimulFlow · LVOS val unsupervised single | J&F: 42.7 -> 42.2 | No clear effect |
| add LVOS training videos to training data | TMO · LVOS test unsupervised single | J&F: 45.9 -> 52.8 | Improved |
| restrict object location with oracle box (ablation) | DeAOT-L · LVOS val oracle (semi-supervised) | J&F: 67.1 -> 78.4 | Improved |
| restrict object location with oracle box (ablation) | XMem · LVOS val oracle (semi-supervised) | J&F: 73.3 -> 68.5 | Hurt |
Closest papers by meaning
- LVOS: A Benchmark for Long-term Video Object Segmentation (ICCV 2023 · similarity 0.98)
- Long-RVOS: A Comprehensive Benchmark for Long-term Referring Video Object Segmentation (CVPR 2026 · similarity 0.91)
- Point-VOS: Pointing Up Video Object Segmentation (CVPR 2024 · similarity 0.91)
- OneVOS: Unifying Video Object Segmentation with All-in-One Transformer Framework (ECCV 2024 · similarity 0.91)
- MOSE: A New Dataset for Video Object Segmentation in Complex Scenes (ICCV 2023 · similarity 0.91)
- M^3-VOS: Multi-Phase, Multi-Transition, and Multi-Scenery Video Object Segmentation (CVPR 2025 · similarity 0.89)
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.
