Research map / Video / Video segmentation and tracking
OneVOS: Unifying Video Object Segmentation with All-in-One Transformer Framework
Wanyun Li, Pinxue Guo, Xinyu Zhou, Lingyi Hong, Yangji He, Xiangyu Zheng, 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 All-in-One modeling (joint extraction, matching, memory in one transformer) (ablation) | discrete multi-object baseline with ConvViT · DAVIS 17 val | J&F: 82.8 -> 87.5 | Improved |
| add current-to-reference attention decoupling alone (ablation) | All-in-One transformer · LVOS val | J&F: 64.9 -> 61.0 | Hurt |
| add memory-to-reference decoupling alone (ablation) | All-in-One transformer · LVOS val | J&F: 64.9 -> 62.3 | Hurt |
| add both decouplings (Uni-Hybrid Attention) (ablation) | All-in-One transformer · LVOS val | J&F: 64.9 -> 67.4 | Improved |
| add Dynamic Token Selector with dynamic memory (ablation) | OneVOS · LVOS val | J&F: 67.4 -> 70.1 | Improved |
| add Dynamic Token Selector with dynamic memory (ablation) | OneVOS · DAVIS 17 val | J&F: 88.5 -> 88.8 | Improved |
| force fixed 0.5 selection rate per layer in DTS (ablation) | DTS · LVOS val | J&F: 70.1 -> 60.2 | Hurt |
| guide DTS with pooled current-frame tokens (ablation) | DTS · LVOS val | J&F: 70.1 -> 66.4 | Hurt |
| add mask embedding at all layers instead of first 6 (ablation) | OneVOS · MOSE | J&F: 60.9 -> 62.3 | Improved |
| increase memory capacity Cap from 1 to 4 (ablation) | OneVOS · DAVIS 17 val | J&F: 87.5 -> 88.5 (FPS 16.6 -> 12.3) | Improved |
| retain 1024 instead of 512 top-k memory tokens (ablation) | OneVOS-D · LVOS val | J&F: 70.1 -> 68.7 | Hurt |
| use ConvViT-base instead of plain MAE ViT backbone (ablation) | OneVOS · DAVIS 17 val | J&F: 87.5 -> 88.5 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- XMem — XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model (ECCV 2022) · better on 2 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Make One-Shot Video Object Segmentation Efficient Again (NeurIPS 2020 · similarity 0.92)
- LVOS: A Benchmark for Large-Scale Long-Term Video Object Segmentation (TPAMI 2025 · similarity 0.91)
- LVOS: A Benchmark for Long-term Video Object Segmentation (ICCV 2023 · similarity 0.91)
- One-Shot Video Object Segmentation (CVPR 2017 · similarity 0.90)
- Video Object Segmentation without Temporal Information (TPAMI 2018 · similarity 0.90)
- Scalable Video Object Segmentation with Simplified Framework (ICCV 2023 · 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.
