Research map / Video / Video segmentation and tracking
Video Instance Segmentation in an Open-World
Omkar Thawakar, Sanath Narayan, Hisham Cholakkal, Rao Muhammad Anwer, Salman Hameed Khan, Jorma T. Laaksonen, Mubarak Shah, Fahad Shahbaz Khan
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 feature enrichment mechanism (ablation) | baseline OW-VIS · split B Task-1 Known | AP: 31.0 -> 31.5 | Improved |
| add spatio-temporal objectness module on top of feature enrichment (ablation) | baseline OW-VIS · split B Task-1 Known | AP: 31.5 -> 32.2 | Improved |
| add feature enrichment mechanism (ablation) | baseline OW-VIS · split B Task-1 Unknown | AP: 2.7 -> 4.5 | Improved |
| add feature enrichment mechanism (ablation) | baseline OW-VIS · split B Task-1 Unknown | AR-1: 5.1 -> 6.1 | Improved |
| add STO module on top of enrichment (ablation) | baseline OW-VIS · split B Task-1 Unknown | AP: 4.5 -> 6.5 | Improved |
| use ScratchNet shallow features instead of conv2 of pretrained backbone (ablation) | OW-VISFormer · split B Task-1 Known | AP: 31.2 -> 32.2 | Improved |
| use ScratchNet shallow features instead of conv2 of pretrained backbone (ablation) | OW-VISFormer · split B Task-1 Unknown | AP: 3.8 -> 6.5 | Improved |
| add feature enrichment and STO to baseline | OW-VISFormer · OW-VIS split A Task-1 Unknown | AP: 6.7 -> 10.0 | Improved |
| add feature enrichment and STO to baseline | OW-VISFormer · OW-VIS split E Task-1 Unknown | AP: 3.5 -> 5.6 | Improved |
| add feature enrichment and STO to SeqFormer | SeqFormer · YouTube-VIS 2019 val | AP: 45.1 -> 46.7 | Improved |
| add feature enrichment and STO to OW-DETR | OW-DETR · MS COCO OWOD Task-1 | U-Recall: 5.7 -> 8.8 | Improved |
| add feature enrichment and STO to OW-DETR | OW-DETR · MS COCO OWOD Task-4 Both | mAP: 33.1 -> 34.0 | 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.
- SeqFormer — SeqFormer: Sequential Transformer for Video Instance Segmentation (ECCV 2022) · better on 1 of 1 shared result
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
- Towards Open-Vocabulary Video Instance Segmentation (ICCV 2023 · similarity 0.92)
- Exploring Transformers for Open-world Instance Segmentation (ICCV 2023 · similarity 0.91)
- OV-VIS: Open-Vocabulary Video Instance Segmentation (IJCV 2024 · similarity 0.91)
- OW-VISCapTor: Abstractors for Open-World Video Instance Segmentation and Captioning (NeurIPS 2024 · similarity 0.90)
- OpenVIS: Open-vocabulary Video Instance Segmentation (AAAI 2025 · similarity 0.90)
- v-CLR: View-Consistent Learning for Open-World Instance Segmentation (CVPR 2025 · similarity 0.88)
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.
