Research map / Video / Video segmentation and tracking
Occluded Video Instance Segmentation: A Benchmark
Jiyang Qi, Yan Gao, Yao Guang Hu, Xinggang Wang, Xiaoyu Liu, Xiang Bai, Serge Belongie, Alan Yuille, Philip H. S. Torr, Song Bai
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 temporal feature calibration | MaskTrack R-CNN · OVIS validation | AP: 10.8 -> 15.4 | Improved |
| add temporal feature calibration | SipMask · OVIS validation | AP: 10.2 -> 14.3 | Improved |
| add temporal feature calibration | MaskTrack R-CNN · YouTube-VIS 2019 validation | AP: 30.3 -> 32.1 | Improved |
| add temporal feature calibration | SipMask · YouTube-VIS 2019 validation | AP: 32.5 -> 35.1 | Improved |
| add synthesized image-sequence clips to training (ablation) | MaskTrack R-CNN · OVIS validation | AP: 10.8 -> 12.0 | Improved |
| add synthesized image-sequence clips to training (ablation) | SipMask · OVIS validation | AP: 10.2 -> 11.8 | Improved |
| add synthesized image-sequence clips to training (ablation) | STEm-Seg · OVIS validation | AP: 13.8 -> 15.2 | Improved |
| use adaptive NMS threshold oracle (ablation) | MaskTrack R-CNN · OVIS validation | AP: 10.8 -> 11.2 | Mixed |
| add temporal feature calibration vs LSS + DCN (ablation) | MaskTrack R-CNN · OVIS | classification error rate (all): 34.5 -> 30.2 | Improved |
| evaluate on OVIS instead of YouTube-VIS | MaskTrack R-CNN · image oracle AP | AP: 78.7 -> 58.4 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- STEm-Seg — STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videos (ECCV 2020) · better on 2 of 2 shared results
- FEELVOS — FEELVOS: Fast End-To-End Embedding Learning for Video Object Segmentation (CVPR 2019) · 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
- Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge (NeurIPS 2021 · similarity 0.96)
- Robust Instance Segmentation Through Reasoning About Multi-Object Occlusion (CVPR 2021 · similarity 0.90)
- Occlusion-Aware Instance Segmentation Via BiLayer Network Architectures (TPAMI 2023 · similarity 0.90)
- Deep Occlusion-Aware Instance Segmentation With Overlapping BiLayers (CVPR 2021 · similarity 0.89)
- LVIS: A Dataset for Large Vocabulary Instance Segmentation (CVPR 2019 · similarity 0.88)
- OpenVIS: Open-vocabulary Video Instance Segmentation (AAAI 2025 · similarity 0.87)
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.
