Research map / Video / Video segmentation and tracking
Video Instance Segmentation via Multi-Scale Spatio-Temporal Split Attention Transformer
Omkar Thawakar, Sanath Narayan, Jiale Cao, Hisham Cholakkal, Rao Muhammad Anwer, Muhammad Haris Khan, Salman Khan, Michael Felsberg, 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 MS-STS attention module to the encoder (ablation) | SeqFormer baseline · YouTube-VIS 2019 val (ablation) | AP: 46.4 -> 48.4 | Improved |
| add temporal attention block in the decoder (ablation) | SeqFormer + MS-STS · YouTube-VIS 2019 val (ablation) | AP: 48.4 -> 49.1 | Improved |
| add adversarial fg-bg separability loss (ablation) | SeqFormer + MS-STS + T-Dec · YouTube-VIS 2019 val (ablation) | AP: 49.1 -> 50.1 | Improved |
| add all three contributions to SeqFormer (ablation) | SeqFormer · YouTube-VIS 2019 val | AP: 46.4 -> 50.1 | Improved |
| use MS-STS VIS instead of SeqFormer on fast motion videos | SeqFormer · YouTube-VIS 2021 new videos, fast motion | AP: 48.9 -> 54.2 | Improved |
| use MS-STS VIS instead of SeqFormer on size-change videos | SeqFormer · YouTube-VIS 2021 new videos, size change | AP: 49.5 -> 53.7 | Improved |
| use MS-STS VIS instead of SeqFormer on aspect-ratio change videos | SeqFormer · YouTube-VIS 2021 new videos, aspect-ratio change | AP: 49.2 -> 53.9 | Improved |
| use MS-STS VIS instead of SeqFormer with Swin-L | SeqFormer · YouTube-VIS 2019 val (Swin-L) | AP: 59.3 -> 61.0 | Improved |
| use MS-STS VIS instead of SeqFormer at AP75 | SeqFormer · YouTube-VIS 2019 val (ResNet-50) | AP75: 51.8 -> 56.6 | Improved |
| use MS-STS VIS instead of SeqFormer | SeqFormer · YouTube-VIS 2021 val | AP: 40.5 -> 42.2 | 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 16 of 16 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
- InstanceFormer: An Online Video Instance Segmentation Framework (AAAI 2023 · similarity 0.91)
- End-to-End Video Instance Segmentation With Transformers (CVPR 2021 · similarity 0.91)
- Hybrid Instance-Aware Temporal Fusion for Online Video Instance Segmentation (AAAI 2022 · similarity 0.90)
- Efficient Video Instance Segmentation via Tracklet Query and Proposal (CVPR 2022 · similarity 0.89)
- Video Mask Transfiner for High-Quality Video Instance Segmentation (ECCV 2022 · similarity 0.89)
- Video Instance Segmentation in an Open-World (IJCV 2024 · 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.
