Research map / Video / Video segmentation and tracking
Siamese Network with Interactive Transformer for Video Object Segmentation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use SITVOS with its Siamese backbone and interactive transformer | semi-supervised VOS · DAVIS 2017-Val | J&F | Helped |
| Add COCO simulated-video pre-training (ablation) | SITVOS · DAVIS 2016-Val | J&F: +2.0% | Helped |
| Add COCO simulated-video pre-training (ablation) | SITVOS · DAVIS 2017-Val | J&F: +7.2% | Helped |
| Add FIM to the transformer (ablation) | SITVOS · DAVIS 2016-Val | J&F: 89.2 -> 90.5; 1.3% | Helped |
| Add FIM to the transformer (ablation) | SITVOS · DAVIS 2017-Val | J&F: 82.0 -> 83.5; 1.5% | Helped |
| Use first and previous frames rather than first frame only in memory (ablation) | SITVOS · DAVIS 2017-Val | J&F: 70.7 -> 81.8 | Helped |
| Use previous frame only rather than first frame only in memory (ablation) | SITVOS · DAVIS 2016-Val | J&F: 83.8 -> 86.5 | Helped |
| Introduce intermediate frames into memory (ablation) | SITVOS · DAVIS 2017-Val | J&F: 81.8 -> 83.1 | Helped |
| Use a fixed number of sampled memory frames rather than a fixed interval (ablation) | SITVOS · DAVIS 2017-Val | J&F: 83.1 -> 83.5 | Helped |
Closest papers by meaning
- Learning Dynamic Network Using a Reuse Gate Function in Semi-Supervised Video Object Segmentation (CVPR 2021 · similarity 0.90)
- Fast Video Object Segmentation by Reference-Guided Mask Propagation (CVPR 2018 · similarity 0.90)
- Learning Fast and Robust Target Models for Video Object Segmentation (CVPR 2020 · similarity 0.89)
- Fast Online Object Tracking and Segmentation: A Unifying Approach (CVPR 2019 · similarity 0.89)
- Point-VOS: Pointing Up Video Object Segmentation (CVPR 2024 · similarity 0.88)
- LiVOS: Light Video Object Segmentation with Gated Linear Matching (CVPR 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.