Research map / Video / Video segmentation and tracking
Spatiotemporal CNN for Video Object Segmentation
Check 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 STCNN instead of the strongest listed baseline, OnAVOS | DAVIS-2016 semi-supervised VOS · DAVIS-2016 validation | J Mean: 0.861 -> 0.838 | Hurt |
| Use STCNN instead of the strongest listed baseline, CRN | DAVIS-2016 semi-supervised VOS · DAVIS-2016 validation | F Mean: 0.857 -> 0.838 | Hurt |
| Use STCNN instead of the strongest listed baseline, SegFlow | DAVIS-2016 semi-supervised VOS · DAVIS-2016 validation | T: 0.182 -> 0.191 | Hurt |
| Use STCNN instead of the top table baseline | DAVIS-2017 VOS · DAVIS-2017 validation | J Mean: 61.6 -> 58.7 | Hurt |
| Use STCNN instead of the top table baseline | DAVIS-2017 VOS · DAVIS-2017 validation | F Mean: 69.1 -> 64.6 | Hurt |
| Use STCNN instead of MRFCNN | Youtube-Objects VOS · Youtube-Objects | mean IoU: 0.784 -> 0.796 | Helped |
| Add the temporal coherence branch (ablation) | STCNN without temporal coherence branch · DAVIS-2016 validation | J Mean: 0.812 -> 0.822 | Helped |
| Add the temporal coherence branch (ablation) | STCNN without temporal coherence branch · DAVIS-2016 validation | F Mean: 0.807 -> 0.820 | Helped |
| Add the temporal coherence branch (ablation) | STCNN without temporal coherence branch · DAVIS-2016 validation | T: 0.231 -> 0.200 | Helped |
| Add the attention module (ablation) | STCNN without attention module · DAVIS-2016 validation | J Mean: 0.822 -> 0.832 | Helped |
| Add the attention module (ablation) | STCNN without attention module · DAVIS-2016 validation | F Mean: 0.820 -> 0.835 | Helped |
| Add Lucid Dream augmentation (ablation) | STCNN without Lucid Dream augmentation · DAVIS-2016 validation | J Mean: 0.832 -> 0.838 | Helped |
Closest papers by meaning
- SSTVOS: Sparse Spatiotemporal Transformers for Video Object Segmentation (CVPR 2021 · similarity 0.90)
- Breaking the "Object" in Video Object Segmentation (CVPR 2023 · similarity 0.89)
- Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentation (CVPR 2021 · similarity 0.88)
- Point-VOS: Pointing Up Video Object Segmentation (CVPR 2024 · similarity 0.88)
- Learning Spatial-Semantic Features for Robust Video Object Segmentation (ICLR 2025 · similarity 0.87)
- Learning Segmentation from Point Trajectories (NeurIPS 2024 · similarity 0.86)
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.