Research map / Video / Video segmentation and tracking
Unsupervised Video Object Segmentation using Motion Saliency-Guided Spatio-Temporal Propagation
Yuan-Ting Hu, Jia-Bin Huang, Alexander G. Schwing
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 focused diffusion (FDiff) round (ablation) | graph diffusion with all connections · DAVIS | IoU (%): 74.34 -> 77.56 | Improved |
| add long range connections to the neighborhood graph (ablation) | saliency only · DAVIS | IoU (%): 57.52 -> 72.38 | Improved |
| add inter-frame flow connections (ablation) | saliency only · DAVIS | IoU (%): 57.52 -> 62.75 | Improved |
| add intra-frame edge connections (ablation) | saliency only · DAVIS | IoU (%): 57.52 -> 62.13 | Improved |
| add long range connections to inter+intra-frame connections (ablation) | inter+intra connections · DAVIS | IoU (%): 65.01 -> 74.34 | Improved |
| add intra-frame connections to inter-frame + long range (ablation) | inter + long range · DAVIS | IoU (%): 72.70 -> 74.34 | Improved |
| add inter-frame connections to intra-frame + long range (ablation) | intra + long range · DAVIS | IoU (%): 74.13 -> 74.34 | Improved |
| use semi-supervised first-frame ground truth in place of saliency initialisation (ablation) | Ours · DAVIS | mean IoU (J): 0.776 -> 0.810 | Improved |
Closest papers by meaning
- Saliency-Aware Video Object Segmentation (TPAMI 2017 · similarity 0.91)
- Unsupervised Video Object Segmentation with Motion-based Bilateral Networks (ECCV 2018 · similarity 0.89)
- Unsupervised Learning of Foreground Object Segmentation (IJCV 2019 · similarity 0.89)
- Unsupervised Object Segmentation in Video by Efficient Selection of Highly Probable Positive Features (ICCV 2017 · similarity 0.89)
- Video Segmentation via Object Flow (CVPR 2016 · similarity 0.88)
- Anchor Diffusion for Unsupervised Video Object Segmentation (ICCV 2019 · 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.
