Research map / Video / Video segmentation and tracking
Sequential Clique Optimization for Video Object Segmentation
Yeong Jun Koh, Young-Yoon Lee, Chang-Su Kim
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 post-processing and MRF (ablation) | Proposed-M · DAVIS 2016 | mean region similarity J: 0.769 -> 0.787 | Improved |
| add post-processing and MRF (ablation) | Proposed-M · DAVIS 2017 | mean region similarity J: 0.694 -> 0.714 | Improved |
| use color bag-of-visual-words instead of deep VGG features for edge weights (ablation) | Proposed-M · DAVIS 2016 | mean region similarity J: 0.755 -> 0.787 | Improved |
| use color bag-of-visual-words instead of deep VGG features for edge weights (ablation) | Proposed-M · DAVIS 2017 | mean region similarity J: 0.666 -> 0.714 | Improved |
| replace conventional matching [3] with SCO (no post-processing) (ablation) | FCIS instances + Proposed-M · DAVIS 2016 | mean region similarity J: 0.737 -> 0.769 | Improved |
| replace conventional matching [3] with SCO (no post-processing) (ablation) | FCIS instances + Proposed-M · DAVIS 2017 | mean region similarity J: 0.635 -> 0.694 | Improved |
| replace binary integer program matching [57] with SCO (no post-processing) (ablation) | FCIS instances + Proposed-M · DAVIS 2016 | mean region similarity J: 0.710 -> 0.769 | Improved |
| use offline graph over all frames instead of online graph of past frames (ablation) | Proposed · DAVIS 2016 | mean region similarity J: 0.783 -> 0.796 | Improved |
| select multiple tracks (Proposed-M) instead of a single track | Proposed-F · DAVIS 2016 | mean region similarity J: 0.796 -> 0.787 | Hurt |
| select multiple tracks (Proposed-M) instead of a single track | Proposed-F · DAVIS 2017 | mean region similarity J: 0.685 -> 0.714 | Improved |
Closest papers by meaning
- Saliency-Aware Video Object Segmentation (TPAMI 2017 · similarity 0.87)
- Instance-Level Video Segmentation From Object Tracks (CVPR 2016 · similarity 0.86)
- TokenCut: Segmenting Objects in Images and Videos With Self-Supervised Transformer and Normalized Cut (TPAMI 2023 · similarity 0.86)
- Graph Moving Object Segmentation (TPAMI 2020 · similarity 0.85)
- CDTS: Collaborative Detection, Tracking, and Segmentation for Online Multiple Object Segmentation in Videos (ICCV 2017 · similarity 0.85)
- Guided Slot Attention for Unsupervised Video Object Segmentation (CVPR 2024 · similarity 0.85)
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.
