Research map / Detection and segmentation / Weakly supervised detection and segmentation
Foreground Clustering for Joint Segmentation and Localization in Videos and Images
Abhishek Sharma
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 segmentation cues to localization (ablation) | QP(Loc.) on YouTube Object Dataset · YouTube Object Dataset | CorLoc: 35 -> 49 | Improved |
| Add the foreground model to joint localization and segmentation (ablation) | QP(Loc.)+Seg on YouTube Object Dataset · YouTube Object Dataset | CorLoc: 49 -> 54 | Improved |
| Add localization cues to segmentation (ablation) | QP(Seg.) on YouTube Object Dataset · YouTube Object Dataset | IoU: 49 -> 56 | Improved |
| Add the foreground model to joint localization and segmentation (ablation) | QP(Seg. +Loc.) on YouTube Object Dataset · YouTube Object Dataset | IoU: 56 -> 61 | Improved |
| Add segmentation cues and the foreground model (ablation) | QP(Loc.) on Object Discovery · Object Discovery | CorLoc: 75 -> 80 | Improved |
| Add segmentation cues and the foreground model (ablation) | QP(Loc.) on PASCAL VOC 2007 · PASCAL VOC 2007 | CorLoc: 40 -> 51 | Improved |
| Use Foreground Clustering instead of CSP15 | Object Discovery localization · Object Discovery | CorLoc: 84 -> 80 | Hurt |
| Use Foreground Clustering instead of CSP15 | PASCAL VOC 2007 localization · PASCAL VOC 2007 | CorLoc: 68 -> 51 | Hurt |
| Use Foreground Clustering instead of FST | YouTube Object Dataset segmentation · YouTube Object Dataset | IoU: 53 -> 61 | Improved |
Closest papers by meaning
- Video Object Segmentation by Learning Location-Sensitive Embeddings (ECCV 2018 · similarity 0.88)
- Track and Segment: An Iterative Unsupervised Approach for Video Object Proposals (CVPR 2016 · similarity 0.87)
- Video Segmentation via Multiple Granularity Analysis (CVPR 2017 · similarity 0.87)
- FOCUS: Towards Universal Foreground Segmentation (AAAI 2025 · similarity 0.87)
- Unsupervised Object Segmentation in Video by Efficient Selection of Highly Probable Positive Features (ICCV 2017 · similarity 0.87)
- Learning Spatial-Semantic Features for Robust Video Object Segmentation (ICLR 2025 · 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.
