Research map / Detection and segmentation / Tracking
Deep Occlusion Reasoning for Multi-Camera Multi-Target Detection
Pierre Baque, Francois Fleuret, Pascal Fua
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 |
|---|---|---|---|
| fine-tune the full CRF end-to-end through back Mean-Field (ablation) | CNN/CRF multi-camera detector · ETHZ multi-camera | MODA | Improved |
| use full high-order occlusion term instead of simplified one (ablation) | CNN/CRF multi-camera detector · ETHZ multi-camera | MODA | Improved |
| add the high-order term (ablation) | CNN/CRF multi-camera detector · ETHZ multi-camera | MODA | Improved |
| add the high-order term when transferring to unseen EPFL data (ablation) | CNN/CRF multi-camera detector · EPFL multi-camera | MODA | Improved |
| train without ground truth annotations (unsupervised, from background subtraction) (ablation) | CNN/CRF multi-camera detector · ETHZ multi-camera | MODA | Mixed |
| use full high-order term instead of simplified one on poorly calibrated data (ablation) | CNN/CRF multi-camera detector · PETS S2L1 | MODA | No clear effect |
| add flow-based temporal consistency to the detections | CNN/CRF multi-camera detector · ETHZ, EPFL, PETS (r=0.5) | MODA | Improved |
Closest papers by meaning
- Learning to Separate: Detecting Heavily-Occluded Objects in Urban Scenes (ECCV 2020 · similarity 0.87)
- PoseTrack21: A Dataset for Person Search, Multi-Object Tracking and Multi-Person Pose Tracking (CVPR 2022 · similarity 0.86)
- Bi-box Regression for Pedestrian Detection and Occlusion Estimation (ECCV 2018 · similarity 0.86)
- DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimation (CVPR 2016 · similarity 0.86)
- CoMotion: Concurrent Multi-person 3D Motion (ICLR 2025 · similarity 0.85)
- Multi-View People Detection in Large Scenes via Supervised View-Wise Contribution Weighting (AAAI 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.
