Research map / Detection and segmentation / CNN features
Progressive End-to-End Object Detection in Crowded Scenes
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 |
|---|---|---|---|
| Add progressive prediction to Sparse RCNN | Sparse RCNN · CrowdHuman | AP: 90.7 -> 92.0 | Helped |
| Add progressive prediction to Sparse RCNN | Sparse RCNN · CrowdHuman | MR^-2: 44.7 -> 41.4 | Helped |
| Add progressive prediction to Sparse RCNN | Sparse RCNN · CrowdHuman | JI: 81.4 -> 83.2 | Helped |
| Add progressive prediction to Deformable DETR | Deformable DETR · CrowdHuman | JI: 83.1 -> 84.0 | Helped |
| Add progressive prediction to Sparse RCNN | Sparse RCNN · CityPersons | AP: 96.8 -> 97.6 | Helped |
| Add progressive prediction to Sparse RCNN | Sparse RCNN · COCO 2017 minival | AP: 45.0 -> 46.1 | Helped |
| Add relation information extractor (ablation) | Sparse RCNN · CrowdHuman | AP: 90.7 -> 91.5 | Helped |
| Add relation information extractor and local self-attention (ablation) | Sparse RCNN · CrowdHuman | AP: 91.5 -> 92.0 | Helped |
| Add new learnable embeddings to relation extractor and local self-attention (ablation) | Sparse RCNN · CrowdHuman | MR^-2: 42.0 -> 41.4 | Helped |
| Increase query count from 500 to 750 (ablation) | Sparse RCNN+Ours · CrowdHuman | AP: 92.0 -> 92.5 | Helped |
| Increase decoder depth from 6 to 8 (ablation) | Sparse RCNN · CrowdHuman | AP: 90.7 -> 90.4 | Hurt |
| Vary the accepted-query confidence threshold (ablation) | Progressive prediction method · CrowdHuman | Detection performance | Helped |
Closest papers by meaning
- Detection in Crowded Scenes: One Proposal, Multiple Predictions (CVPR 2020 · similarity 0.90)
- Dense Distinct Query for End-to-End Object Detection (CVPR 2023 · similarity 0.89)
- End-To-End People Detection in Crowded Scenes (CVPR 2016 · similarity 0.88)
- CrowdCLIP: Unsupervised Crowd Counting via Vision-Language Model (CVPR 2023 · similarity 0.85)
- Adaptive NMS: Refining Pedestrian Detection in a Crowd (CVPR 2019 · similarity 0.85)
- Looking Beyond the Known: Towards a Data Discovery Guided Open-World Object Detection (NeurIPS 2025 · similarity 0.84)
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.