Research map / Detection and segmentation / CNN features
Body-Face Joint Detection via Embedding and Head Hook
Junfeng Wan, Jiangfan Deng, Xiaosong Qiu, Feng Zhou
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 embedding guidance to position-mode association (ablation) | FPN + BFJ · CrowdHuman val | mMR-2: 66.4 -> 55.7 | Improved |
| add head hook guidance to position-mode association (ablation) | FPN + BFJ · CrowdHuman val | mMR-2: 66.4 -> 54.2 | Improved |
| fuse embedding and head hook similarities (add embedding to head hook) (ablation) | FPN + BFJ · CrowdHuman val | mMR-2: 54.2 -> 52.5 | Improved |
| add embedding guidance to position-mode association (ablation) | RetinaNet + BFJ · CrowdHuman val | mMR-2: 73.8 -> 68.9 | Improved |
| add head hook guidance to position-mode association (ablation) | RetinaNet + BFJ · CrowdHuman val | mMR-2: 73.8 -> 64.5 | Improved |
| fuse both guidance cues (ablation) | RetinaNet + BFJ · CrowdHuman val | mMR-2: 64.5 -> 63.7 | Improved |
| add Angular loss to Smooth L1 head hook loss (ablation) | FPN + BFJ · CrowdHuman val | mMR-2: 53.7 -> 52.5 | Improved |
| add Angular loss to Smooth L1 head hook loss (ablation) | RetinaNet + BFJ · CrowdHuman val | mMR-2: 64.8 -> 63.7 | Improved |
| use BFJ association instead of cascade, position and position-with-head baselines | FPN · CrowdHuman val | mMR-2: 67.2 -> 52.5 | Improved |
| use BFJ association on CrowdDet instead of baselines | CrowdDet · CrowdHuman val | mMR-2: 66.1 -> 52.3 | Improved |
| use head as bridge between body and face in detection (POSH vs POS) | FPN + POS · CrowdHuman val | face MR-2: 54.3 -> 57.1 | Hurt |
| use cascade face detector on body crops (CAS vs POS) | FPN · CrowdHuman val | face AP@0.5: 70.3 -> 59.3 | Hurt |
Closest papers by meaning
- BPJDet: Extended Object Representation for Generic Body-Part Joint Detection (TPAMI 2024 · similarity 0.90)
- PairDETR : Joint Detection and Association of Human Bodies and Faces (CVPR 2024 · similarity 0.89)
- Relational Learning for Joint Head and Human Detection (AAAI 2020 · similarity 0.87)
- Detangling People: Individuating Multiple Close People and Their Body Parts via Region Assembly (CVPR 2017 · similarity 0.86)
- GigaHumanDet: Exploring Full-Body Detection on Gigapixel-Level Images (AAAI 2024 · similarity 0.85)
- PBADet: A One-Stage Anchor-Free Approach for Part-Body Association (ICLR 2024 · 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.
