Research map / Vision-language and multimodal / Human and embodied modeling
Deep Learning Technique for Human Parsing: A Survey and Outlook
Lu Yang, Wenhe Jia, Shan Li, Qing Song
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 |
|---|---|---|---|
| hierarchical graph part-relation parser (HHP) instead of tree-based multi-source fusion (CNIF); uncontrolled cross-paper comparison | single human parsing · LIP val | mIoU (%): 57.74 -> 59.25 | Improved |
| attention with human-part position priors (CDGNet, ResNet101) instead of LSTM-based Struc-LSTM (VGG16); uncontrolled cross-paper comparison | single human parsing · ATR test | F-1 (%): 87.88 -> 87.16 | Hurt |
| transformer backbone with pretraining (SOLIDER, Swin-S) instead of CDGNet ResNet101; uncontrolled cross-paper comparison | single human parsing · LIP val | mIoU (%): 60.30 -> 60.21 | No clear effect |
| edge-aware CE2P baseline versus later edge/attention CDGNet; uncontrolled cross-paper comparison | single human parsing · LIP val | mIoU (%): 53.10 -> 60.30 | Improved |
Closest papers by meaning
- Look Into Person: Self-Supervised Structure-Sensitive Learning and a New Benchmark for Human Parsing (CVPR 2017 · similarity 0.92)
- Parsing Based on Parselets: A Unified Deformable Mixture Model for Human Parsing (TPAMI 2016 · similarity 0.91)
- End-to-End One-Shot Human Parsing (TPAMI 2023 · similarity 0.90)
- Instance-level Human Parsing via Part Grouping Network (ECCV 2018 · similarity 0.90)
- Devil in the Details: Towards Accurate Single and Multiple Human Parsing (AAAI 2019 · similarity 0.90)
- Renovating Parsing R-CNN for Accurate Multiple Human Parsing (ECCV 2020 · similarity 0.90)
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.
