Research map / Detection and segmentation / CNN features
Contextual Attention for Hand Detection in the Wild
Supreeth Narasimhaswamy, Zhengwei Wei, Yang Wang, Justin Zhang, Minh Hoai
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 contextual attention module to MaskRCNN (ablation) | MaskRCNN · Oxford-Hand test | AP: 69.9% -> 73.0% | Improved |
| add contextual attention module to MaskRCNN (ablation) | MaskRCNN · TV-Hand test | AP: 59.9% -> 60.3% | No clear effect |
| add semantics context component (ablation) | Hand-CNN · Oxford-Hand test | AP: 71.4% -> 73.0% | Improved |
| add similarity context component (ablation) | Hand-CNN · Oxford-Hand test | AP: 70.8% -> 73.0% | Improved |
| add semantics context component (ablation) | Hand-CNN · TV-Hand test | AP: 59.4% -> 60.3% | Improved |
| add similarity context component (ablation) | Hand-CNN · TV-Hand test | AP: 59.6% -> 60.3% | Improved |
| add COCO-Hand-S to TV-Hand training data (ablation) | MaskRCNN · Oxford-Hand test | AP: 62.5% -> 69.9% | Improved |
| add COCO-Hand-S to TV-Hand training data (ablation) | MaskRCNN · TV-Hand test | AP: 55.4% -> 59.9% | Improved |
| use COCO-Hand (masked unannotated hands) instead of COCO-Hand-S (ablation) | MaskRCNN · Oxford-Hand test | AP: 69.9% -> 76.7% | Improved |
| use COCO-Hand (masked unannotated hands) instead of COCO-Hand-S (ablation) | MaskRCNN · TV-Hand test | AP: 59.9% -> 63.5% | Improved |
| share weights between orientation branch and MaskRCNN branch (ablation) | Hand-CNN · hand detection | AP | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FasterRCNN — Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (TPAMI 2016) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Detecting Hands and Recognizing Physical Contact in the Wild (NeurIPS 2020 · similarity 0.92)
- Scale Invariant Fully Convolutional Network: Detecting Hands Efficiently (AAAI 2019 · similarity 0.91)
- Recognition from Hand Cameras: A Revisit with Deep Learning (ECCV 2016 · similarity 0.89)
- Real-Time 3D Hand Pose Estimation with 3D Convolutional Neural Networks (TPAMI 2018 · similarity 0.87)
- Online Detection and Classification of Dynamic Hand Gestures With Recurrent 3D Convolutional Neural Network (CVPR 2016 · similarity 0.87)
- 3D Convolutional Neural Networks for Efficient and Robust Hand Pose Estimation From Single Depth Images (CVPR 2017 · similarity 0.87)
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.
