Research map / 3D vision / Human pose estimation
Where and Why Are They Looking? Jointly Inferring Human Attention and Intentions in Complex Tasks
Ping Wei, Yang Liu, Tianmin Shu, Nanning Zheng, Song-Chun Zhu
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 |
|---|---|---|---|
| jointly model pose, attention, objects, and their relations with HAO | human intention prediction · TIA | accuracy: 0.29 -> 0.40 | Improved |
| add the human-attention relation to pose features (ablation) | HAO intention prediction · TIA | accuracy: 0.34 -> 0.36 | Improved |
| add the human-attention relation to attention patches (ablation) | HAO intention prediction · TIA | accuracy: 0.07 -> 0.28 | Improved |
| add the attention-object relation to attention patches (ablation) | HAO intention prediction · TIA | accuracy: 0.07 -> 0.25 | Improved |
| add the attention-object relation to object features (ablation) | HAO intention prediction · TIA | accuracy: 0.18 -> 0.28 | Improved |
| jointly model pose, attention, objects, and their relations with HAO | human attention prediction · TIA | 3D location error: 0.655 -> 0.628 | Improved |
| jointly model pose, attention, objects, and their relations with HAO | human attention prediction · TIA | 3D direction error: 0.540 -> 0.475 | Improved |
| jointly model pose, attention, objects, and their relations with HAO | human attention prediction · TIA | 2D location error: 97 -> 93 | Improved |
| decompose tasks into sequential intentions and jointly use human, attention, and object information | task recognition · TIA | accuracy: 0.62 -> 0.73 | Improved |
| add the human-attention relation to pose features (ablation) | HAO task recognition · TIA | accuracy: 0.58 -> 0.61 | Improved |
| add the human-attention relation to attention patches (ablation) | HAO task recognition · TIA | accuracy: 0.20 -> 0.46 | Improved |
| add the attention-object relation to attention patches (ablation) | HAO task recognition · TIA | accuracy: 0.20 -> 0.54 | Improved |
Closest papers by meaning
- Learning from Observer Gaze: Zero-Shot Attention Prediction Oriented by Human-Object Interaction Recognition (CVPR 2024 · similarity 0.87)
- Reasoning About Human-Object Interactions Through Dual Attention Networks (ICCV 2019 · similarity 0.87)
- Gazeformer: Scalable, Effective and Fast Prediction of Goal-Directed Human Attention (CVPR 2023 · similarity 0.87)
- Connecting Gaze, Scene, and Attention: Generalized Attention Estimation via Joint Modeling of Gaze and Scene Saliency (ECCV 2018 · similarity 0.87)
- Inferring Shared Attention in Social Scene Videos (CVPR 2018 · similarity 0.87)
- Unifying Top-down and Bottom-up Scanpath Prediction Using Transformers (CVPR 2024 · similarity 0.86)
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.
