Research map / Video / Video segmentation and tracking
Preference-Aware Task Assignment in Spatial Crowdsourcing
Yan Zhao, Jinfu Xia, Guanfeng Liu, Han Su, Defu Lian, Shuo Shang, Kai Zheng
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 historical tensor Xh to tensor decomposition (ablation) | TD · Worker preference estimation | RMSE: 0.3056 -> 0.2406 | Improved |
| add time-task and task-feature context matrices Y and Z (ablation) | TD+H · Worker preference estimation | RMSE: 0.2406 -> 0.2344 | Improved |
| add historical tensor Xh to tensor decomposition (ablation) | TD · Worker preference estimation | MAE: 0.2671 -> 0.2129 | Improved |
| add context matrices Y and Z (ablation) | TD+H · Worker preference estimation | MAE: 0.2129 -> 0.2054 | Improved |
| increase time span of historical data from 1 to 4 weeks | HCTD · Worker preference estimation | RMSE | Improved |
| use HCTD-estimated preferences for task assignment instead of AVF or preference-free MCTA | HCTD-TA · Check-in dataset, assignment success rate | assignment success rate | Improved |
| add spatial (travel cost) weighting to PTA (SPTA) (ablation) | PTA · Check-in dataset, varying |S| | assignment success rate: up to 42% | Improved |
| add temporal (deadline) weighting to PTA (TPTA) (ablation) | PTA · Check-in dataset, varying |S| | number of assigned tasks: up to 40% | Improved |
| add spatial or temporal weighting to PTA when varying task valid time (ablation) | PTA · Check-in dataset, varying valid time phi | assignment success rate | Hurt |
Closest papers by meaning
- GKD-Recruiter: Jointly Modeling Social and Task Heterogeneity for Spatial Crowdsourcing via Graph Knowledge Distillation (ICML 2026 · similarity 0.87)
- Gradient-Guided Credit Assignment and Joint Optimization for Dependency-Aware Spatial Crowdsourcing (AAAI 2025 · similarity 0.86)
- Making Better Use of the Crowd: How Crowdsourcing Can Advance Machine Learning Research (JMLR 2018 · similarity 0.83)
- Exploiting Worker Correlation for Label Aggregation in Crowdsourcing (ICML 2019 · similarity 0.82)
- KFNN: K-Free Nearest Neighbor For Crowdsourcing (NeurIPS 2024 · similarity 0.81)
- Get Rid of Isolation: A Continuous Multi-task Spatio-Temporal Learning Framework (NeurIPS 2024 · similarity 0.81)
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.
