Research map / Reinforcement learning / Imitation learning
Predicting Goal-Directed Human Attention Using Inverse Reinforcement Learning
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| use IRL instead of the Detector baseline | Scanpath prediction · COCO-Search18 test | TFP-AUC: 4.046 -> 4.509 | Helped |
| use IRL instead of BC-CNN | Scanpath prediction · COCO-Search18 test | Sequence Score: 0.409 -> 0.422 | Helped |
| replace DCB with CFI (ablation) | IRL · COCO-Search18 test | Sequence Score: 0.422 -> 0.402 | Hurt |
| remove history map (ablation) | IRL with DCB · COCO-Search18 test | Sequence Score: 0.422 -> 0.419 | No clear effect |
| remove saliency map (ablation) | IRL with DCB · COCO-Search18 test | Sequence Score: 0.422 -> 0.419 | No clear effect |
| remove stuff maps (ablation) | IRL with DCB · COCO-Search18 test | Sequence Score: 0.422 -> 0.407 | Hurt |
| remove thing maps (ablation) | IRL with DCB · COCO-Search18 test | Sequence Score: 0.422 -> 0.331 | Hurt |
| remove target map (ablation) | IRL with DCB · COCO-Search18 test | Sequence Score: 0.422 -> 0.338 | Hurt |
| use immediate reward instead of total reward (ablation) | IRL policy · COCO-Search18 test | Sequence Score: 0.422 -> 0.375 | Hurt |
| train with IRL rather than CNN behavior cloning at 5 images per category | Scanpath prediction · COCO-Search18 test | TFP-AUC: 3.484 -> 3.696 | Helped |
| use a group model trained on other subjects instead of an individual model | IRL · COCO-Search18 test subjects | performance | No clear effect |
Closest papers by meaning
- Gazing at Rewards: Eye Movements as a Lens into Human and AI Decision-Making in Hybrid Visual Foraging (CVPR 2025 · similarity 0.86)
- Unifying Top-down and Bottom-up Scanpath Prediction Using Transformers (CVPR 2024 · similarity 0.86)
- Estimating cognitive biases with attention-aware inverse planning (NeurIPS 2025 · similarity 0.86)
- DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning (ICLR 2026 · similarity 0.86)
- Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language Models (ICLR 2025 · similarity 0.85)
- Focus-Then-Decide: Segmentation-Assisted Reinforcement Learning (AAAI 2024 · similarity 0.85)
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.