Research map / Probabilistic and scientific modeling / Molecules and proteins
Bifold and Semantic Reasoning for Pedestrian Behavior Prediction
Amir Rasouli, Mohsen Rohani, Jun Luo
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 joint prediction module (MJP) alongside independent prediction (MIP) (ablation) | BiPed · PIE action prediction | accuracy: 0.85 -> 0.89 | Improved |
| add independent prediction module (MIP) alongside joint prediction (MJP) (ablation) | BiPed · PIE trajectory prediction | ADE: 16.22 -> 15.87 | Improved |
| combine both independent and joint encoders and predictors (ablation) | BiPed · PIE | ADE: 15.59 -> 15.21 | Improved |
| add categorical interaction module with hybrid conv+LSTM and IAU (ablation) | BiPed · PIE trajectory prediction | ADE: 16.00 -> 15.21 | Improved |
| separate semantic maps into categories instead of a single map (ablation) | BiPed · PIE trajectory prediction | ADE: 17.04 -> 15.70 | Improved |
| add interaction attention unit to categorical hybrid (ablation) | BiPed · PIE trajectory prediction | ADE: 15.55 -> 15.21 | Improved |
| add auxiliary grid classification task (cell size 60) (ablation) | BiPed · PIE trajectory prediction | ADE: 16.38 -> 15.21 | Improved |
| increase grid cell size from 60 to 120 (ablation) | BiPed · PIE trajectory prediction | ADE: 15.21 -> 16.32 | Hurt |
| use noisy ego-motion planner instead of true future ego-motion | BiPed · PIE trajectory prediction | ADE: 15.21 -> 18.03 | Hurt |
| add future ego-motion information (ablation) | BiPed · PIE trajectory prediction | ADE: 18.44 -> 15.21 | Improved |
| use noisy ego-motion planner instead of true future ego-motion | BiPed · JAAD trajectory prediction | ADE: 20.58 -> 20.75 | No clear effect |
| use BiPed instead of PIE_full | trajectory predictor · PIE | ADE: 19.50 -> 15.21 | Improved |
Closest papers by meaning
- PIE: A Large-Scale Dataset and Models for Pedestrian Intention Estimation and Trajectory Prediction (ICCV 2019 · similarity 0.89)
- PSI: A Benchmark for Human Interpretation and Response in Traffic Interactions (NeurIPS 2025 · similarity 0.86)
- MS-TIP: Imputation Aware Pedestrian Trajectory Prediction (ICML 2024 · similarity 0.85)
- A Unified Environmental Network for Pedestrian Trajectory Prediction (AAAI 2024 · similarity 0.85)
- Social-Transmotion: Promptable Human Trajectory Prediction (ICLR 2024 · similarity 0.85)
- Multi-modal Knowledge Distillation-based Human Trajectory Forecasting (CVPR 2025 · 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.
