Research map / Architectures and efficiency / RNNs and normalization
CARPe Posterum: A Convolutional Approach for Real-Time Pedestrian Path Prediction
Matias Mendieta, Hamed Tabkhi
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 |
|---|---|---|---|
| Use a convolutional predictor instead of a recurrent/generative prediction framework | CARPe · ETH/UCY (Nvidia P100) | FPS: 19.46 -> 762.14 | Improved |
| Use a convolutional predictor and compact graph module instead of Next's architecture | CARPe vs Next · ETH/UCY AVG | FDE: 1.14 -> 1.05 | Improved |
| Use CARPe rather than Next | Jetson Nano · Jetson Nano | FPS (GPU): 5.61 -> 95.87 | Improved |
| Use CARPe rather than Next | Jetson Nano · Jetson Nano | FPS (CPU): 5.50 -> 48.11 | Improved |
Closest papers by meaning
- A Set of Control Points Conditioned Pedestrian Trajectory Prediction (AAAI 2023 · similarity 0.89)
- A Unified Environmental Network for Pedestrian Trajectory Prediction (AAAI 2024 · similarity 0.89)
- Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Prediction (CVPR 2020 · similarity 0.88)
- SGCN: Sparse Graph Convolution Network for Pedestrian Trajectory Prediction (CVPR 2021 · similarity 0.88)
- ViTE: Virtual Graph Trajectory Expert Router for Pedestrian Trajectory Prediction (AAAI 2026 · similarity 0.87)
- Pedestrian Trajectory Prediction with Missing Data: Datasets, Imputation, and Benchmarking (NeurIPS 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.
