Research map / Video / Video segmentation and tracking
Temporal Pyramid Network for Pedestrian Trajectory Prediction with Multi-Supervision
Rongqin Liang, Yuanman Li, Xia Li, Yi Tang, Jiantao Zhou, Wenbin Zou
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 |
|---|---|---|---|
| Use TPNMS instead of S-GAN | pedestrian trajectory prediction · ETH+UCY AVG | ADE: 0.58 -> 0.38; 34% relative improvements | Improved |
| Use TPNMS instead of S-GAN | pedestrian trajectory prediction · ETH+UCY AVG | FDE: 1.18 -> 0.73; 38% relative improvements | Improved |
| Use TPNMS instead of Social-STGCNN | pedestrian trajectory prediction · ETH+UCY AVG | ADE: 0.44 -> 0.38; about 14% | Improved |
| Use TPNMS instead of Social-STGCNN | pedestrian trajectory prediction · ETH+UCY AVG | FDE: 0.75 -> 0.73; about 3% | Improved |
| Add temporal pyramid architecture to the S-GAN-P baseline (ablation) | S-GAN-P trajectory predictor · ETH+UCY AVG | ADE: 0.61 -> 0.41 | Improved |
| Add temporal pyramid architecture to the S-GAN-P baseline (ablation) | S-GAN-P trajectory predictor · ETH+UCY AVG | FDE: 1.21 -> 0.79 | Improved |
| Add multi-supervision to the temporal pyramid network (ablation) | TPN · ETH+UCY AVG | ADE: 0.41 -> 0.38 | Improved |
| Add multi-supervision to the temporal pyramid network (ablation) | TPN · ETH+UCY AVG | FDE: 0.79 -> 0.73 | Improved |
Closest papers by meaning
- CF-LSTM: Cascaded Feature-Based Long Short-Term Networks for Predicting Pedestrian Trajectory (AAAI 2020 · similarity 0.88)
- SGCN: Sparse Graph Convolution Network for Pedestrian Trajectory Prediction (CVPR 2021 · similarity 0.88)
- Multi-Stream Representation Learning for Pedestrian Trajectory Prediction (AAAI 2023 · similarity 0.87)
- Complementary Attention Gated Network for Pedestrian Trajectory Prediction (AAAI 2022 · similarity 0.87)
- Sparse Instance Conditioned Multimodal Trajectory Prediction (ICCV 2023 · similarity 0.87)
- A Unified Environmental Network for Pedestrian Trajectory Prediction (AAAI 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.
