# Temporal Pyramid Network for Pedestrian Trajectory Prediction with Multi-Supervision

arXiv: https://arxiv.org/abs/2012.01884 · HTML: https://mlsanity.com/paper/2012.01884/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2020.

## Built on by (most cited first, 20 of 20)

- [View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrums](https://mlsanity.com/paper/2110.07288/) (2021)
- [EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecasting](https://mlsanity.com/paper/2307.09306/) (2023)
- [Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction](https://mlsanity.com/paper/2403.18447/) (2024)
- [MSN: Multi-Style Network for Trajectory Prediction](https://mlsanity.com/paper/2107.00932/) (2021)
- [CSCNet: Contextual Semantic Consistency Network for Trajectory Prediction in Crowded Spaces](https://mlsanity.com/paper/2202.08506/) (2022)
- [Social Interpretable Tree for Pedestrian Trajectory Prediction](https://mlsanity.com/paper/2205.13296/) (2022)
- [STGlow: A Flow-based Generative Framework with Dual Graphormer for Pedestrian Trajectory Prediction](https://mlsanity.com/paper/2211.11220/) (2022)
- [Another Vertical View: A Hierarchical Network for Heterogeneous Trajectory Prediction via Spectrums](https://mlsanity.com/paper/2304.05106/) (2023)
- [Improving Transferability for Cross-domain Trajectory Prediction via Neural Stochastic Differential Equation](https://mlsanity.com/paper/2312.15906/) (2023)
- [Recurrent Aligned Network for Generalized Pedestrian Trajectory Prediction](https://mlsanity.com/paper/2403.05810/) (2024)
- [Pedestrian Trajectory Prediction Based on Social Interactions Learning With Random Weights](https://mlsanity.com/paper/2501.07711/) (2025)
- [Continuous Locomotive Crowd Behavior Generation](https://mlsanity.com/paper/2504.04756/) (2025)
- [Resonance: Learning to Predict Social-Aware Pedestrian Trajectories as Co-Vibrations](https://mlsanity.com/paper/2412.02447/) (2024)
- [Uncovering the human motion pattern: Pattern Memory-based Diffusion Model for Trajectory Prediction](https://mlsanity.com/paper/2401.02916/) (2024)
- [A Memory-Augmented Multi-Task Collaborative Framework for Unsupervised Traffic Accident Detection in Driving Videos](https://mlsanity.com/paper/2307.14575/) (2023)
- [Recent Advances in Multi-Agent Human Trajectory Prediction: A Comprehensive Review](https://mlsanity.com/paper/2506.14831/) (2025)
- [A Multi-Stage Goal-Driven Network for Pedestrian Trajectory Prediction](https://mlsanity.com/paper/2406.18050/) (2024)
- [MGTraj: Multi-Granularity Goal-Guided Human Trajectory Prediction with Recursive Refinement Network](https://mlsanity.com/paper/2509.09200/) (2025)
- [TrajMamba: An Ego-Motion-Guided Mamba Model for Pedestrian Trajectory Prediction from an Egocentric Perspective](https://mlsanity.com/paper/2603.14739/) (2026)
- [MUSCLE-NET: Predicted-Multiscale-Aware Network for Pedestrian Trajectory Forecasting](https://mlsanity.com/paper/2606.00471/) (2026)

## Abstract (arXiv)

Predicting human motion behavior in a crowd is important for many applications, ranging from the natural navigation of autonomous vehicles to intelligent security systems of video surveillance. All the previous works model and predict the trajectory with a single resolution, which is rather inefficient and difficult to simultaneously exploit the long-range information (e.g., the destination of the trajectory), and the short-range information (e.g., the walking direction and speed at a certain time) of the motion behavior. In this paper, we propose a temporal pyramid network for pedestrian trajectory prediction through a squeeze modulation and a dilation modulation. Our hierarchical framework builds a feature pyramid with increasingly richer temporal information from top to bottom, which can better capture the motion behavior at various tempos. Furthermore, we propose a coarse-to-fine fusion strategy with multi-supervision. By progressively merging the top coarse features of global context to the bottom fine features of rich local context, our method can fully exploit both the long-range and short-range information of the trajectory. Experimental results on several benchmarks demonstrate the superiority of our method.