mlsanityData to 7 Oct 2026

TSCA-Net: Temporal-Spatial Clique Attention for Interpretable Multimodal Pedestrian Trajectory Prediction

arXiv 2607.11939 ↗First posted 11 Jul 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Accurate pedestrian trajectory prediction in crowded environments remains challenging due to the multimodal uncertainty of human motion and the variable complexity of motion dynamics across different scene contexts. Existing goal-conditioned models rely on static displacement structures that assign equal weight to all historical time steps, standard graph attention mechanisms, and fixed-capacity motion decoders that cannot adapt to local prediction complexity. To address these limitations, we propose TSCA-Net, a trajectory prediction framework built upon three complementary modules. The Temporal-Spatial Clique Attention (TSCA) module introduces learnable temporal gating into clique-based goal-history interaction, enabling time-aware modulation of historical observations relative to each candidate goal. The Cross-Pedestrian Clique Potential (CPCP) module models asymmetric pairwise agent relationships through a dynamic clique potential framework with a time-varying social graph. The Adaptive KAN Grid Refinement (AKGR) mechanism dynamically adjusts the B-spline grid resolution of a Kolmogorov-Arnold Network-augmented LSTM decoder based on per-agent goal distribution entropy, balancing model expressiveness against overfitting across varying motion complexities. Extensive experiments on the ETH/UCY and Stanford Drone Dataset benchmarks demonstrate that TSCA-Net achieves state-of-the-art performance, with average ADE/FDE of 0.13/0.20 m on ETH/UCY and 6.95/10.43 pixels on SDD. Comprehensive ablation studies confirm the complementary contributions of all three proposed modules.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 30 of its 51 references that are in the map. First posted on arXiv 11 Jul 2026.

Builds on

30 of 51 references.

References · 30

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
  3. 2024KAN: Kolmogorov-Arnold Networkscited by 634
  4. 2020TNT: Target-driveN Trajectory Predictioncited by 345
  5. 2021AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecastingcited by 327
  6. 2020Social-STGCNN: A Social Spatio-Temporal Graph Convolutional Neural Network for Human Trajectory Predictioncited by 324
  7. 2017DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agentscited by 310
  8. 2018SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraintscited by 296
  9. 2020It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Predictioncited by 235
  10. 2019Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networkscited by 228
  11. 2020From Goals, Waypoints & Paths To Long Term Human Trajectory Forecastingcited by 166
  12. 2019Anomaly Detection in Video Sequence with Appearance-Motion Correspondencecited by 118
18 more
  1. 2021SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Predictioncited by 97
  2. 2022Remember Intentions: Retrospective-Memory-based Trajectory Predictioncited by 86
  3. 2019The Garden of Forking Paths: Towards Multi-Future Trajectory Predictioncited by 72
  4. 2020MANTRA: Memory Augmented Networks for Multiple Trajectory Predictioncited by 69
  5. 2022Human Trajectory Prediction via Neural Social Physicscited by 66
  6. 2021Stepwise Goal-Driven Networks for Trajectory Predictioncited by 62
  7. 2021View Vertically: A Hierarchical Network for Trajectory Prediction via Fourier Spectrumscited by 44
  8. 2018PORCA: Modeling and Planning for Autonomous Driving among Many Pedestrianscited by 36
  9. 2019Discrete Residual Flow for Probabilistic Pedestrian Behavior Predictioncited by 34
  10. 2024ITINERA: Integrating Spatial Optimization with Large Language Models for Open-domain Urban Itinerary Planningcited by 33
  11. 2021Are socially-aware trajectory prediction models really socially-aware?cited by 32
  12. 2022Goal-driven Self-Attentive Recurrent Networks for Trajectory Predictioncited by 28
  13. 2022SMEMO: Social Memory for Trajectory Forecastingcited by 26
  14. 2021You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Predictioncited by 23
  15. 2022End-to-End Trajectory Distribution Prediction Based on Occupancy Grid Mapscited by 22
  16. 2021Safety-Oriented Pedestrian Motion and Scene Occupancy Forecastingcited by 6
  17. 2020Enhanced Few-shot Learning for Intrusion Detection in Railway Video Surveillancecited by 3
  18. 2018Pedestrian Trajectory Prediction with Structured Memory Hierarchiescited by 2

Built on by

Not cited yet.