ART: Adaptive Relational Transformer for Pedestrian Trajectory Prediction with Temporal-Aware Relations

• URL: http://arxiv.org/abs/2604.03649v1
• Date: Sat, 04 Apr 2026 08:59:33 GMT
• Title: ART: Adaptive Relational Transformer for Pedestrian Trajectory Prediction with Temporal-Aware Relations
• Abstract summary: In this work, we present an Adaptive Transformer (ART) to capture the evolution of pairwise interactions.<n>ART delivers state-of-the-art accuracy with high computational efficiency.<n>In evaluations on ETH/UCY and NBA benchmarks, ART delivers state-of-the-art accuracy with high computational efficiency.
• Score: 25.28104102630492
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Accurate prediction of real-world pedestrian trajectories is crucial for a wide range of robot-related applications. Recent approaches typically adopt graph-based or transformer-based frameworks to model interactions. Despite their effectiveness, these methods either introduce unnecessary computational overhead or struggle to represent the diverse and time-varying characteristics of human interactions. In this work, we present an Adaptive Relational Transformer (ART), which introduces a Temporal-Aware Relation Graph (TARG) to explicitly capture the evolution of pairwise interactions and an Adaptive Interaction Pruning (AIP) mechanism to reduce redundant computations efficiently. Extensive evaluations on ETH/UCY and NBA benchmarks show that ART delivers state-of-the-art accuracy with high computational efficiency.

Related papers

• EEGForceFusion: Joint Tokenised-Continuous Representation Learning for Subject-Independent Grasp Force Decoding [7.727905404396572]
  We propose a hybrid EEG decoding framework that jointly models continuous and tokenised representations.<n>The proposed approach integrates convolutional-recurrent representation learning, quantisation-based tokenisation, and transformer-based temporal modelling.<n>Results demonstrate strong cross-subject generalisation and highlight the practicality of hybrid continuous-tokenised representations for real-time EEG-based force decoding.
  arXiv  Detail & Related papers  (2026-07-27T08:08:08Z)
• ADFormer: Aggregation Differential Transformer for Passenger Demand Forecasting [13.568598787640127]
  We propose the Differential Aggregation Transformer (AD), which offers new insights to demand forecasting promotion.<n>We utilize distinct spatial correlations and achieve attention denoising. Meanwhile, we design aggregation strategies based on the nature of space and time.<n> Experiments conducted on taxi and bike confirm the effectiveness and efficiency of our model, demonstrating its practical value.
  arXiv  Detail & Related papers  (2025-06-03T07:55:51Z)
• CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction [77.8576094863446]
  We propose a new detextbfCoupled dutextbfAl-interactive lineatextbfR atttextbfEntion (CARE) mechanism. We first propose an asymmetrical feature decoupling strategy that asymmetrically decouples the learning process for local inductive bias and long-range dependencies. By adopting a decoupled learning way and fully exploiting complementarity across features, our method can achieve both high efficiency and accuracy.
  arXiv  Detail & Related papers  (2024-11-25T07:56:13Z)
• Interpretable Interaction Modeling for Trajectory Prediction via Agent Selection and Physical Coefficient [1.6954753390775528]
  We present ASPILin, which manually selects interacting agents and replaces the attention scores in Transformer with a newly computed physical correlation coefficient.<n>Surprisingly, these simple modifications can significantly improve prediction performance and substantially reduce computational costs.
  arXiv  Detail & Related papers  (2024-05-21T18:45:18Z)
• Multi-Agent Dynamic Relational Reasoning for Social Robot Navigation [50.01551945190676]
  Social robot navigation can be helpful in various contexts of daily life but requires safe human-robot interactions and efficient trajectory planning. We propose a systematic relational reasoning approach with explicit inference of the underlying dynamically evolving relational structures. We demonstrate its effectiveness for multi-agent trajectory prediction and social robot navigation.
  arXiv  Detail & Related papers  (2024-01-22T18:58:22Z)
• Correlated Attention in Transformers for Multivariate Time Series [22.542109523780333]
  We propose a novel correlated attention mechanism, which efficiently captures feature-wise dependencies, and can be seamlessly integrated within the encoder blocks of existing Transformers. In particular, correlated attention operates across feature channels to compute cross-covariance matrices between queries and keys with different lag values, and selectively aggregate representations at the sub-series level. This architecture facilitates automated discovery and representation learning of not only instantaneous but also lagged cross-correlations, while inherently capturing time series auto-correlation.
  arXiv  Detail & Related papers  (2023-11-20T17:35:44Z)
• Real-Time Motion Prediction via Heterogeneous Polyline Transformer with Relative Pose Encoding [121.08841110022607]
  Existing agent-centric methods have demonstrated outstanding performance on public benchmarks. We introduce the K-nearest neighbor attention with relative pose encoding (KNARPE), a novel attention mechanism allowing the pairwise-relative representation to be used by Transformers. By sharing contexts among agents and reusing the unchanged contexts, our approach is as efficient as scene-centric methods, while performing on par with state-of-the-art agent-centric methods.
  arXiv  Detail & Related papers  (2023-10-19T17:59:01Z)
• VIRT: Improving Representation-based Models for Text Matching through Virtual Interaction [50.986371459817256]
  We propose a novel textitVirtual InteRacTion mechanism, termed as VIRT, to enable full and deep interaction modeling in representation-based models. VIRT asks representation-based encoders to conduct virtual interactions to mimic the behaviors as interaction-based models do.
  arXiv  Detail & Related papers  (2021-12-08T09:49:28Z)
• SGCN:Sparse Graph Convolution Network for Pedestrian Trajectory Prediction [64.16212996247943]
  We present a Sparse Graph Convolution Network(SGCN) for pedestrian trajectory prediction. Specifically, the SGCN explicitly models the sparse directed interaction with a sparse directed spatial graph to capture adaptive interaction pedestrians. visualizations indicate that our method can capture adaptive interactions between pedestrians and their effective motion tendencies.
  arXiv  Detail & Related papers  (2021-04-04T03:17:42Z)
• Domain Adaptive Robotic Gesture Recognition with Unsupervised Kinematic-Visual Data Alignment [60.31418655784291]
  We propose a novel unsupervised domain adaptation framework which can simultaneously transfer multi-modality knowledge, i.e., both kinematic and visual data, from simulator to real robot. It remedies the domain gap with enhanced transferable features by using temporal cues in videos, and inherent correlations in multi-modal towards recognizing gesture. Results show that our approach recovers the performance with great improvement gains, up to 12.91% in ACC and 20.16% in F1score without using any annotations in real robot.
  arXiv  Detail & Related papers  (2021-03-06T09:10:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.