mlsanityData to 7 Oct 2026

Context-free Self-Conditioned GAN for Trajectory Forecasting

arXiv 2603.08658 ↗First posted 9 Mar 2026cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we present a context-free unsupervised approach based on a self-conditioned GAN to learn different modes from 2D trajectories. Our intuition is that each mode indicates a different behavioral moving pattern in the discriminator's feature space. We apply this approach to the problem of trajectory forecasting. We present three different training settings based on self-conditioned GAN, which produce better forecasters. We test our method in two data sets: human motion and road agents. Experimental results show that our approach outperforms previous context-free methods in the least representative supervised labels while performing well in the remaining labels. In addition, our approach outperforms globally in human motion, while performing well in road agents.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 42 references that are in the map. First posted on arXiv 9 Mar 2026.

Builds on

26 of 42 references.

References · 26

  1. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  2. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  3. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  4. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  5. 2014Conditional Generative Adversarial Netscited by 2,152
  6. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  7. 2019Argoverse: 3D Tracking and Forecasting with Rich Mapscited by 728
  8. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
  9. 2018SoPhie: An Attentive GAN for Predicting Paths Compliant to Social and Physical Constraintscited by 296
  10. 2019Human Motion Trajectory Prediction: A Surveycited by 231
  11. 2019Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networkscited by 228
  12. 2017VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learningcited by 199
14 more
  1. 2019Mode Seeking Generative Adversarial Networks for Diverse Image Synthesiscited by 138
  2. 2020Human Trajectory Forecasting in Crowds: A Deep Learning Perspectivecited by 128
  3. 2018Reconstruction Network for Video Captioningcited by 98
  4. 2019What the Constant Velocity Model Can Teach Us About Pedestrian Motion Predictioncited by 78
  5. 2019Conditional Generative Neural System for Probabilistic Trajectory Predictioncited by 76
  6. 2018ClusterGAN : Latent Space Clustering in Generative Adversarial Networkscited by 75
  7. 2020Goal-GAN: Multimodal Trajectory Prediction Based on Goal Position Estimationcited by 57
  8. 2020Diverse Image Generation via Self-Conditioned GANscited by 54
  9. 2017Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Stepcited by 45
  10. 2019TH"OR: Human-Robot Navigation Data Collection and Accurate Motion Trajectories Datasetcited by 36
  11. 2019Forecasting Trajectory and Behavior of Road-Agents Using Spectral Clustering in Graph-LSTMscited by 34
  12. 2020RNN-based Pedestrian Crossing Prediction using Activity and Pose-related Featurescited by 21
  13. 2018A survey on trajectory clustering analysiscited by 12
  14. 2020Generating Reliable and Efficient Predictions of Human Motion: A Promising Encounter between Physics and Neural Networkscited by 6

Built on by

Not cited yet.