AC-VRNN: Attentive Conditional-VRNN for multi-future trajectory prediction

• Published in: Computer vision and image understanding Vol. 210; p. 103245
• Main Authors: Bertugli, Alessia, Calderara, Simone, Coscia, Pasquale, Ballan, Lamberto, Cucchiara, Rita
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.09.2021
• Subjects: Graph attention networks; Multi-future prediction; Time series; Trajectory forecasting; Variational recurrent neural networks; Trajectory forecasting; Graph attention networks; Variational recurrent neural networks; Multi-future prediction; Time series
• ISSN: 1077-3142; 1090-235X
• DOI: 10.1016/j.cviu.2021.103245

Anticipating human motion in crowded scenarios is essential for developing intelligent transportation systems, social-aware robots and advanced video surveillance applications. A key component of this task is represented by the inherently multi-modal nature of human paths which makes socially accept...