English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Human trajectory forecasting in crowds presents the challenges of modellingsocial interactions and outputting collision-free multimodal distribution.Following the success of Social Generative Adversarial Networks (SGAN), recentworks propose various GAN-based designs to better model human motion in crowds.Despite superior performance in reducing distance-based metrics, currentnetworks fail to output socially acceptable trajectories, as evidenced by highcollisions in model predictions. To counter this, we introduce SGANv2: animproved safety-compliant SGAN architecture equipped with spatio-temporalinteraction modelling and a transformer-based discriminator. Thespatio-temporal modelling ability helps to learn the human social interactionsbetter while the transformer-based discriminator design improves temporalsequence modelling. Additionally, SGANv2 utilizes the learned discriminatoreven at test-time via a collaborative sampling strategy that not only refinesthe colliding trajectories but also prevents mode collapse, a common phenomenonin GAN training. Through extensive experimentation on multiple real-world andsynthetic datasets, we demonstrate the efficacy of SGANv2 to providesocially-compliant multimodal trajectories.

Safety-compliant Generative Adversarial Networks for Human Trajectory Forecasting