AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Hierarchical Multi-Supervision Multi-Interaction Graph Attention Network for Multi-Camera Pedestrian Trajectory Prediction

Guoliang Zhao, Yuxun Zhou, Zhanbo Xu, Yadong Zhou, Jiang Wu

AAAI 2022 · Graph learning › Knowledge and temporal graphs · approach: Social and behavior graphs · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use the joint destination-and-trajectory framework instead of the segregated LSTM+FC* approachMCTP on mcScenes · mcScenesminADE20: 0.066 -> 0.049Improved
Use HM3GAT rather than MC-STGATMCTP on mcScenes · mcScenesminADE20: 0.056 -> 0.049Improved
Add the latent goal decoder (ablation)HM3GAT on mcScenes · mcScenesADE: 0.050 -> 0.049Improved
Add the latent goal decoder (ablation)HM3GAT on mcScenes · mcScenesFDE: 0.095 -> 0.095No clear effect
Add the multiple-interaction module (ablation)HM3GAT on mcScenes · mcScenesADE: 0.054 -> 0.049Improved
Add the multiple-interaction module (ablation)HM3GAT on mcScenes · mcScenesFDE: 0.100 -> 0.095Improved
Add hierarchical and multiple-interaction modules (ablation)HM3GAT on mcScenes · mcScenesADE: 0.056 -> 0.049Improved
Add hierarchical and multiple-interaction modules (ablation)HM3GAT on mcScenes · mcScenesFDE: 0.108 -> 0.095Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy