AI Paper Atlas

Research map / Video / Video segmentation and tracking

Multi-Stream Representation Learning for Pedestrian Trajectory Prediction

Yuxuan Wu, Le Wang, Sanping Zhou, Jinghai Duan, Gang Hua, Wei Tang

AAAI 2023 · Video › Video segmentation and tracking · approach: Spatio-temporal predictive modeling · 61 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 three separate temporal, spatial, and cross branches instead of joint flattened self-attention (ablation)MSRL · ETH-UCY AVGADE: 0.26 -> 0.21Improved
Use three separate temporal, spatial, and cross branches instead of joint flattened self-attention (ablation)MSRL · ETH-UCY AVGFDE: 0.43 -> 0.34Improved
Add a spatial branch to the temporal branch (ablation)MSRL · ETH-UCY AVGADE: 0.24 -> 0.22Improved
Add a cross-correlation branch to temporal and spatial branches (ablation)MSRL · ETH-UCY AVGADE: 0.22 -> 0.21Improved
Add gated feature fusion (ablation)MSRL · ETH-UCY AVGADE: 0.21 -> 0.20Improved
Add sparse attention gates to spatial and cross branches (ablation)MSRL · ETH-UCY AVGADE: 0.20 -> 0.19Improved
Replace the multi-stream module with a temporal transformer followed by a spatial transformer (ablation)MSRL · ETH-UCY AVGADE: 0.21 -> 0.22Hurt
Combine spatial and cross interactions in one branch rather than separating them (ablation)MSRL · ETH-UCY AVGADE: 0.21 -> 0.21No clear effect
Use MSRL rather than LB-EBMETH-UCY trajectory prediction · ETH-UCY AVGADE: 0.21 -> 0.19Improved
Use MSRL rather than MemoNetSDD trajectory prediction · SDDADE: 8.56 -> 8.22Improved
Use MSRL rather than MemoNetSDD trajectory prediction · SDDFDE: 12.66 -> 13.39Hurt

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