AI Paper Atlas

Research map / Video / Video segmentation and tracking

CF-LSTM: Cascaded Feature-Based Long Short-Term Networks for Predicting Pedestrian Trajectory

Yi Xu, Jing Yang, Shaoyi Du

AAAI 2020 · Video › Video segmentation and tracking · approach: Physics-inspired motion prediction · 36 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
integrate hidden states of previous two time steps (cascaded feature) into LSTMvanilla LSTM · ETH/UCY averageADE/FDE: 0.7/1.52 -> 0.43/0.63Improved
replace per-column cascaded integration with MLP integration (P-LSTM) (ablation)CF-LSTM · ETH/UCY averageADE/FDE: 0.43/0.63 -> 0.47/0.68Hurt
add cascaded feature to Social LSTM (CF-S-LSTM) (ablation)S-LSTM · ETH/UCY averageADE/FDE: 0.52/0.88 -> 0.45/0.65Improved
add social interaction pooling to cascaded feature model (CF-S-LSTM vs CF-LSTM) (ablation)CF-LSTM · ETH/UCY averageADE/FDE: 0.43/0.63 -> 0.45/0.65Hurt
CF-LSTM vs SoPhie on ZARA01CF-LSTM · ZARA01ADE: 0.30 -> 0.39Hurt

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