AI Paper Atlas

Research map / Time series / Long-term forecasting

MX-LSTM: Mixing Tracklets and Vislets to Jointly Forecast Trajectories and Head Poses

Irtiza Hasan, Francesco Setti, Theodore Tsesmelis, Alessio Del Bue, Fabio Galasso, Marco Cristani

CVPR 2018 · Time series › Long-term forecasting · approach: Lightweight long-term forecasters · 147 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
Add social pooling to the individual tracklet-and-vislet model (ablation)MX-LSTM · Zara01, Zara02, UCY, TownCentreMAD: 0.63 -> 0.59; 0.72 -> 0.35; 0.53 -> 0.49; 2.09 -> 1.15Improved
Add social pooling to the individual tracklet-and-vislet model (ablation)MX-LSTM · Zara01, Zara02, UCY, TownCentreFAD: 1.37 -> 1.31; 1.56 -> 0.79; 1.16 -> 1.12; 4.00 -> 2.30Improved
Use view-frustum social pooling instead of unrestricted social pooling (ablation)MX-LSTM · Zara01, Zara02, UCY, TownCentreMAD: 0.63 -> 0.59; 0.36 -> 0.35; 0.51 -> 0.49; 1.70 -> 1.15Improved
Use view-frustum social pooling instead of unrestricted social pooling (ablation)MX-LSTM · Zara01, Zara02, UCY, TownCentreFAD: 1.40 -> 1.31; 0.84 -> 0.79; 1.15 -> 1.12; 3.40 -> 2.30Improved
Add cross-stream covariance terms by using full rather than block-diagonal covariance (ablation)MX-LSTM · Zara01, Zara02, UCY, TownCentreMAD: 0.60 -> 0.59; 0.41 -> 0.35; 0.54 -> 0.49; 1.40 -> 1.15Mixed
Add cross-stream covariance terms by using full rather than block-diagonal covariance (ablation)MX-LSTM · Zara01, Zara02, UCY, TownCentreFAD: 1.51 -> 1.31; 1.00 -> 0.79; 1.23 -> 1.12; 2.90 -> 2.30Improved

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