AI Paper Atlas

Research map / Video / Video segmentation and tracking

S2F2: Single-Stage Flow Forecasting for Future Multiple Trajectories Prediction

Yu-Wen Chen, Hsuan-Kung Yang, Chu-Chi Chiu, Chun-Yi Lee

ECCV 2022 · Video › Video segmentation and tracking · approach: Physics-inspired motion prediction · 6 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
replace two-stage STED with single-stage S2F2trajectory forecasting · StaticMOT val forecasting (3 future frames)FDE: 23.761 -> 16.228Improved
replace two-stage STED with single-stage S2F2trajectory forecasting · StaticMOT val forecasting (3 future frames)latency (ms): 623.480 -> 13.788Improved
replace constant velocity with S2F2trajectory forecasting · StaticMOT val forecasting (3 future frames)ADE: 14.481 -> 12.275Improved
add SSIM loss (ablation)S2F2 · MOT17 val (trained on MOT17) ablationFDE: 43.021 -> 39.891Improved
add SSIM loss (ablation)S2F2 · MOT17 val (trained on MOT17) ablationMOTA: 67.0 -> 67.7Improved
add past flow decoder (ablation)S2F2 · MOT17 val (trained on MOT17) ablationFDE: 39.891 -> 43.097Hurt
add past flow decoder with detached past GRU encoder (ablation)S2F2 · MOT17 val (trained on MOT17) ablationFDE: 39.891 -> 46.869Hurt
add forecasting refinement to online association (ablation)S2F2 · MOT17MOTA: 67.6 -> 67.7Improved
add forecasting refinement to online association (ablation)S2F2 · MOT17FDE: 40.014 -> 39.891Improved
add forecasting refinement to online association (ablation)S2F2 · StaticMOTMOTA: 73.3 -> 73.6Improved
replace FairMOT association with ByteTrack (ablation)S2F2 · MOT17MOTA: 67.7 -> 66.2Hurt
replace FairMOT association with ByteTrack (ablation)S2F2 · StaticMOTMOTA: 73.6 -> 73.4Hurt

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