AI Paper Atlas

Research map / Video / Video segmentation and tracking

Probabilistic Future Prediction for Video Scene Understanding

Anthony Hu, Fergal Cotter, Nikhil Mohan, Corina Gurau, Alex Kendall

ECCV 2020 · Video › Video segmentation and tracking · approach: Stochastic video prediction · 79 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 probabilistic present/future distributionsTemporal Block model · Urban driving dataM_perception: 13.6% -> 20.0%Improved
add probabilistic modellingRes. 3D Conv. · Urban driving dataM_perception: 6.9% -> 8.1%Improved
add probabilistic modellingConv. GRU · Urban driving dataM_perception: 7.4% -> 9.0%Improved
add probabilistic modellingSep. Inception · Urban driving dataM_perception: 9.6% -> 13.8%Improved
use proposed Temporal Block instead of Sep. Inceptionprobabilistic model · Urban driving dataM_perception: 13.8% -> 20.0%Improved
add future prediction loss to policy training (ablation)driving policy · Urban driving datasteering error: 0.043 -> 0.036Improved
add future prediction loss to policy training (ablation)driving policy · Urban driving dataspeed error: 0.039 -> 0.030Improved
make future prediction probabilisticdriving policy · Urban driving datasteering error: 0.036 -> 0.033Improved
make future prediction probabilisticdriving policy · Urban driving dataspeed error: 0.030 -> 0.026Improved
add global context pooling to Temporal Block (ablation)Temporal Block · Cityscapes (i=5)IoU: 0.453 -> 0.464Improved
add global context pooling to Temporal Block (ablation)Temporal Block · Cityscapes (i=10)IoU: 0.413 -> 0.416Improved
add kt,1,ks convolution to Temporal Block without global context (ablation)Temporal Block · Cityscapes (i=5)IoU: 0.454 -> 0.461Mixed

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