AI Paper Atlas

Research map / Video / Video segmentation and tracking

The Pose Knows: Video Forecasting by Generating Pose Futures

Jacob Walker, Kenneth Marino, Abhinav Gupta, Martial Hebert

ICCV 2017 · Video › Video segmentation and tracking · approach: Stochastic video prediction · 343 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 pose-VAE plus pose-conditioned GAN instead of direct pixel Video-GANvideo forecasting on UCF101 · UCF101Inception score: 1.74 -> 3.14Improved
use pose-VAE plus pose-conditioned GAN instead of direct pixel Video-GANvideo forecasting on UCF101 · UCF101MMD: 0.139 -> 0.022Improved
add the VAE to the future decoder (versus deterministic ERD and SRNN) (ablation)Pose-VAE · UCF101 pose forecastingminimum Euclidean distance over n samplesImproved
make deterministic baselines stochastic using Gaussian noise with variance from test data (ablation)ERD and SRNN · UCF101 pose forecastingminimum Euclidean distance over n samplesHurt
use recurrent Pose-VAE instead of feed-forward VAE (ablation)Pose-VAE · UCF101 pose forecastingminimum Euclidean distance over n samplesImproved
increase number of samples drawn from Pose-VAEPose-VAE · UCF101 pose forecastingminimum Euclidean distanceImproved

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