AI Paper Atlas

Research map / Video / Video segmentation and tracking

Conditional Temporal Variational AutoEncoder for Action Video Prediction

Xiaogang Xu, Yi Wang, Liwei Wang, Bei Yu, Jiaya Jia

IJCV 2023 · Video › Video segmentation and tracking · approach: Stochastic video prediction · 9 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 action labels to ACT-VAE (ablation)ACT-VAE · Penn-action keypointsL2: 29.59 -> 28.32Improved
add action labels to ACT-VAE (ablation)ACT-VAE · Human3.6M keypointsL2: 30.88 -> 30.41Improved
condition latent z_t on previous latents z_<t (ablation)ACT-VAE · Penn-action keypointsL2: 30.31 -> 29.59Improved
condition latent z_t on previous latents z_<t (ablation)ACT-VAE · Penn-action keypointsStd: 1.462 -> 1.584Improved
add temporal coherence over latents (ablation)ACT-VAE · Penn-action keypointsL2: 34.74 -> 30.31Improved
add temporal coherence over latents (ablation)ACT-VAE · Penn-action keypointsStd: 0.732 -> 1.462Improved
add foreground-background mask in P2I (ablation)P2I network · Penn-action videoFVD: 1455.2 -> 1092.8Improved
add action conditional BN in P2I (ablation)P2I network · Penn-action videoFVD: 1377.2 -> 1092.8Improved
add action conditional BN in P2I (ablation)P2I network · Penn-action videoRecognition accuracy: 68.83 -> 70.04Improved
lower lambda_1 from 200 to 20 (ablation)ACT-VAE · Penn-action keypointsL2: 28.32 -> 31.84Hurt
raise lambda_2 from 0.002 to 0.02 (ablation)ACT-VAE · Penn-action keypointsL2: 28.32 -> 31.99Hurt
use ACT-VAE pose generator in place of VAE pose generatorP2I framework · Penn-action videoFVD: 1318.9 -> 1092.8Improved

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