Research map / Video / Video generation
Deep Video Generation, Prediction and Completion of Human Action Sequences
Haoye Cai, Chunyan Bai, Yu-Wing Tai, Chi-Keung Tang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use pose-based two-stage generation instead of pixel-space VGAN | video generation · Human3.6m generation | frame Inception Score: 1.53 -> 3.99 | Improved |
| use pose-based two-stage generation instead of pixel-space VGAN | video generation · Human3.6m generation | video Inception Score: 1.40 -> 3.99 | Improved |
| latent optimization over pose generator instead of PoseVAE | video prediction · Human3.6m prediction | frame Inception Score: 1.91 -> 3.87 | Improved |
| latent optimization over pose generator instead of PredNet | video prediction · Human3.6m prediction | video Inception Score: 2.94 -> 4.09 | Improved |
| latent optimization over pose generator instead of MS-GAN | video prediction · Human3.6m prediction | frame Inception Score: 1.48 -> 3.87 | Improved |
| latent optimization with pose generator instead of cond-VGAN | video completion · Human3.6m completion | frame Inception Score: 2.35 -> 3.91 | Improved |
| latent optimization with pose generator instead of cond-VGAN | video completion · Human3.6m completion | video Inception Score: 2.00 -> 4.10 | Improved |
| use pose-based method instead of PredNet and MS-GAN for long prediction | video prediction · Human3.6m prediction | frame-by-frame Inception Score | Improved |
| use pose-based method for prediction | video prediction · Human3.6m prediction | frame-by-frame PSNR and SSIM | Improved |
Closest papers by meaning
- Procedural Generation of Videos to Train Deep Action Recognition Networks (CVPR 2017 · similarity 0.90)
- HumanDreamer: Generating Controllable Human-Motion Videos via Decoupled Generation (CVPR 2025 · similarity 0.89)
- Learning Diverse Stochastic Human-Action Generators by Learning Smooth Latent Transitions (AAAI 2020 · similarity 0.89)
- Generating Human Action Videos by Coupling 3D Game Engines and Probabilistic Graphical Models (IJCV 2019 · similarity 0.89)
- HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation (NeurIPS 2024 · similarity 0.87)
- OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation (CVPR 2025 · similarity 0.87)
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.
