Research map / Video / Video generation
Generating Videos of Zero-Shot Compositions of Actions and Objects
Megha Nawhal, Mengyao Zhai, Andreas Lehrmann, Leonid Sigal, Greg Mori
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 |
|---|---|---|---|
| add gradient discriminator to frame discriminator (no relational) (ablation) | HOI-GAN (masks) · EPIC GS1 | I-score: 1.4 -> 2.3 | Improved |
| add video discriminator to frame+gradient (no relational) (ablation) | HOI-GAN (masks) · EPIC GS1 | I-score: 2.3 -> 2.8 | Improved |
| add relational discriminator to frame discriminator only (ablation) | HOI-GAN (masks) · EPIC GS1 | I-score: 1.4 -> 2.4 | Improved |
| add relational discriminator to F+G (ablation) | HOI-GAN (masks) · EPIC GS1 | I-score: 2.3 -> 5.9 | Improved |
| add relational discriminator to F+G+V (ablation) | HOI-GAN (masks) · SS GS1 | I-score: 3.3 -> 8.6 | Improved |
| add relational discriminator to F+G+V (ablation) | HOI-GAN (masks) · EPIC GS1 | S-score: 21.2 -> 13.2 | Improved |
| add video discriminator to F+G with relational discriminator (ablation) | HOI-GAN (masks) · SS GS2 | I-score: 5.4 -> 7.1 | Improved |
| use word embeddings instead of one-hot labels as conditions (ablation) | HOI-GAN (masks) · EPIC GS1 | I-score: 4.3 -> 6.2 | Improved |
| use segmentation masks instead of bounding boxes in context frame (ablation) | HOI-GAN (masks) · EPIC GS1 | I-score: 6.0 -> 6.2 | Improved |
| use segmentation masks instead of bounding boxes in context frame (ablation) | HOI-GAN (masks) · EPIC GS2 | I-score: 5.7 -> 5.2 | Mixed |
| replace MoCoGAN with HOI-GAN | MoCoGAN · SS GS1 | FID: 11.4 -> 7.2 | Improved |
| replace MoCoGAN with HOI-GAN | MoCoGAN · EPIC | classification accuracy: 11.0 -> 35.4 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MoCoGAN — MoCoGAN: Decomposing Motion and Content for Video Generation (CVPR 2018) · better on 12 of 12 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Generating Human Action Videos by Coupling 3D Game Engines and Probabilistic Graphical Models (IJCV 2019 · similarity 0.87)
- ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation (ICCV 2023 · similarity 0.87)
- Procedural Generation of Videos to Train Deep Action Recognition Networks (CVPR 2017 · similarity 0.87)
- HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation (CVPR 2025 · similarity 0.86)
- Deep Video Generation, Prediction and Completion of Human Action Sequences (ECCV 2018 · similarity 0.86)
- Compositional Video Synthesis with Action Graphs (ICML 2021 · similarity 0.86)
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.
