DeCo MAE
This repository contains the official weights and code for the paper "DeCo-MAE".
Model source
- Kind
- Other
- File size
- 1.89 GB
- Version
- vCooldown best
- Updated
- Oct 24, 2026
- Source
- Hugging Face
Source description
DeCo-MAE: Decomposing Semantics for Compositional Zero-Shot Action Recognition
This repository contains the official weights and code for the paper "DeCo-MAE".
🏆 Model Zoo
| Model | Setting | Accuracy | Download |
|---|---|---|---|
| DeCo-MAE (Final SOTA) | Fully Supervised | 85.80% | Download |
| DeCo-MAE (Zero-Shot) | Zero-Shot Split | 78.86% | Download |
🚀 Usage
Please refer to the GitHub Repository for detailed instructions.
Sources
1 source
Sources
1 sourceVerified Oct 24
Download files
Model artifacts
3 artifacts
Model artifacts
3 artifactsSource excerpts
2 excerpts
Source excerpts
2 excerpts--- license: mit tags: - video-classification - zero-shot-learning - action-recognition - videomae pipeline_tag: video-classification --- # DeCo-MAE: Decomposing Semantics for Compositional Zero-Shot Action Recognition This repository contains the **official weights** and code for the paper **"DeCo-MAE"**. ## 🏆 Model Zoo | Model | Setting | Accuracy | Download | | :--- | :--- | :--- | :--- | | **DeCo-MAE (Final SOTA)** | Fully Supervised | **85.80%** | [Download](./final_sota_best.pth) | | **DeCo-MAE (Zero-Shot)** | Zero-Shot Split | **78.86%** | [Download](./zeroshot_model.pth) | ## 🚀 Usage Please refer to the [GitHub Repository](https://github.com/SuhangXia/DeCo-MAE) for detailed instructions.
Source context: 0 downloads · 0 likes · Pipeline video-classification · Repo LancetRobotics/DeCo-MAE
