TCA-T2M

KO | EN

gitlite — search

#python #hacktoberfest #react #ai #go #machine-learning #docker #java #windows #cli #kubernetes #security #mcp #open-source

(★ 16)

No description available.

TCA-T2M Latest Version Download

Download Latest Version (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

## [Temporal Consistency-Aware Text-to-Motion Generation](https://link.springer.com/article/10.1007/s44267-026-00110-8), [arXiv](https://arxiv.org/html/2602.18057v1)

This repository offers the official Pytorch code for this paper.
If you have any questions, feel free to contact Hongsong Wang (hongsongwang@seu.edu.cn).

The project with motion generation visualizations are [https://giat995.github.io/video_vis/](https://giat995.github.io/video_vis/)

##  Get You Ready
  
### 1. Conda Environment
```
conda env create -f environment.yml
conda activate momask
pip install git+https://github.com/openai/CLIP.git
```
We test our code on Python 3.7.13 and PyTorch 1.7.1

#### Alternative: Pip Installation

We provide an alternative pip installation in case you encounter difficulties setting up the conda environment.

```
pip install -r requirements.txt
```
We test this installation on Python 3.10

### 2. Models and Dependencies

#### Download Pre-trained Models
```
bash prepare/download_models.sh
```

#### Download Evaluation Models and Gloves
For evaluation only.
```
bash prepare/download_evaluator.sh
bash prepare/download_glove.sh
```

#### Troubleshooting
To address the download error related to gdown: "Cannot retrieve the public link of the file. You may need to change the permission to 'Anyone with the link', or have had many accesses". A potential solution is to run `pip install --upgrade --no-cache-dir gdown`, as suggested on https://github.com/wkentaro/gdown/issues/43. This should help resolve the issue.

#### (Optional) Download Manually
Visit [[Google Drive]](https://drive.google.com/drive/folders/1sHajltuE2xgHh91H9pFpMAYAkHaX9o57?usp=drive_link) to download the models and evaluators mannually.

### 3. Get Data

You have two options here:
* **Skip getting data**, if you just want to generate motions using *own* descriptions.
* **Get full data**, if you want to *re-train* and *evaluate* the model.

**(a). Full data (text + motion)**

**HumanML3D** - Follow the instruction in [HumanML3D](https://github.com/EricGuo5513/HumanML3D.git), then copy the result dataset to our repository:
```
cp -r ../HumanML3D/HumanML3D ./dataset/HumanML3D
```
**KIT**-Download from [HumanML3D](https://github.com/EricGuo5513/HumanML3D.git), then place result in `./dataset/KIT-ML`

**If you find this code useful for your research, please consider citing our paper**:
```

article{wang2026temporalconsistency,
      title={Temporal Consistency-Aware Text-to-Motion Generation}, 
      author={Hongsong Wang and Wenjing Yan and Qiuxia Lai and Xin Geng},
      year={2026},
      journal={Visual Intelligence},
      SN= {2731-9008},
      doi={10.1007/s44267-026-00110-8}
}

TCA-T2M

TCA-T2M Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

TCA-T2M

TCA-T2M Latest Version Download

Today's picks

Was this content helpful?

Recent Feedback

Download README