Published on: 2026-07-31Updated on: 2026-08-18
Associated article: https://doi.org/10.26599/COMMTR.2026.9640045 From: Communications in Transportation Research
TWM: Multimodal data generation engine via Traffic World Model
The code is structured into two subdirectories, image_code and video_code, which respectively hold the full implementation of data generation, preprocessing, model training, inference and evaluation for the image and video modalities, with each subdirectory equipped with a separate README file that provides detailed environment setup and usage instructions. The runtime environment for this code is configured with Python 3.10, torch==2.6.0+cu126, and torchvision==0.21.0+cu126
DOI: 10.26599/ETSD.2026.9190031
CSTR: 32009.11.ETSD.2026.9190031
Category: Road transport data (freight), Transport infrastructure data
Data Type: Image/video data
Asia, China, Hangzhou Download ZIP (23.09 MB) Data and Code Disclosure and Sharing Policy
Zhenyu Zhang, Jiaqi Wang, Chunmian Lin, et al. TWM: Multimodal data generation engine via Traffic World Model. ETS-Data, 2026. https://doi.org/10.26599/ETSD.2026.9190031
Zhenyu Zhang, Jiaqi Wang, Chunmian Lin, et al. TWM: Multimodal data generation engine via Traffic World Model. ETS-Data, 2026. https://cstr.cn/32009.11.ETSD.2026.9190031
Zhenyu Zhang, Jiaqi Wang, Chunmian Lin, et al. TWM: Multimodal data generation engine via Traffic World Model. ETS-Data, 2026. https://cstr.cn/32009.11.ETSD.2026.9190031
image_code7.49 MB
video_code31.30 MB
README.md1.14 KB
Replication Explanatory File for Journal-Associated Data.docx42.96 KB
Cite this dataset