Task
Video Classification
C
nvidia/Cosmos-Embed1-448p-anomaly-detection
Video Classification·nvidia· 4.2K· 11
Cosmos-Embed1 is a joint video-text embedder tailored for physical AI. It can be used for text-to-video retrieval, inverse video search, semantic deduplication, zero-shot and k-nearest-neighbors (kNN) classification, and as a base model for video curation tasks. It has state-of-the-art (SOTA) performance on autonomous vehicle (AV) and robotics datasets, while maintaining competitive performance in
# pull & run locally
pip install mlforge-sdk && mlforge pull nvidia/Cosmos-Embed1-448p-anomaly-detection
pip install mlforge-sdk && mlforge pull nvidia/Cosmos-Embed1-448p-anomaly-detection
Model details
Provider
nvidia
Framework
cosmos
Parameters
1.2B
Size
8.9 GB
License
other
Downloads
4.2K
Likes
11
Paper
arXiv:2505.19877
Updated
2026-05-19
About nvidia/Cosmos-Embed1-448p-anomaly-detection
Cosmos-Embed1 is a joint video-text embedder tailored for physical AI. It can be used for text-to-video retrieval, inverse video search, semantic deduplication, zero-shot and k-nearest-neighbors (kNN) classification, and as a base model for video curation tasks. It has state-of-the-art (SOTA) performance on autonomous vehicle (AV) and robotics datasets, while maintaining competitive performance in general domains. A fine-tuned variant is also provided for video anomaly detection and classification. This model is ready for commercial use.