The codebase was designed to help researchers and practitioners quickly reproduce FAIR’s results and leverage robust pre-trained backbones for downstream tasks. It also integrates Gradient Blending, an audio-visual modeling method that fuses modalities effectively (available in the Caffe2 implementation). Although VMZ is now archived and no longer actively maintained, it remains a valuable reference for understanding early large-scale video model training, transfer learning, and multimodal integration strategies that influenced modern architectures like SlowFast and X3D.
Features
- Implements R(2+1)D and MCx models for efficient spatiotemporal video representation learning
- Enables reproducibility of FAIR’s published video understanding research
- Built with both Caffe2 and PyTorch backends for flexibility
- Supports Gradient Blending for audio-visual fusion (Caffe2 only)
- Provides pre-trained models on IG-65M, one of the largest weakly-supervised video datasets
- Includes CSN (Channel-Separated Networks) for computationally efficient video recognition
License
Apache License V2.0Follow VMZ (Video Model Zoo)
You Might Also Like
Gen AI apps are built with MongoDB Atlas
MongoDB Atlas is the developer-friendly database used to build, scale, and run gen AI and LLM-powered apps—without needing a separate vector database. Atlas offers built-in vector search, global availability across 115+ regions, and flexible document modeling. Start building AI apps faster, all in one place.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of VMZ (Video Model Zoo)!