Open-source vision stack with stereo camera hardware, GPU processing, and AI agent for training video classifiers.

Masked Multi-Component Gated Decomposition Architecture

🎥 Discover similar motion dynamics in videos with MotionMatch, a physics-based search engine leveraging Meta's V-JEPA 2 for efficient retrieval.

vjepa / vjepa2 / vjepa2.1 PCA visualization utility for dense features and world model inspection.

Can the V-JEPA2 model be used as a world model?

A physics-based video search engine using Meta's V-JEPA 2 world model to find videos with similar motion dynamics.

Locally-Hosted Media Gallery App with AI Similarity Search

GranularVAR: Multi-scale video understanding with augmentation-graded contrastive learning and calibrated uncertainty. V-JEPA 2 encoder + granularity-conditioned decoder. GWU MS Data Science Capstone, Spring 2026.

Patch-level predictive surprise from video foundation model embeddings. The embedding delta is the attention signal.

🎥 Enhance video–text alignment using V-DeClip's advanced MCGD architecture for precise, semantically decomposed video embeddings.

Assess Data Quality Before Annotation or Labelled Data Quality after Annotation (Txt files/Yolo Format). Visualise the patterns covered by each class/activity.