#

vjepa

Here are 10 public repositories matching this topic...

valthera / openvalthera

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

Updated Oct 19, 2025
Python

SuryaAnything / V-DeClip

Masked Multi-Component Gated Decomposition Architecture

deep-learning transformers recall temporal self-supervised-learning masked video-retrieval msrvtt msr-vtt contrastive-learning temporal-feature-alignment openclip vjepa vjepa2 video-retrieval-pipeline text-video-alignment

Updated Jan 13, 2026
Python

uriahje9503 / MotionMatch

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

game python sample real-time video ai computer-vision deep-learning robotics embeddings yolo motion-capture action-recognition replicated similarity-search video-analysis fastapi vjepa

Updated Mar 25, 2026
Python

Tsunami-kun / vjepa2.1-pca

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

visualization open-source pca video-understanding self-supervised-learning world-models dense-features world-model vjepa vjepa2 vjepa21 vjepa2-1

Updated Mar 19, 2026
Python

iamvibhorsingh / MotionMatch

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

python machine-learning video docker-compose container embeddings yolo action-recognition similarity-search fastapi vector-search milvus vjepa v-jepa2

Updated Nov 4, 2025
Python

RobvanGastel / adapt-vjepa-world-model

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

self-supervised-learning world-model vjepa

Updated Feb 27, 2026
Jupyter Notebook

emapco / ai-powered-media-gallery

Locally-Hosted Media Gallery App with AI Similarity Search

redis docker-compose nextjs transformers embeddings fastapi vector-search video-embedding vjepa

Updated Oct 14, 2025
TypeScript

DanielGillespie278 / gazefield

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

computer-vision attention video-understanding spatial-attention predictive-coding vjepa

Updated Feb 25, 2026
Python

Ahmedmohamadsalah / V-DeClip

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

deep-learning transformers recall temporal self-supervised-learning masked video-retrieval msrvtt msr-vtt contrastive-learning temporal-feature-alignment openclip vjepa vjepa2 video-retrieval-pipeline text-video-alignment

Updated Mar 25, 2026
Python

bnkf1156f / EDA_intra_class_variation

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

clustering yolo data-quality-checks visualize-data annotation-tool dbscan-clustering hdbscan image-embeddings dinov2 siglip vjepa evaluate-annotations

Updated Mar 25, 2026
Python

Improve this page

Add a description, image, and links to the vjepa topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the vjepa topic, visit your repo's landing page and select "manage topics."