Skip to content
AI News HubLIVE
Original source2 min read

MV-JEPA: Post-Training Video Encoders for Cross-View Understanding

Summary

MV-JEPA introduces multi-view predictive post-training that strengthens cross-view instance and temporal correspondence in JEPA video encoders with only 9,000 updates on a single GPU, while preserving single-view inference and most pretrained capabilities.

SourcearXiv Computer VisionAuthor: Yangchen Zhao, Ali Payani, Caiwen Ding
MV-JEPA: Post-Training Video Encoders for Cross-View Understanding
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 18 Nov 2026]

Title:MV-JEPA: Post-Training Video Encoders for Cross-View Understanding

View a PDF of the paper titled MV-JEPA: Post-Training Video Encoders for Cross-View Understanding, by Yangchen Zhao and 2 other authors

View PDF HTML (experimental)

Abstract:JEPA-based video encoders learn strong representations for video and image understanding through prediction in latent space. However, their standard pretraining predicts features within individual images or video clips, without explicitly exploiting paired camera views of the same object or moment. Consequently, the learned representations may not reliably support matching across different camera viewpoints. To solve this problem, we introduce multi-view predictive post-training to strengthen cross-view instance and temporal correspondence while retaining independent single-view inference. A shared encoder processes masked context views independently, and a training-time predictor jointly predicts latent tokens for masked context regions and a fully held-out view. We alternate cross-view prediction with single-view masked prediction on general image and video data to help retain the encoder's pretrained capabilities. After only 9,000 post-training updates on a single GPU, MV-JEPA improves cross-view instance retrieval and coarse cross-camera moment retrieval on various datasets, with further gains in zero-shot action-phase retrieval and frozen-feature classification on AE2. Frozen-probe evaluations further indicate that post-training largely preserves motion recognition, image recognition, and dense semantic segmentation performance on the evaluated benchmarks. Together, these results demonstrate that multi-view predictive post-training can strengthen instance and coarse temporal correspondence in JEPA video encoders without modifying the encoder architecture or single-view inference interface.

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2611.25172 [cs.CV]

(or arXiv:2611.25172v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2611.25172

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Yangchen Zhao [view email] [v1] Wed, 18 Nov 2026 20:58:38 UTC (1,551 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled MV-JEPA: Post-Training Video Encoders for Cross-View Understanding, by Yangchen Zhao and 2 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CV

new | recent | 2026-11

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Proposes multi-view predictive post-training to enhance cross-view instance and temporal correspondence
  • Requires only 9,000 updates on a single GPU without modifying encoder architecture
  • Improves cross-view retrieval and zero-shot action-phase retrieval
  • Frozen-probe evaluations show preserved motion, image recognition, and segmentation performance

Highlights and analysis are generated automatically and may contain errors. Check the original source.

MV-JEPA: Post-Training Video Encoders for Cross-View Understanding | AI News Hub