Self-supervised audio-visual model MJEPA accepted at ECCV 2026

Arxiv CS.CV (computer vision)

Self-supervised learning model MJEPA for audio-visual representation learning accepted at ECCV 2026. The architecture jointly learns from video's co-occurring audio and visual streams.

mjepa

See 1 more source

RT @RevantTeotia: 🎉 Our paper MJEPA has been accepted at #ECCV2026 !! Huge thanks to my awesome...3 hours agoYann LeCun

Arxiv CS.CV (computer vision)·Revant TeotiaAdrien BardesMichael RabbatSumit ChopraMatthew J. MuckleyNicolas Ballas

Jun 25, 4:00 AM