MoVi: Real-Time Large Multimodal Model-Driven Interactive Video Analytics on Mobile Devices

IEEE INFOCOM 2026 - IEEE Conference on Computer Communications 2026

View at publisher
Authors: Zekai Li, Xiaoyi Fan, Xiping Hu, Yifei Zhu
DOI: 10.1109/infocom59046.2026.11571484
Cited by: 1
References: 29

Fields of Study & Subjects

Multimodal Machine Learning Applications Human Pose and Action Recognition Human Motion and Animation

Publication details

Journal / source
IEEE INFOCOM 2026 - IEEE Conference on Computer Communications
Publisher
IEEE
Pages
1–10
Publication date
18 May 2026