Conference

EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs
Transferring and integrating knowledge across first-person (egocentric) and third-person (exocentric) viewpoints is intrinsic to human …
PDF Cite Code DOI
EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs
Unveiling Egocentric Reasoning with Spatio-Temporal CoT
Egocentric video reasoning focuses on the unseen, egocentric agent who shapes the scene, demanding inference of hidden intentions and …
PDF Cite Code
Unveiling Egocentric Reasoning with Spatio-Temporal CoT
Vinci: A Real-time Smart Assistant based on Egocentric Vision-language Model for Portable Devices
We present Vinci, a vision-language system designed to provide real-time, comprehensive AI assistance on portable devices. At its core, …
PDF Cite Code DOI
Vinci: A Real-time Smart Assistant based on Egocentric Vision-language Model for Portable Devices