The task of moment localization is to localize a temporal moment in an
u...
Fusing LiDAR and camera information is essential for achieving accurate ...
In this technical report, we introduce our submission to the Waymo 3D
De...
3D dense captioning is a recently-proposed novel task, where point cloud...
Given a text description, Temporal Language Grounding (TLG) aims to loca...
Blind face inpainting refers to the task of reconstructing visual conten...
Automatically generating sentences to describe events and temporally
loc...
Deep neural networks (DNNs) are known for their vulnerability to adversa...
This paper describes our solution for the 2^nd YouTube-8M video
understa...
This paper introduces the system we developed for the Google Cloud &
You...