Abstract: Weakly supervised temporal action localization aims at learning the instance-level action pattern from the video-level labels, where a significant challenge is action-context confusion. To ...

Abstract: In this paper, we propose a novel method to localize (or track) a foreground object and segment the foreground object from the surrounding background with occlusions for a moving camera. We ...

1 MoE Key Lab of Artificial Intelligence, Shanghai Jiao Tong University Please specify the checkpoint save path in --checkpoint and dataset path in--dataset_dir. How to test on my data? We also ...

Localization of a robotic system within a previously mapped environment is important for reducing estimation drift and for reusing previously built maps. Existing techniques for geometry-based ...

We propose a method for evaluating the localization accuracy of an indoor navigation system in arbitrarily large environments. Instead of using externally mounted sensors, as required by most ...

Get article recommendations from ACS based on references in your Mendeley library. Pair your accounts.