This paper introduces Content-aware Token Sharing (CTS), a token reducti...
Unified panoptic segmentation methods are achieving state-of-the-art res...
Learning anticipation in Multi-Agent Reinforcement Learning (MARL) is a
...
Learning anticipation is a reasoning paradigm in multi-agent reinforceme...
We consider the problem of intelligently navigating through complex traf...
In this work, we introduce the new scene understanding task of Part-awar...
In this technical report, we present two novel datasets for image scene
...
In this work, we present an end-to-end network for fast panoptic
segment...
In this work, we propose a single deep neural network for panoptic
segme...
We present an end-to-end method for the task of panoptic segmentation. T...