7 accepted papers
3D visual grounding aims to locate the referred target object in 3D point cloud scenes according to a free-form language description. Previous methods mostly follow a two-stage paradigm, i.e., language-irrelevant detection and cross-modal matching, which is limited by the isolated architecture. In s…
The Frenét frame is commonly used in motion planning for its superiority of reshaping nonconvex curving boundaries and decoupling lateral and longitudinal behaviors. Nevertheless, such frame is not friendly for describing vehicle-related characteristics such as body shape and classical dynamic model
Video instance segmentation (VIS) is the task that requires simultaneously classifying, segmenting and tracking object instances of interest in video. Recent methods typically develop sophisticated pipelines to tackle this task. Here, we propose a new video instance segmentation framework built upon…
Motion prediction of multiple agents in a dynamic scene is a crucial component in many real applications, including intelligent monitoring and autonomous driving. Due to the complex interactions among the agents and their interactions with the surrounding scene, accurate trajectory prediction is sti…
Accurate trajectory prediction plays a key role in robot navigation. It is beneficial for planning a collision-free and appropriate path for the autonomous robots, especially in crowded scenes. However, it is a particularly challenging task because there are complex and subtle interactions among ped
Very recently, a variety of vision transformer architectures for dense prediction tasks have been proposed and they show that the design of spatial attention is critical to their success in these tasks. In this work, we revisit the design of the spatial attention and demonstrate that a carefully dev…
Pedestrian trajectory prediction is crucial for many important applications. This problem is a great challenge because of complicated interactions among pedestrians. Previous methods model only the pairwise interactions between pedestrians, which not only oversimplifies the interactions among pedest…