Conversion rate (CVR) prediction is an essential task for large-scale
e-...
3D lane detection from monocular images is a fundamental yet challenging...
3D single object tracking in LiDAR point clouds (LiDAR SOT) plays a cruc...
When using LiDAR semantic segmentation models for safety-critical
applic...
Measuring and alleviating the discrepancies between the synthetic (sourc...
Although recent point cloud analysis achieves impressive progress, the
p...
Estimating accurate lane lines in 3D space remains challenging due to th...
An outstanding image-text retrieval model depends on high-quality labele...
As camera and LiDAR sensors capture complementary information used in
au...
Recent progress on 3D scene understanding has explored visual grounding
...
The lack of label data is one of the significant bottlenecks for Chinese...
3D single object tracking (3D SOT) in LiDAR point clouds plays a crucial...
3D dense captioning aims to describe individual objects by natural langu...
Learning the embeddings for urban regions from human mobility data can r...
3D scene understanding is a relatively emerging research field. In this
...
Code-switching is a speech phenomenon when a speaker switches language d...
Dense video captioning (DVC) aims to generate multi-sentence description...
Current state-of-the-art approaches for image captioning typically adopt...
Current 3D single object tracking approaches track the target based on a...
Point Cloud Sampling and Recovery (PCSR) is critical for massive real-ti...
Compared with the visual grounding in 2D images, the natural-language-gu...
LiDAR point cloud analysis is a core task for 3D computer vision, especi...
Raw point clouds data inevitably contains outliers or noise through
acqu...
Industrial AI systems are mostly end-to-end machine learning (ML) workfl...
Relation classification is an important research arena in the field of
n...