English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Autonomous driving faces great safety challenges for a lack of globalperspective and the limitation of long-range perception capabilities. It hasbeen widely agreed that vehicle-infrastructure cooperation is required toachieve Level 5 autonomy. However, there is still NO dataset from realscenarios available for computer vision researchers to work onvehicle-infrastructure cooperation-related problems. To accelerate computervision research and innovation for Vehicle-Infrastructure CooperativeAutonomous Driving (VICAD), we release DAIR-V2X Dataset, which is the firstlarge-scale, multi-modality, multi-view dataset from real scenarios for VICAD.DAIR-V2X comprises 71254 LiDAR frames and 71254 Camera frames, and all framesare captured from real scenes with 3D annotations. The Vehicle-InfrastructureCooperative 3D Object Detection problem (VIC3D) is introduced, formulating theproblem of collaboratively locating and identifying 3D objects using sensoryinputs from both vehicle and infrastructure. In addition to solving traditional3D object detection problems, the solution of VIC3D needs to consider thetemporal asynchrony problem between vehicle and infrastructure sensors and thedata transmission cost between them. Furthermore, we propose Time CompensationLate Fusion (TCLF), a late fusion framework for the VIC3D task as a benchmarkbased on DAIR-V2X. Find data, code, and more up-to-date information athttps://thudair.baai.ac.cn/index and https://github.com/AIR-THU/DAIR-V2X.

DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection