Zhangzhe's Blog

08-06

BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection

08-06

BEVDet: High-Performance Multi-Camera 3D Object Detection in Bird-Eye-View

07-29

MOTR: End-to-End Multiple-Object Tracking with Transformer

07-29

Deformable DETR: Deformable Transformers for End-to-end Object Detection

07-18

一些高效backbone设计思想

07-16

UniAD: Planning-oriented Autonomous Driving

07-03

GPT-4 Technical Report

06-30

GPT3:Language Models are Few-Shot Learners

05-25

Segment Anything

05-16

GPT2: Language Models are Unsupervised Multitask Learners