M2DA: Multi-Modal Fusion Transformer Incorporating Driver Attention for Autonomous Drivingby Dongyang Xu, Haokun Li, Qingfan…
Segment Any Object Model (SAOM): Real-to-Simulation Fine-Tuning Strategy for Multi-Class Multi-Instance Segmentationby Mariia Khan, Yue…
Trustworthy Automated Driving through Qualitative Scene Understanding and Explanationsby Nassim Belmecheri, Arnaud Gotlieb, Nadjib Lazaar,…
SGS-SLAM: Semantic Gaussian Splatting For Neural Dense SLAMby Mingrui Li, Shuhong Liu, Heng Zhou, Guohao…
Good at captioning, bad at counting: Benchmarking GPT-4V on Earth observation databy Chenhui Zhang, Sherrie…
Object Attribute Matters in Visual Question Answeringby Peize Li, Qingyi Si, Peng Fu, Zheng Lin,…
Visual Lexicon: Rich Image Features in Language Spaceby XuDong Wang, Xingyi Zhou, Alireza Fathi, Trevor…
Stag-1: Towards Realistic 4D Driving Simulation with Video Generation Modelby Lening Wang, Wenzhao Zheng, Dalong…
Quantifying the synthetic and real domain gap in aerial scene understandingby Alina MarcuFirst submitted to…
DeSplat: Decomposed Gaussian Splatting for Distractor-Free Renderingby Yihao Wang, Marcus Klasson, Matias Turkulainen, Shuzhe Wang,…