3 papers
cs.CV2026
TCMA: Text-Conditioned Multi-granularity Alignment for Drone Cross-Modal Text-Video Retrieval
Zixu Zhao, Yang Zhan, Yunhao Li +1
Unmanned aerial vehicles (UAVs) have become powerful platforms for real-time, high-resolution data collection, producing massive volumes of aerial videos. Efficient retrieval of re…
cs.LG2026
Scaling Learning-based AEB with Massive Unlabeled Data
Xiangyu Wang, Yang Zhan, Mengxiang Hao +9
This paper studies how to scale learning-based automatic emergency braking (AEB) with massive unlabeled fleet data under production constraints. Our approach is based on meta-feedb…
cs.CV2026
UAVBench and UAVIT-1M: Benchmarking and Enhancing MLLMs for Low-Altitude UAV Vision-Language Understanding
Yang Zhan, Yuan Yuan
Multimodal Large Language Models (MLLMs) have made significant strides in natural images and satellite remote sensing images. However, understanding low-altitude drone scenarios re…