Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Mao, Weixin"'
Autor:
Li, Haosheng, Mao, Weixin, Deng, Weipeng, Meng, Chenyu, Zhang, Rui, Jia, Fan, Wang, Tiancai, Fan, Haoqiang, Wang, Hongan, Deng, Xiaoming
Task-oriented grasping, which involves grasping specific parts of objects based on their functions, is crucial for developing advanced robotic systems capable of performing complex tasks in dynamic environments. In this paper, we propose a training-f
Externí odkaz:
http://arxiv.org/abs/2410.08901
Autor:
Bai, Yifan, Wu, Dongming, Liu, Yingfei, Jia, Fan, Mao, Weixin, Zhang, Ziheng, Zhao, Yucheng, Shen, Jianbing, Wei, Xing, Wang, Tiancai, Zhang, Xiangyu
Rapid advancements in Autonomous Driving (AD) tasks turned a significant shift toward end-to-end fashion, particularly in the utilization of vision-language models (VLMs) that integrate robust logical reasoning and cognitive abilities to enable compr
Externí odkaz:
http://arxiv.org/abs/2405.18361
Autor:
Huang, Binyuan, Wen, Yuqing, Zhao, Yucheng, Hu, Yaosi, Liu, Yingfei, Jia, Fan, Mao, Weixin, Wang, Tiancai, Zhang, Chi, Chen, Chang Wen, Chen, Zhenzhong, Zhang, Xiangyu
Autonomous driving progress relies on large-scale annotated datasets. In this work, we explore the potential of generative models to produce vast quantities of freely-labeled data for autonomous driving applications and present SubjectDrive, the firs
Externí odkaz:
http://arxiv.org/abs/2403.19438
Autor:
Jia, Fan, Mao, Weixin, Liu, Yingfei, Zhao, Yucheng, Wen, Yuqing, Zhang, Chi, Zhang, Xiangyu, Wang, Tiancai
Typically, autonomous driving adopts a modular design, which divides the full stack into perception, prediction, planning and control parts. Though interpretable, such modular design tends to introduce a substantial amount of redundancy. Recently, mu
Externí odkaz:
http://arxiv.org/abs/2311.13549
Autor:
Mao, Weixin, Yang, Jinrong, Ge, Zheng, Song, Lin, Zhou, Hongyu, Mao, Tiezheng, Li, Zeming, Yoshie, Osamu
Depth perception is a crucial component of monoc-ular 3D detection tasks that typically involve ill-posed problems. In light of the success of sample mining techniques in 2D object detection, we propose a simple yet effective mining strategy for impr
Externí odkaz:
http://arxiv.org/abs/2306.17450
Autor:
Han, Chunrui, Yang, Jinrong, Sun, Jianjian, Ge, Zheng, Dong, Runpei, Zhou, Hongyu, Mao, Weixin, Peng, Yuang, Zhang, Xiangyu
Long-term temporal fusion is a crucial but often overlooked technique in camera-based Bird's-Eye-View (BEV) 3D perception. Existing methods are mostly in a parallel manner. While parallel fusion can benefit from long-term information, it suffers from
Externí odkaz:
http://arxiv.org/abs/2303.05970
The great progress of 3D object detectors relies on large-scale data and 3D annotations. The annotation cost for 3D bounding boxes is extremely expensive while the 2D ones are easier and cheaper to collect. In this paper, we introduce a hybrid traini
Externí odkaz:
http://arxiv.org/abs/2211.08287
Currently, detecting 3D objects in Bird's-Eye-View (BEV) is superior to other 3D detectors for autonomous driving and robotics. However, transforming image features into BEV necessitates special operators to conduct feature sampling. These operators
Externí odkaz:
http://arxiv.org/abs/2208.09394
Autor:
Yang, Jinrong, Song, Lin, Liu, Songtao, Mao, Weixin, Li, Zeming, Li, Xiaoping, Sun, Hongbin, Sun, Jian, Zheng, Nanning
Many point-based 3D detectors adopt point-feature sampling strategies to drop some points for efficient inference. These strategies are typically based on fixed and handcrafted rules, making it difficult to handle complicated scenes. Different from t
Externí odkaz:
http://arxiv.org/abs/2207.10909
To date, the most powerful semi-supervised object detectors (SS-OD) are based on pseudo-boxes, which need a sequence of post-processing with fine-tuned hyper-parameters. In this work, we propose replacing the sparse pseudo-boxes with the dense predic
Externí odkaz:
http://arxiv.org/abs/2207.02541