Talk2Sensors: 3D Visual Grounding in Autonomous Driving via Sensor-Adaptive Physical Cue Matching
Talk2Sensors:基于传感器自适应物理线索匹配的自动驾驶3D视觉 grounding
机构 * Thrust of Artificial Intelligence, The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)人工智能学域) ; MMLab, CUHK(香港中文大学MMLab) ; School of Transportation Science and Engineering, Harbin Institute of Technology(哈尔滨工业大学交通科学与工程学院) ; School of Advanced Technology, Xi’an Jiaotong-Liverpool University(西交利物浦大学先进技术学院) ; School of Electronics and Computer Science, University of Southampton(南安普顿大学电子与计算机科学学院) ; School of Intelligent Manufacturing and Smart Transportation, Suzhou City University(苏州城市学院智能制造与智能交通学院) ; Qingdao University of Science and Technology(青岛科技大学) ; Institute for Math & AI, Wuhan University(武汉大学数学与人工智能研究院) ; Institute of Big Data, Fudan University(复旦大学大数据研究院)
AI总结 针对现有室外3D视觉 grounding 未充分利用多传感器互补物理属性的问题,提出首个多传感器数据集Talk2Sensors及TSFormer框架,在相关基准上实现了最优性能。
Comments 14 pages, 12 figures