IROS

Efficient Prediction of Dense Visual Embeddings via Distillation and RGB-D Transformers

通过蒸馏和RGB-D变换器高效预测密集视觉嵌入

Söhnke Benedikt Fischedick, Daniel Seichter, Benedict Stephan, Robin Schmidt, Horst-Michael Gross

机构 * Neuroinformatics and Cognitive Robotics Lab（神经信息学与认知机器人实验室） ； Technische Universität Ilmenau（技术大学伊门豪森） 纠错

AI总结 本文提出DVEFormer，通过知识蒸馏和RGB-D变换器高效预测密集视觉嵌入，实现灵活的文本查询和3D地图构建。

Comments Published in Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2025)

Journal ref Proc. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), 2025, pp. 2400-2407

Body-Hand Modality Expertized Networks with Cross-attention for Fine-grained Skeleton Action Recognition

具有交叉注意力的体-手模态专家化网络用于细粒度骨骼动作识别

Seungyeon Cho, Tae-Kyun Kim

机构 * School of Computing, KAIST（韩国成均馆大学计算机学院） 纠错

AI总结 本文提出BHaRNet，通过体-手专家化网络和交叉注意力机制，提升细粒度骨骼动作识别的准确率，同时降低计算成本。

Comments 7 figures, 8 pages. Accepted to IROS 2025, project page: https://github.com/VinnyCSY/BHaRNet

Journal ref 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hangzhou, China, 2025, pp. 11614-11621

PLK-Calib: Single-shot and Target-less LiDAR-Camera Extrinsic Calibration using Plücker Lines

PLK-Calib: 基于普吕弗线的单次拍摄无目标激光雷达-摄像头外参校准

Yanyu Zhang, Jie Xu, Wei Ren

机构 * Department of Electrical and Computer Engineering, University of California, Riverside（电气与计算机工程系，加州大学河滨分校） 纠错

AI总结 本文提出基于普吕弗线的单次拍摄无目标算法，用于高精度激光雷达-摄像头外参校准，通过几何特性分解旋转和平移，提升校准精度。

Journal ref 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 16091-16097, 2025