9 papers
CASA: Content-Acoustic Speaking Assessment with Speech Encoder and Large Language Model
Nhan Phan, Ilona Lähteenmäki, Anna von Zansen +4
Research on automatic speaking assessment (ASA) has increasingly adopted multimodal speech large language models to assess learners' speaking performance. However, existing studies…
Graph-Loc: Robust Graph-Based LiDAR Pose Tracking with Compact Structural Map Priors under Low Observability and Occlusion
Wentao Zhao, Yihe Niu, Zikun Chen +4
Map-based LiDAR pose tracking is essential for long-term autonomous operation, where onboard map priors need be compact for scalable storage and fast retrieval, while online observ…
OTPL-VIO: Robust Visual-Inertial Odometry with Optimal Transport Line Association and Adaptive Uncertainty
Zikun Chen, Wentao Zhao, Yihe Niu +2
Robust stereo visual-inertial odometry (VIO) remains challenging in low-texture scenes and under abrupt illumination changes, where point features become sparse and unstable, leadi…
Guided Diffusion-based Generation of Adversarial Objects for Real-World Monocular Depth Estimation Attacks
Yongtao Chen, Yanbo Wang, Wentao Zhao +3
Monocular Depth Estimation (MDE) serves as a core perception module in autonomous driving systems, but it remains highly susceptible to adversarial attacks. Errors in depth estimat…
RaCalNet: Radar Calibration Network for Sparse-Supervised Metric Depth Estimation
Xingrui Qin, Wentao Zhao, Chuan Cao +5
Dense depth estimation using millimeter-wave radar typically requires dense LiDAR supervision, generated via multi-frame projection and interpolation, for guiding the learning of a…
SALT: A Flexible Semi-Automatic Labeling Tool for General LiDAR Point Clouds with Cross-Scene Adaptability and 4D Consistency
Yanbo Wang, Yongtao Chen, Chuan Cao +4
We propose a flexible Semi-Automatic Labeling Tool (SALT) for general LiDAR point clouds with cross-scene adaptability and 4D consistency. Unlike recent approaches that rely on cam…