Jintao Cheng

MambaFlow: A Novel and Flow-Guided State Space Model for Scene Flow Estimation

Jiehao Luo, Jintao Cheng, Qingwen Zhang, Bohuan Xue et autres

Scene flow estimation aims to predict 3D motion from consecutive point cloud frames, which is of great interest in autonomous driving field. Existing methods face challenges such as insufficient spatio-temporal modeling and inherent loss of fine-grained feature during voxelization. However, the success …

cn, hk, se (code pays fourni par la source)

VersaQ-3D: Architecture Support for Visual Geometry Grounded Transformers via Versatile Quantization

Yipu Zhang, Jintao Cheng, Xingyu Liu, Zeyu Li et autres

3D reconstruction and view synthesis are fundamental to AR/VR, robotics, and digital twins. The Visual Geometry Grounded Transformer (VGGT) enables strong feed-forward 3D reconstruction while its billion-parameter scale limits on-device deployment. LLM-oriented quantization methods fail on VGGT due to saturated activation channels …

KDMOS:Knowledge Distillation for Motion Segmentation

Jintao Cheng, Zeyu Chen, Rui Fan, Zhilong He et autres

Motion Object Segmentation (MOS) is crucial for autonomous driving, as it enhances localization, path planning, map construction, scene flow estimation, and future state prediction. While existing methods achieve strong performance, balancing accuracy and real-time inference remains a challenge. To address this, we …

cn (code pays fourni par la source)

Scale, Don't Fine-tune: Guiding Multimodal LLMs for Efficient Visual Place Recognition at Test-Time

Jintao Cheng, Weibin Li, Jiehao Luo, Zhijian He et autres

Visual Place Recognition (VPR) has evolved from handcrafted descriptors to deep learning approaches, yet significant challenges remain. Current approaches, including Vision Foundation Models (VFMs) and Multimodal Large Language Models (MLLMs), enhance semantic understanding but suffer from high computational overhead and limited cross-domain …

A Pseudo Global Fusion Paradigm-Based Cross-View Network for LiDAR-Based Place Recognition

Jintao Cheng, Jiehao Luo, Xieyuanli Chen, Wu Jin et autres

LiDAR-based Place Recognition (LPR) remains a critical task in Embodied Artificial Intelligence (AI) and Autonomous Driving, primarily addressing localization challenges in GPS-denied environments and supporting loop closure detection. Existing approaches reduce place recognition to a Euclidean distance-based metric learning task, neglecting the …

OverlapMamba: A Shift State Space Model for LiDAR-Based Place Recognition

Jiehao Luo, Jintao Cheng, Qiuchi Xiang, Jin Chu Wu et autres

Place recognition is the foundation for autonomous systems to achieve independent decision-making and secure operation. It is also crucial in tasks such as loop closure detection and global localization in Simultaneous Localization and Mapping (SLAM) technology. Existing LiDAR-based place recognition (LPR) methods …

cn, hk (code pays fourni par la source)

KDMOS:Knowledge Distillation for Motion Segmentation

Jintao Cheng, Zeyu Chen, Rui Fan, Zhilong He et autres

Motion Object Segmentation (MOS) is crucial for autonomous driving, as it enhances localization, path planning, map construction, scene flow estimation, and future state prediction. While existing methods achieve strong performance, balancing accuracy and real-time inference remains a challenge. To address this, we …

You Sense Only Once Beneath: Ultra-Light Real-Time Underwater Object Detection

Jun Dong, Wen‐Li Wu, Jintao Cheng, Xiaoyu Tang

Despite the remarkable achievements in object detection, the model’s accuracy and efficiency still require further improvement under challenging underwater conditions, such as low image quality and limited computational resources. To address this, we propose an Ultra-Light Real-Time Underwater Object Detection framework, You …

cn (code pays fourni par la source)

Speech Emotion Recognition via CNN-Transformer and multidimensional attention mechanism

Xiaoyu Tang, Jiazheng Huang, Yixin Lin, Ting Dang et autres

cn, au (code pays fourni par la source)

You Sense Only Once Beneath: Ultra-Light Real-Time Underwater Object Detection

Jun Dong, Wen‐Li Wu, Jintao Cheng, Xiaoyu Tang

Despite the remarkable achievements in object detection, the model's accuracy and efficiency still require further improvement under challenging underwater conditions, such as low image quality and limited computational resources. To address this, we propose an Ultra-Light Real-Time Underwater Object Detection framework, You …

Incorporating GNSS Information with LIDAR-Inertial Odometry for Accurate Land-Vehicle Localization

Jintao Cheng, Bohuan Xue, S.-F. Chen, Qiuchi Xiang et autres

Currently, visual odometry and LIDAR odometry are performing well in pose estimation in some typical environments, but they still cannot recover the localization state at high speed or reduce accumulated drifts. In order to solve these problems, we propose a novel LIDAR-based …

Real-Time AIoT for AAV Antenna Interference Detection via Edge–Cloud Collaboration

Jun Dong, Jintao Cheng, Jin Chu Wu, Chengxi Zhang et autres

In the fifth-generation (5G) era, eliminating communication interference sources is crucial for maintaining network performance. Interference often originates from unauthorized or malfunctioning antennas, and radio monitoring agencies must address numerous sources of such antennas annually. Autonomous aerial vehicles (AAVs) can improve inspection …

cn, hk (code pays fourni par la source)