activity
20242026
collaborators

6 papers

cs.CV2026

Revisiting Token Compression for Accelerating ViT-based Sparse Multi-View 3D Object Detectors

Mingqian Ji, Shanshan Zhang, Jian Yang

Vision Transformer (ViT)-based sparse multi-view 3D object detectors have achieved remarkable accuracy but still suffer from high inference latency due to heavy token processing. T…

cs.CV2026

RayMamba: Ray-Aligned Serialization for Long-Range 3D Object Detection

Cheng Lu, Mingqian Ji, Shanshan Zhang +2

Long-range 3D object detection remains challenging because LiDAR observations become highly sparse and fragmented in the far field, making reliable context modeling difficult for e…

cs.CV2025

Enhancing Pseudo-Boxes via Data-Level LiDAR-Camera Fusion for Unsupervised 3D Object Detection

Mingqian Ji, Jian Yang, Shanshan Zhang

Existing LiDAR-based 3D object detectors typically rely on manually annotated labels for training to achieve good performance. However, obtaining high-quality 3D labels is time-con…

cs.CV2025

OcRFDet: Object-Centric Radiance Fields for Multi-View 3D Object Detection in Autonomous Driving

Mingqian Ji, Jian Yang, Shanshan Zhang

Current multi-view 3D object detection methods typically transfer 2D features into 3D space using depth estimation or 3D position encoder, but in a fully data-driven and implicit m…

cs.CV2025

DepthFusion: Depth-Aware Hybrid Feature Fusion for LiDAR-Camera 3D Object Detection

Mingqian Ji, Jian Yang, Shanshan Zhang

State-of-the-art LiDAR-camera 3D object detectors usually focus on feature fusion. However, they neglect the factor of depth while designing the fusion strategy. In this work, we a…

cs.CV2024

Imagine the Unseen: Occluded Pedestrian Detection via Adversarial Feature Completion

Shanshan Zhang, Mingqian Ji, Yang Li +1

Pedestrian detection has significantly progressed in recent years, thanks to the development of DNNs. However, detection performance at occluded scenes is still far from satisfacto…