Picture for Chengju Liu

Chengju Liu

RoadFormer+: Delivering RGB-X Scene Parsing through Scale-Aware Information Decoupling and Advanced Heterogeneous Feature Fusion

Add code
Jul 31, 2024
Viaarxiv icon

Accurate Prior-centric Monocular Positioning with Offline LiDAR Fusion

Add code
Jul 12, 2024
Viaarxiv icon

MAGIC: Meta-Ability Guided Interactive Chain-of-Distillation for Effective-and-Efficient Vision-and-Language Navigation

Add code
Jun 25, 2024
Viaarxiv icon

SAM-LAD: Segment Anything Model Meets Zero-Shot Logic Anomaly Detection

Add code
Jun 02, 2024
Viaarxiv icon

Efficient Text-driven Motion Generation via Latent Consistency Training

Add code
May 05, 2024
Viaarxiv icon

Vision-and-Language Navigation via Causal Learning

Add code
Apr 16, 2024
Viaarxiv icon

Causality-based Cross-Modal Representation Learning for Vision-and-Language Navigation

Add code
Mar 06, 2024
Viaarxiv icon

CLIPose: Category-Level Object Pose Estimation with Pre-trained Vision-Language Knowledge

Add code
Feb 24, 2024
Viaarxiv icon

TransPose: 6D Object Pose Estimation with Geometry-Aware Transformer

Add code
Oct 25, 2023
Viaarxiv icon

InstructDET: Diversifying Referring Object Detection with Generalized Instructions

Add code
Oct 17, 2023
Viaarxiv icon