activity
20222024
most citedCLIPose: Category-Level Object Pose Estimation with Pre-trained Vision-Language Knowledge

29 citations · 37 across the 7 of their papers we have counts for

collaborators

7 papers

cs.CV20241 cited

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

Jianxin Huang, Jiahang Li, Ning Jia +4

Task-specific data-fusion networks have marked considerable achievements in urban scene parsing. Among these networks, our recently proposed RoadFormer successfully extracts hetero…

cs.RO2024

Accurate Prior-centric Monocular Positioning with Offline LiDAR Fusion

Jinhao He, Huaiyang Huang, Shuyang Zhang +3

Unmanned vehicles usually rely on Global Positioning System (GPS) and Light Detection and Ranging (LiDAR) sensors to achieve high-precision localization results for navigation purp…

cs.CV2024

Vision-and-Language Navigation via Causal Learning

Liuyi Wang, Zongtao He, Ronghao Dang +3

In the pursuit of robust and generalizable environment perception and language understanding, the ubiquitous challenge of dataset bias continues to plague vision-and-language navig…

cs.CV2024

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

Liuyi Wang, Zongtao He, Ronghao Dang +3

Vision-and-Language Navigation (VLN) has gained significant research interest in recent years due to its potential applications in real-world scenarios. However, existing VLN metho…

cs.CV202429 cited

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

Xiao Lin, Minghao Zhu, Ronghao Dang +5

Most of existing category-level object pose estimation methods devote to learning the object category information from point cloud modality. However, the scale of 3D datasets is li…

cs.RO20235 cited

Multiple Thinking Achieving Meta-Ability Decoupling for Object Navigation

Ronghao Dang, Lu Chen, Liuyi Wang +3

We propose a meta-ability decoupling (MAD) paradigm, which brings together various object navigation methods in an architecture system, allowing them to mutually enhance each other…