1 citations · 1 across the 17 of their papers we have counts for
8 papers · 1 filter
CLOSER-VLN: Closed-Loop Self-Verified Retrieval-Augmented Reasoning for Aerial Vision-Language Navigation
Shaoxuan Li, Xiangyu Dong, Xiaoguang Ma +3
Vision-language navigation (VLN) has recently advanced with large language and multimodal models, enabling agents to follow natural-language instructions in unseen environments wit…
Hierarchical Dual-Change Collaborative Learning for UAV Scene Change Captioning
Fuhai Chen, Pengpeng Huang, Junwen Wu +4
This paper proposes a novel task for UAV scene understanding - UAV Scene Change Captioning (UAV-SCC) - which aims to generate natural language descriptions of semantic changes in d…
ViSA-Enhanced Aerial VLN: A Visual-Spatial Reasoning Enhanced Framework for Aerial Vision-Language Navigation
Haoyu Tong, Xiangyu Dong, Xiaoguang Ma +3
Existing aerial Vision-Language Navigation (VLN) methods predominantly adopt a detection-and-planning pipeline, which converts open-vocabulary detections into discrete textual scen…
LightZeroNav: Zero-Shot Vision Language Navigation in Continuous Environments Based on Lightweight VLMs
Kun Luo, Xiangyu Dong, Xiaoguang Ma +2
Although vision-language navigation (VLN) has progressed rapidly, zero-shot VLN in continuous environments (VLN-CE) remains highly challenging when using lightweight vision-languag…
SE-VLN: A Self-Evolving Vision-Language Navigation Framework Based on Multimodal Large Language Models
Xiangyu Dong, Haoran Zhao, Jiang Gao +5
Recent advances in vision-language navigation (VLN) were mainly attributed to emerging large language models (LLMs). These methods exhibited excellent generalization capabilities i…
Group-Mix SAM: Lightweight Solution for Industrial Assembly Line Applications
Wu Liang, X. -G. Ma
Since the advent of the Segment Anything Model(SAM) approximately one year ago, it has engendered significant academic interest and has spawned a large number of investigations and…
ALow-Cost Real-Time Framework for Industrial Action Recognition Using Foundation Models
Zhicheng Wang, Wensheng Liang, Ruiyan Zhuang +3
Action recognition (AR) in industrial environments -- particularly for identifying actions and operational gestures -- faces persistent challenges due to high deployment costs, poo…
Transcending Adversarial Perturbations: Manifold-Aided Adversarial Examples with Legitimate Semantics
Shuai Li, Xiaoyu Jiang, Xiaoguang Ma
Deep neural networks were significantly vulnerable to adversarial examples manipulated by malicious tiny perturbations. Although most conventional adversarial attacks ensured the v…