6 papers
Goal2Pixel: Grounding Goals to Pixels for Vision-Language Navigation
Muyi Bao, Yuxin Cai, Hang Xu +7
Vision-language models (VLMs) have become a common foundation for vision-and-language navigation in continuous environments (VLN-CE). Yet most VLM-based methods cast navigation as…
IntentNav: Learning Spatial-Visual Object Navigation from Human Demonstrations
Yuxin Cai, Zongtai Li, Maonan Wang +9
Object navigation requires a robot to search for an unobserved target in an unknown environment by deciding where to explore next under partial observability. Effective search rese…
NUMINA: A Natural Understanding Benchmark for Multi-dimensional Intelligence and Numerical Reasoning Abilities
Changyu Zeng, Yifan Wang, Zimu Wang +6
Recent advancements in 2D multimodal large language models (MLLMs) have significantly improved performance in vision-language tasks. However, extending these capabilities to 3D env…
FTCFormer: Fuzzy Token Clustering Transformer for Image Classification
Muyi Bao, Changyu Zeng, Yifan Wang +5
Transformer-based deep neural networks have achieved remarkable success across various computer vision tasks, largely attributed to their long-range self-attention mechanism and sc…
Vision Mamba in Remote Sensing: A Comprehensive Survey of Techniques, Applications and Outlook
Muyi Bao, Shuchang Lyu, Zhaoyang Xu +5
Deep learning has profoundly transformed remote sensing, yet prevailing architectures like Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) remain constrained by…
ASP-VMUNet: Atrous Shifted Parallel Vision Mamba U-Net for Skin Lesion Segmentation
Muyi Bao, Shuchang Lyu, Zhaoyang Xu +4
Skin lesion segmentation is a critical challenge in computer vision, and it is essential to separate pathological features from healthy skin for diagnostics accurately. Traditional…