Results 41 to 50 of about 13,981 (216)

CIR-SSM: A Cross and Inter Resolution State-Space Model for Underwater Image Enhancement

Applied Sciences
Underwater images often suffer from strong color casts, low contrast, and blurred textures. It is observed that low resolution can provide globally correct color, so low-resolution priors can guide high-resolution correction.
Fengxian Liu, Ning Ye, Haitao Wang
doaj   +1 more source

VAMBA: Understanding Hour-Long Videos with Hybrid Mamba-Transformers [PDF]

IEEE International Conference on Computer Vision
State-of-the-art transformer-based large multimodal models (LMMs) struggle to handle hour-long video inputs due to the quadratic complexity of the causal self-attention operations, leading to high computational costs during training and inference ...
Weiming Ren, Wentao Ma, Huan Yang, Cong Wei, Ge Zhang, Wenhu Chen   +5 more
semanticscholar   +1 more source

Virtual commissioning of the Korea Light Source Hard X‐ray Nanoprobe beamline with multilingual natural language control

Journal of Synchrotron Radiation, EarlyView.
A pre‐installation virtual commissioning platform for the Korea Light Source ID10 hard X‐ray nanoprobe couples browser‐based Monte Carlo ray tracing, EPICS/Bluesky control and a multilingual natural‐language agent (98.2% accuracy in Korean, English and Japanese) under a zero‐change hardware transition principle, producing commissioning design inputs ...
Minho Seo, Hyeong-joo Choi, Daseul Ham, Changwan Ha, Yong-Hyun Kim, Changhui Lee, Jun Lim, Ki-jeong Kim, In-hui Hwang, Jaeyong Shin   +9 more
wiley   +1 more source

Multiscale Sequence Aware Mamba for Hyperspectral Image Classification

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Benefiting from the state-space model, Mamba-based networks can effectively model long-range sequential dependencies while maintaining linear complexity.
Fulin Xu, Duo Zhan, Mingyang Ma, Shaohui Mei   +3 more
doaj   +1 more source

Mamba Collaborative Implicit Neural Representation for Hyperspectral and Multispectral Remote Sensing Image Fusion

IEEE Transactions on Geoscience and Remote Sensing
Hyperspectral remote sensing images (HSIs) capture detailed spectral characteristics of features, while multispectral remote sensing images (MSIs) provide clear spatial distribution. Fusing these two types of images can enhance feature identification and
Chunyu Zhu, Shan Deng, Xuan Song, Yachao Li, Qi Wang   +4 more
semanticscholar   +1 more source

Mamba YOLO: A Simple Baseline for Object Detection with State Space Model [PDF]

AAAI Conference on Artificial Intelligence
Driven by the rapid development of deep learning technology, the YOLO series has set a new benchmark for real-time object detectors. Additionally, transformer-based structures have emerged as the most powerful solution in the field, greatly extending the
Zeyu Wang, Chen Li, Huiying Xu, Xinzhong Zhu, Hongbo Li   +4 more
semanticscholar   +1 more source

Attention Based Optimization for 3D Shape Registration

Computer Graphics Forum, EarlyView.
Abstract Transformers are sequence‐to‐sequence architectures originally designed to handle structurally rigid and order‐sensitive data, such as text and images. At their core, they exploit the attention mechanism, which is permutation‐equivariant and relies on computing token‐to‐token relationships.
A. Riva, L. Olearo, S. Melzi
wiley   +1 more source

Mamba Hawkes Process

CoRR
Irregular and asynchronous event sequences are prevalent in many domains, such as social media, finance, and healthcare. Traditional temporal point processes (TPPs), like Hawkes processes, often struggle to model mutual inhibition and nonlinearity effectively.
Anningzhe Gao, Shan Dai, Yan Hu
openaire   +2 more sources

ECG-Mamba: Cardiac Abnormality Classification With Non-Uniform-Mix Augmentation on 12-Lead ECGs

IEEE Journal of Translational Engineering in Health and Medicine
Objective: The detection of heart abnormalities using electrocardiograms (ECG) is a critical task in medical diagnostics. A lot of literature has utilized ResNet and Transformer architectures to detect heart disease based on ECG signals.
Huawei Jiang, Husna Mutahira, Shibo Wei, Mannan Saeed Muhammad   +3 more
doaj   +1 more source

FaceMamba: Geometry‐Aware Mamba for Efficient Speech‐Driven 3D Facial Animation

Computer Graphics Forum, EarlyView.
Abstract Speech‐driven 3D facial animation plays a pivotal role in immersive digital human applications. Recent works have explored Mamba‐based sequence modeling as an efficient alternative to Transformer, but they often suffer from limited cross‐modal alignment and insufficient control over fine‐grained facial deformations.
Yifan Ge, Zhiqiang Ren, Yazhan Zhang, Haofei Wang, Yawen Zhang, Shengli Zhang   +5 more
wiley   +1 more source