Combating Label Noise with a General Surrogate Model for Sample Selection

Information Science, Computer Science, Artificial Intelligence,
label noise   sample selection   deep learning   vision-language model   CLIP model   noise-aware loss   robust training  

Academic Background and Problem Statement With the rapid development of Deep Neural Networks (DNNs), visual intelligence systems have made significant progress in tasks such as image classification, object detection, and video understanding. However, these breakthroughs rely heavily on the collection of high-quality annotated data, which is often t...

From Behavior to Natural Language: Generative Approach for UAV Intent Recognition

Engineering, Aerospace Engineering, Information Science, Computer Science, Artificial Intelligence,
UAV   intent recognition   generative model   cross-modal   time series   deep learning   confrontation environment  

UAV Behavior Intent Recognition Based on Generative Models: A Cross-Modal Study From Behavior to Natural Language Background and Research Objectives In recent years, Unmanned Aerial Vehicle (UAV) technology has advanced rapidly and has found widespread applications in civilian and military domains, including search and rescue, precision agriculture...

Enhancing Aerial Object Detection with Selective Frequency Interaction Network

Engineering, Aerospace Engineering, Information Science, Computer Science, Artificial Intelligence,
aerial object detection   frequency-domain features   selective frequency interaction   convolutional neural networks   feature extraction   deep learning   computer vision  

Selective Frequency Interaction Network for Improved Aerial Object Detection Background and Problem Statement With the advancements in computer vision, aerial object detection has become a critical research focus in remote sensing. This task aims to identify targets such as vehicles or buildings from aerial images captured at varying angles and alt...

AugDiff: Diffusion-Based Feature Augmentation for Multiple Instance Learning in Whole Slide Image

Information Science, Computer Science, Artificial Intelligence, Medicine, Oncology,
feature augmentation   diffusion model   multiple instance learning   whole slide image   computational pathology   deep learning   image generation  

Diffusion-Based Feature Augmentation: A Novel Approach for Multiple Instance Learning in Whole Slide Images Academic Background and Research Motivation In computational pathology, effectively analyzing Whole Slide Images (WSIs) is a burgeoning area of research. WSIs are ultra-high-resolution images with a broad field of view and are widely employed...

A Wearable Echomyography System Based on a Single Transducer

Engineering, Electrical Engineering, Information Science, Artificial Intelligence, Medicine, Respiratory System, Neurology, Medical Imaging, Life Sciences, Bioengineering,
wearable devices   echomyography   single transducer   deep learning   muscle activity monitoring   wireless circuit   ultrasound  

Innovative Advances in Wearable Single-Transducer Echomyography Systems: From Muscle Dynamics Monitoring to Complex Gesture Tracking Academic Background and Research Significance In recent years, wearable electronic devices have garnered significant attention for their enormous potential in health monitoring and human-machine interaction. Electromy...

Robust Self-Supervised Denoising of Voltage Imaging Data Using CellMincer

Medicine, Neurology, Medical Imaging, Life Sciences, Biophysics,
voltage imaging   self-supervised learning   denoising algorithm   deep learning   signal processing  

Academic Background Voltage imaging is a powerful technique for studying neuronal activity, but its effectiveness is often constrained by low signal-to-noise ratios (SNR). Traditional denoising methods, such as matrix factorization, impose rigid assumptions about noise and signal structures, while existing deep learning approaches fail to fully cap...

The Conformational Space of RNase P RNA in Solution

Life Sciences, Biochemistry, Biophysics,
RNA conformation   solution atomic force microscopy   deep learning   statistical analysis   enzymatic activity  

The Conformational Space of RNase P RNA in Solution Academic Background The conformational diversity of RNA plays a crucial role in biology, particularly in processes such as RNA splicing, packaging, cellular transcriptional activation, and responses to environmental stimuli. However, traditional biophysical techniques have been unable to directly ...

Dynamic Attention Vision-Language Transformer Network for Person Re-Identification

Information Science, Electronic Information, Computer Science, Automation, Artificial Intelligence,
dynamic attention   vision-language   person re-identification   feature integration   deep learning   multimodal   domain adaptation  

Dynamic Attention Vision-Language Transformer Network for Person Re-Identification Research Report In recent years, multimodal person re-identification (ReID) has gained increasing attention in the field of computer vision. Person ReID aims to identify specific individuals across different camera views, serving as a critical technology in security ...

Rethinking Contemporary Deep Learning Techniques for Error Correction in Biometric Data

Engineering, Electrical Engineering, Information Science, Computer Science, Artificial Intelligence, Life Sciences, Bioengineering,
biometrics   secure sketch   error correction   maximum likelihood decoding   deep learning  

Rethinking Deep Learning Techniques for Error Correction in Biometric Data Background With the rapid development of information technology, biometric data has become increasingly important in identity verification and secure storage. Traditional cryptography relies on uniformly distributed and precisely reproducible random strings. However, most re...

A RAFT-based Network and Synthetic Dataset for Digital Video Stabilization

Information Science, Artificial Intelligence,
RAFT   video stabilization   synthetic dataset   deep learning   optical flow prediction  

Report on the Study of Deep Learning-Based Video Stabilization Methods and the SynthStab Synthetic Dataset Background Introduction Digital video stabilization technology, which removes unnecessary vibrations and camera motion artifacts through software, is a critical component in modern video processing, particularly for amateur video shooting. How...