Research uncovers vulnerabilities in smartphone gait recognition technology.
― 6 min read
Computer Science - Computer Vision and Pattern Recognition
RSSA study on how well news thumbnails match their articles.
― 5 min read
Examining gender bias in T2I models through the Paired Stereotype Test.
― 6 min read
A new approach enhances image safety in text-to-image models through prompt optimization.
― 7 min read
BioFusionNet combines tumor images, genetic data, and clinical insights for better risk assessment.
― 9 min read
SegmentAnyBone enhances bone imaging accuracy in MRI scans for improved diagnosis.
― 6 min read
A new method enhances object detection in documents using graph structures.
― 8 min read
A new method enhances efficiency in graph-based approximate nearest neighbor search.
― 5 min read
A new approach improves visual recognition tasks through residual attention mechanisms.
― 8 min read
This benchmark assesses the performance of medical language models in healthcare.
― 7 min read
Introducing FOMO, a method to improve DNNs against adversarial attacks through forgetting.
― 6 min read
Learn how conditional invariance enhances model performance across varying data types.
― 6 min read
A look at the potential and challenges of neuromorphic sensors for face analysis.
― 8 min read
A new system learns user preferences in real-time to suggest clothing.
― 6 min read
A novel deep-learning framework classifies images of varying sizes for better permeability prediction.
― 7 min read
Researchers improve tumor detection accuracy using advanced imaging techniques.
― 5 min read
MVDiffusion++ creates detailed 3D models from just one or a few images.
― 5 min read
A study on how AI learns object relationships through visual reasoning tasks.
― 7 min read
Event-based cameras enhance the reading of blurred barcodes and signs.
― 6 min read
Addressing domain shift and concept drift in AI models.
― 5 min read
Introducing CAMixer, a novel approach for detecting changes in synthetic aperture radar images.
― 5 min read
Using cameras and landmarks improves location tracking in GPS-denied environments.
― 5 min read
New methods help robots navigate using visual input without complex maps.
― 9 min read
A new method improves 3D scene inference despite environmental challenges.
― 5 min read
A new approach to troop navigation using visual landmarks instead of GPS.
― 6 min read
New framework improves video compression efficiency and quality.
― 5 min read
AnyGPT processes text, images, music, and speech for diverse applications.
― 4 min read
Research explores the use of event cameras for non-contact heart rate monitoring.
― 6 min read
A new method enhances deep learning models' strength and accuracy.
― 6 min read
This article explores how data augmentation improves learning in deep reinforcement learning.
― 7 min read
A new AI tool improves early detection of pancreatic cancer through enhanced imaging.
― 6 min read
A novel method improves understanding of extensive video content.
― 4 min read
A look at how Direct Consistency Optimization improves image generation from text.
― 7 min read
A new method enhances robot identification of flexible items using text and image processing.
― 5 min read
SepCLR enhances feature separation in data for better analysis.
― 6 min read
InMD-X enhances decision-making for Internal Medicine Doctors with specialized language models.
― 5 min read
A novel approach for detecting hateful memes using few-shot learning techniques.
― 6 min read
A new dataset aims to improve detection of AI-created images.
― 6 min read
New dataset enhances evaluation methods for machine unlearning in image generation.
― 6 min read
A look into how VLMs combine image and text processing.
― 5 min read