A new framework to classify images without prior labels using broad vocabulary.
― 6 min read
Muzammal Naseer
FLIP enhances face anti-spoofing systems using language and vision transformers.
― 5 min read
ProText enhances vision-language models using text-only data for better task handling.
― 6 min read
Understanding model robustness is key for real-world applications in various fields.
― 5 min read
New framework improves video searches by combining visuals and detailed language descriptions.
― 6 min read
Learn to classify objects using images and 3D point clouds without labels.
― 6 min read
Assessing the capabilities and challenges of advanced video understanding models.
― 5 min read
Study examines the robustness of segmentation models against adversarial attacks in healthcare.
― 6 min read
This article examines how Visual State Space Models handle visual challenges.
― 6 min read
VANE-Bench enhances detection of anomalies in videos amidst growing AI content.
― 5 min read
Collaboration in healthcare through federated learning improves medical image classification while protecting privacy.
― 6 min read
New methods expose vulnerabilities in medical models through backdoor attacks.
― 5 min read
A new method uses makeup to enhance privacy in facial recognition systems.
― 5 min read
PromptSmooth improves Med-VLMs' accuracy against adversarial attacks efficiently.
― 4 min read
StableMamba enhances image and video processing with improved robustness and performance.
― 5 min read
New tools improve how we describe changes in satellite images over time.
― 5 min read
A new dataset revolutionizes analysis of medical images and their descriptions.
― 8 min read