Emulating human-like adaptive vision for efficient and flexible machine visual perception
nature.com·1d
🧠AI
Flag this post
Decoupling Augmentation Bias in Prompt Learning for Vision-Language Models
arxiv.org·23h
🧠AI
Flag this post
VIST3A: Text-to-3D by Stitching a Multi-view Reconstruction Network to a VideoGenerator
paperium.net·6h·
Discuss: DEV
🧠AI
Flag this post
Fair human-centric image dataset for ethical AI benchmarking
nature.com·1d
🧠AI
Flag this post
Teaching robots to map large environments
news.mit.edu·1d·
Discuss: Hacker News
🤖robotics
Flag this post
Symmetry as a Superpower
dev.to·16h·
Discuss: DEV
🧠AI
Flag this post
Show HN: DeepFaceLab – Free AI Face Swap Online
deepfacelab.app·1d·
Discuss: Hacker News
real-time analytics
Flag this post
Beyond ImageNet: Understanding Cross-Dataset Robustness of Lightweight Vision Models
arxiv.org·2d
🧠AI
Flag this post
Computers Are Getting Much Better at Image Recognition
smithsonianmag.com·3d
🧠AI
Flag this post
Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials
arxiv.org·2d
🧠AI
Flag this post
Topographical sparse mapping: A training framework for deep learning models
sciencedirect.com·2d·
Discuss: Hacker News
🧠AI
Flag this post
SCALE-VLP: Soft-Weighted Contrastive Volumetric Vision-Language Pre-training with Spatial-Knowledge Semantics
arxiv.org·23h
🧠AI
Flag this post
Optimizing the nnU-Net model for brain tumor (Glioma) segmentation Using a BraTS Sub-Saharan Africa (SSA) dataset
arxiv.org·23h
🧠AI
Flag this post
Can AI See the World Like a Cat? Probing Deep Learning's Feline Understanding
dev.to·1d·
Discuss: DEV
🧠AI
Flag this post
Eyes on Target: Gaze-Aware Object Detection in Egocentric Video
arxiv.org·2d
real-time analytics
Flag this post
DentalSplat: Dental Occlusion Novel View Synthesis from Sparse Intra-Oral Photographs
arxiv.org·23h
🤖robotics
Flag this post
HiDream.ai Awards Best Demo at ACM MM 2025: Redefining Conversational Visual Creation
prnewswire.com·20h
🧠AI
Flag this post
Disentangled Concepts Speak Louder Than Words:Explainable Video Action Recognition
arxiv.org·23h
🧠AI
Flag this post