IEEE

AMITA: Attribute-Guided Masked Image-Text Alignment for Multi-Label Image Representation

Abstract: Multi-label image classification, which involves recognizing multiple objects within a single image, is a fundamental task in computer vision. Recently, Visual-Language Models (VLMs) have ...
GitHub

CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning

We are excited to release the CapRL 2.0 series: CapRL-Qwen3VL-2B and CapRL-Qwen3VL-4B. These models feature fewer parameters while delivering even more powerful captioning performance. Notably, ...
GitHub

MR-FIQA: Face Image Quality Assessment with Multi-Reference Representations from Synthetic Data Generation

Stage-1 Generation: The code in this stage is mainly built on the PyTorch framework. Specifically, it requires PyTorch version 1.10.0 or later, along with the ...
IEEE

Robust Image Steganography Approach Based on Edge Detection Combined With CNN Algorithm

Abstract: Image steganography conceals secret data within a cover image to generate a new image (stego image) in a manner that makes the secret data undetectable. The main problem in image ...