Latest AI and machine learning research in identifying and reporting child abuse for healthcare professionals.
Multimodal Large Language Models (MLLMs) have demonstrated strong perception and reasoning capabilities. However, most existing models focus on isolated objects and neglect structured relationships for efficient target navigation, limiting their performance on visually intensive tasks. To address this challenge, we introduce Scene Graph Thinking (SaGe), a novel paradigm that enables fine-grained a...
This paper presents the IEEE International Conference on Multimedia and Expo (ICME) 2026 Grand Challenge on Cross-Scenario Defect Detection and Fine-Grained Severity Grading for High-Precision Manufacturing. The challenge is motivated by two key limitations of existing industrial defect inspection systems: (1) current deep learning-based methods often suffer significant performance degradation whe...
Ultrasound image classification is essential for computer-aided diagnosis. However, current methods often neglect clinical priors, leading to poor gen...
Topological data analysis (TDA), particularly persistent homology (PH), captures geometric structural properties in medical images (e.g., connected co...
Segment Anything Model (SAM) has revolutionized promptable image segmentation with strong zero-shot generalization. However, its performance degrades ...
Grounding deictic gestures in natural images is fundamental to AR and human-robot collaboration, providing a basis for seamless spatial interaction. W...
Purpose: To investigate how artificial intelligence (AI) systems detect referrable diabetic retinopathy (DR) from retinal photographs by analysing hea...
Autoregressive visual models (AVMs) based on next-scale prediction have emerged as a prominent paradigm for image and video synthesis. However, decomp...
Motivation: Proteolysis-targeting chimeras (PROTACs) enable targeted protein degradation through ternary complex formation with E3 ubiquitin ligase. H...
Metastatic breast cancer is one of the leading causes of premature mortality among women worldwide. A major barrier to optimal care is the marked hete...
Visual perception depends on top-down goals and bottom-up sensory mechanisms. Vision-language models implement both, allowing us to treat each compone...
Estimating continuous optical flow is a fundamental yet challenging problem in dynamic visual perception. Event-based cameras, with microsecond latenc...
Vascular circulation follows fundamental biophysical principles that optimize mass transport and metabolic energy expenditure, which can be effectivel...
Estimating continuous optical flow is a fundamental yet challenging problem in dynamic visual perception. Event-based cameras, with microsecond latenc...
Unsupervised fine-grained image hashing aims to learn compact binary codes that preserve subtle visual differences among highly similar instances with...
The release of public 3D medical image segmentation (MIS) datasets accelerates clinical research but simultaneously heightens risks of unauthorized AI...
Accurate image segmentation remains challenging, particularly in generating sharp, confident boundaries. While modern architectures have advanced the ...
Current critic-less RLHF methods aggregate multi-objective rewards via an arithmetic mean, leaving them vulnerable to constraint neglect: high-magnitu...
Despite significant progress, RGB-based trackers remain vulnerable to challenging imaging conditions, such as low illumination and fast motion. Event ...
Recent advances in Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have made it standard practice to reconstruct 3D scenes from multi-v...