Latest AI and machine learning research in identifying and reporting child abuse for healthcare professionals.
Quantifying uncertainty in neural implicit 3D representations, particularly those utilizing Signed Distance Functions (SDFs), remains a substantial challenge due to computational inefficiencies, scalability issues, and geometric inconsistencies. Existing methods typically neglect direct geometric integration, leading to poorly calibrated uncertainty maps. We introduce BayesSDF, a novel probabili...
This work focuses on modeling dynamic urban environments for autonomous driving simulation. Contemporary data-driven methods using neural radiance fields have achieved photorealistic driving scene modeling, but they suffer from low rendering efficacy. Recently, some approaches have explored 3D Gaussian splatting for modeling dynamic urban scenes, enabling high-fidelity reconstruction and real-ti...
High-definition (HD) map construction methods are crucial for providing precise and comprehensive static environmental information, which is essenti...
MR imaging techniques are of great benefit to disease diagnosis. However, due to the limitation of MR devices, significant intensity inhomogeneity o...
Text-to-image diffusion models often struggle to achieve accurate semantic alignment between generated images and text prompts while maintaining eff...
As the core operator of Transformers, Softmax Attention exhibits excellent global modeling capabilities. However, its quadratic complexity limits it...
Knowledge Tracing (KT), as a pivotal technology in intelligent education systems, analyzes students' learning data to infer their knowledge acquisitio...
Since there exists a notable gap between user-provided and model-preferred prompts, generating high-quality and satisfactory images using diffusion ...
Medical visual question answering (MedVQA) plays a vital role in clinical decision-making by providing contextually rich answers to image-based quer...
Text on historical maps provides valuable information for studies in history, economics, geography, and other related fields. Unlike structured or s...
Few-shot industrial anomaly detection (FS-IAD) presents a critical challenge for practical automated inspection systems operating in data-scarce env...
We develop a mass-conserving, adaptive-rank solver for the 1D1V Wigner-Poisson system. Our work is motivated by applications to the study of the sto...
Estimating single-cell responses across various perturbations facilitates the identification of key genes and enhances drug screening, significantly...
Egocentric video-language understanding demands both high efficiency and accurate spatial-temporal modeling. Existing approaches face three key chal...
Patent images are technical drawings that convey information about a patent's innovation. Patent image retrieval systems aim to search in vast colle...
Incomplete multi-modal medical image segmentation faces critical challenges from modality imbalance, including imbalanced modality missing rates and...
Medical images are usually collected from multiple domains, leading to domain shifts that impair the performance of medical image segmentation model...
Cutting-edge works have demonstrated that text-to-image (T2I) diffusion models can generate adversarial patches that mislead state-of-the-art object...
Driven by advancements in motion capture and generative artificial intelligence, leveraging large-scale MoCap datasets to train generative models fo...
Grounding language to a navigating agent's observations can leverage pretrained multimodal foundation models to match perceptions to object or event...