Search
Search Results
-
PRON: Proposition-Oriented Repair and Operator Normalization for UMR Parsing
Mapping natural language into auditable inference logic is essential for trustworthy AI in high-stakes legal domains. Existing training-free Uniform...
-
Toward Abstraction-Level Event Retrieval in Large Video Collections: Leveraging Human Knowledge and LLM-Based Reasoning in the Ho Chi Minh City AI Challenge 2025
Large-scale video collections require retrieval systems that understand both semantic content and temporal structure. While vision–language models...
-
VidAlign: Integrating Multi-event Alignment and LLM Co-searching for Video Retrieval
The exponential growth of video content demands efficient retrieval systems capable of understanding complex, multi-event scenarios. In this work, we...
-
Improving Plant Species Distribution Models with Hydrologic and Topographic Features
Species distribution models (SDMs) for plants typically prioritize climate and broad remote sensing while underusing hydrologic and topographic...
-
Applying Large Language Model (LLM) Agents for Automated Lifelog Retrieval
Recent advances in LLMs have enabled new levels of autonomy in complex multimedia retrieval systems. This work introduces an LLM-based Planning Agent...
-
HERF: Hybrid Evidence Retrieval Framework for Entity-Centric Question Answering
Question answering (QA) systems are typically built on either knowledge bases or the open web, each with distinct advantages and limitations....
-
TI-FS: Text and Images Mutual Support for Improving Few-Shot Learning in Cross-Device Image Recapture Detection
Text-image joint training has been extensively employed in computer vision tasks, particularly in cross-device image recapture detection. Moreover,...
-
ICPR 2026 Competition on Low-Resolution License Plate Recognition
Low-Resolution License Plate Recognition (LRLPR) remains a challenging problem in real-world surveillance scenarios, where long capture distances,...
-
Hierarchical Multi-modal Retrieval for Knowledge-Grounded News Image Captioning
Traditional image captioning methods often struggle to generate comprehensive, context-rich descriptions, especially for details not directly...
-
FOAMI: Enhancing ICS Threat Detection via Feature Optimization, Realistic Augmentation, and Mutual Inference
Industrial Control Systems (ICS) are now encountering a multitude of advanced cyber dangers, particularly those associated with the Internet....
-
Fish-Net: An Effective Model for Underwater Fish Detection
The automated detection of fish is growing in demand for different applications, such as aquaculture monitoring and oceanographic research....
-
Nonlinear Dynamic Modeling and Synthetic Data Generation for Multi-fault Diagnosis in Rotor Systems: A 3D Multibody Case Study
Rotor-bearing-coupling systems frequently suffer from complex mechanical faults, notably shaft misalignment and mass imbalance, producing strongly...
-
The ‘Human Firewall’: Enhancing Information Security Awareness and Reducing Cybersecurity Risks in the People’s Credit Fund System
This study investigates the “Human Firewall Gap” in Vietnam’s People’s Credit Fund System (PCFs), where staff possess basic cybersecurity knowledge...
-
EA-LDM: Explicit Alignment Latent Diffusion Model for Patient-Specific CT Reconstruction from Bi-planar X-Rays
Reconstructing 3D CT volumes from bi-planar X-rays offers a low-dose, efficient alternative to CBCT for Adaptive Radiotherapy. However, the...
-
Maximizing Domain Generalization in Automated Fetal Brain Biometry
Reliable fetal brain biometry is important for prenatal neurodevelopmental evaluation and disease diagnosis, yet current clinical practice relies...
-
ALSAnchorNet: Biologically Informed Multimodal MRI Fusion for Amyotrophic Lateral Sclerosis Diagnosis
Deep learning–based multimodal MRI integration for Amyotrophic Lateral Sclerosis (ALS) diagnosis remains largely unexplored. We present ALSAnchorNet,...
-
GeoIdTree: Domain-Adaptive Multi-temporal Plant Identification from Geospatial Orthomosaics and RGB Images
Forest biodiversity conservation requires reliable plant identification across time, yet multi-period recognition remains challenging due to...
-
EcoVLA: Energy-Efficient Device-Edge Co-inference for Vision-Language-Action Models Under Real-Time Constraints
Vision-Language-Action (VLA) models are a promising foundation for Embodied AI, but their high inference cost hinders robotic deployment. On-device...
-
Beyond Consistency: Explicit Boundary Learning for Semi-supervised Ovarian Tumor Segmentation
Accurate segmentation of ovarian tumors in ultrasound images is critical for early diagnosis and risk stratification but remains challenging due to...
-
A Hybrid Quantum-Classical Machine Learning Framework for Robust Sepsis Detection Utilizing Immune Gene Signatures
Sepsis remains a critical medical condition demanding rapid and accurate diagnosis to improve patient outcomes. While gene expression data offers a...
