The Visual Computer
Издатель: Springer Nature · ISSN 0178-2789,1432-2315 · 1097 статей
- Enhancing scene graph generation via semantic-aligned masked vision-and-language pre-training
- Diffusion-guided knowledge absorption for robust object detection under rainy night conditions
- DuoLit: dual-level priors and gated lighting injection for human material estimation
-
HAT-SAM3: endoscopy-aware adaptation of a foundation segmentation model for generalizable polyp segmentation
Abstract Automatic polyp segmentation remains difficult when models are evaluated outside their training distribution. Polyps vary substantially in scale, shape, color, boundary contrast, and surface appearance; colonoscopy further...
- Residual-driven Chebyshev acceleration for Jacobi Neo-Hookean XPBD solver
- Deep learning-based multi-object tracking: a comprehensive survey from foundations to state-of-the-art
- A new weighted Caputo fractional-order total variation for Cauchy noise removal with Bayesian optimization
- Enhancing face recognition robustness: AdvFaceDefGAN against dual-identity attacks
- 3D object detection using a multi-scale point transformer-RCNN
- JC-STNet: a physics-inspired joint-centric spatiotemporal network for real-time 2D pose estimation
-
Explainable AI for accurate diagnosis of papillary thyroid carcinoma via fine-needle aspiration cytopathology
Abstract Papillary thyroid carcinoma (PTC) represents most thyroid cancer cases worldwide, making early and accurate diagnosis crucial for successful treatment. This study introduces an explainable AI framework for the automated...
- Enhancing image colorization with semantic-guided diffusion and lightweight fine-tuning
- GUIDE: Dual-Gated semantic conditioning with correctable priors for single-image human material estimation
- MRFNet: multi-scale reparameterized fusion network for efficient small object detection in aerial imagery
- KPGBeltNet: in-vehicle seatbelt detection algorithm based on human keypoint-guided sampling and local–global attention
- Bird’s eye view (BEV) features for vulnerable road user intention recognition
- Enhanced saliency detection in remote sensing: a hierarchical adaptive fusion approach
- Enhanced industrial anomaly detection via CutMask data augmentation: a self-supervised approach
- Enhanced bridge crack segmentation via CNN–Mamba dual encoders with edge enhancement
- Feature mixing-driven dynamic contrastive learning for robust source-free unsupervised domain adaptation
- FreDeGS: frequency-guided 3D gaussian splatting for scene deblurring
- Multi-task adaptive CLIP for enhanced person re-identification across domains
- CamPedV2: a diverse real-time pedestrian detection dataset for challenging environmental conditions
- RT-suitedness: predicting hardware ray tracing energy gains from static scene geometry
- Enhancing small object detection: a transformer-based middleware approach
- SPMMSegNet: self-parameterization multi-scale mesh segmentation network for tooth identification
- Advanced background learning for hyperspectral anomaly detection via synthetic spectral sample generation
-
VR-Deform: real-time visual and haptic interaction with deformable bodies using XPBD in virtual reality
Abstract In this paper, we simulate a lifelike interaction with deformable bodies in virtual reality (VR) and provide force haptic feedback. Our method achieves physically compelling responses and stable feedback, which are essential...
- FDMD: feature-enhanced diffusion with multi-step trajectory discrimination for rare anomaly detection in visually protected industrial images
- Frequency-aware optimization for floating artifact removal in 3D Gaussian splatting