The Visual Computer
Издатель: Springer Nature · ISSN 0178-2789,1432-2315 · 1097 статей
- Diffusion model-based image restoration: interactive learning of determinism and stochasticity
- Perceptually Guided Gaussian Splatting (PGGS): hyperparameter control with perceptual rewards and view augmentation
-
From detection to identity preservation: A pipeline–scenario–protocol–readiness review of datasets for visual multi-person tracking and re-identification
Abstract Multi-person tracking (MPT) requires visual systems to localize people in video frames and preserve their identities over time. Although public datasets have advanced person detection, person re-identification (Re-ID), person...
- Accurate 6D pose estimation using consumer-grade depth cameras in real-world scenarios
- Prompt-to-Grade: closed-loop promptable segmentation and reliability-aware fusion for cine-ultrasound grading
- PoseAlign: sculpting pose-consistent meshes via text-guided deformation
- DGLNet: dynamic global–local context aggregation for lightweight facial expression recognition
- A flow-aware reformulation of reciprocal collision avoidance for crowd evacuation in advective flood fields
- Efficient controllable diffusion via dynamic hybrid attention and decoupled knowledge distillation
- GeoFeatureGS: block-consistent semantic feature learning for large-scale geographic scenes with 3D gaussian splatting
- Occluded person re-identification: a taxonomic survey and reproducible empirical benchmark
- GRPO-SEG: reinforcement learning with hard-sample re-prompting for efficient MLLM-guided Referring Image Segmentation
- L-dance: LLM-guided motion intensity aware natural dance generation
- Infrared–visible image fusion for robust visual perception: methods, benchmarks, evaluation and open challenges
- SC-TAS: stability-constrained task-adaptive saliency for artifact-aware attention transfer in JPEG-compressed images
- Prototype-guided material evidence transfer for hyperspectral street-scene semantic segmentation
- Structurally faithful accelerated MRI reconstruction via edge-memory guided deep unrolling
- Vision-based postural kinematics reveal brain–body workload coupling in ship-motion digital control operation
- Lightweight hierarchical graph neural networks for cloth simulation via scheduled pruning and heterogeneous distillation
- Efficient 3D reconstruction of heritage monuments using symmetry-aware part-based modeling
- Transition-aware sparse attention for long-range single-lead ECG sleep apnea detection
- Cross-modal alignment enhancement for lightweight large vision language models
- DiaVTG: multi-turn reasoning framework for video temporal grounding
- Morphology-aware fractal structural learning for robust ultrasound liver lesion classification
- Enhancing part-level text-to-shape generation through hierarchical structure modeling
- AutoGreen-DocVL: layout-aware visual document understanding for traceable green disclosure evidence recognition
- MD2PLL: a meta-learning framework for robust disambiguation in partial-label visual recognition
- Dynamic concept memory and contrastive feature generation for robust generalized zero-shot learning
- Lightweight weapon detection via fractional-order Legendre polynomials for smart edge devices
- TlMamba: structure-aware Vision Mamba for long-tailed ancient Tai Lue palm-leaf manuscript character recognition