The Visual Computer
Publisher: Springer Nature · ISSN 0178-2789,1432-2315 · 1097 articles
- Reliability-guided token compression for efficient transformer-based visual inference
- Parametric reconstruction of 3D free-form curves from two views
- HMAST: structure-preserving masked autoencoding with swin transformers for long-tailed visual recognition
- Multimodal sound-guided diffusion for high-fidelity fashion image manipulation
- CADF-Net: efficient image super-resolution network based on correlated spatial attention and dynamic fusion
- Video frame interpolation in the era of deep learning and generative AI: a systematic survey
- DAST-Net: dual-stream adaptive spatiotemporal modeling for long-term human motion prediction in human-robot collaborative assembly
- AesMaTF: an efficient Mamba-Transformer hybrid with diagonal selective scanning for image aesthetic assessment
- Physics-aware underwater image enhancement via SAM-guided dual-domain mamba network
- HMFT: a hierarchical multi-embedding fusion transformer for robust multi-object 6D pose estimation for intelligent robots under occlusion and symmetry
- Mamba-based refinement fusion strategy for oriented object detection in remote sensing images
- YOLO-DFA: dynamic feature-aware fusion for small object detection in UAV and remote sensing imagery
- From multimodal fusion to foundation models: a structured review of retinal vessel segmentation for robust visual computing
- SSF-DETR: an adaptive spatial–spectral fusion transformer for robust wind turbine blade surface defect detection
- Object detection and approximate boundary extraction using deep learning-based patch classification and curve evolution
- Reliability-aware conflict calibration for generalized few-shot point cloud segmentation
- Efficient monocular human mesh recovery and dynamic acupoint mapping for digital Traditional Chinese Medicine
- Multiscale local binary patterns across orthogonal planes for robust dynamic texture recognition
- BPC-SLAM: part-level dynamic suppression and structure-constrained RGB-D SLAM for human-centric dynamic environments
- Progressive global-to-local image restoration for structure-preserving shadow removal
- Score-supervised video summarization via Bi-LSTM and multi-head attention with SSV regularization
- Motion-Adaptive soft shift and pyramid-projection binary convolution for low-light raw video denoising
- Temporal channel decomposition fusion: rethinking 3D feature utilization in spatiotemporal action detection
- Efficient depth-guided segmentation: lightweight high-resolution dichotomous image segmentation
- HEFGNet: hierarchically enhanced feature-guided network for fine-grained food image segmentation
- Human pose estimation for visual computing: taxonomy, benchmarks, applications, and emerging foundations
- An attention-driven recurrent network and vision transformer-based assistive model for disability-oriented human activity recognition
- Region-aware adversarial distillation for deployment-efficient lightweight object detection
- Unregistered dermoscopy-guided enhanced super-resolution of clinical skin tumor images via cross-modal GAN
-
Evaluating architectural innovations in deep learning-based image semantic segmentation
Abstract Image semantic segmentation, a pivotal task in computer vision, involves partitioning images into meaningful regions for precise pixel-level classification. Although numerous review articles have summarized advances in deep...