Multimedia Systems
Publisher: Springer Nature · ISSN 0942-4962,1432-1882 · 1223 articles
- AIGC-driven traditional music composition and cultural context adaptation studies
- QHSP-Net: query-aware higher-order statistical pooling network for referring image segmentation
- PESSANet: prior-enhanced selectable sparse attention network for image super-resolution
- Diagnosis-driven hard sample generation: low-frequency attenuation supervised contrastive learning for mammogram classification
- Knowledge enhancement with cross-modal fusion network for radiological report generation
-
Multi-task cross-modal attention networks for robust anthropometric prediction
Abstract Accurate estimation of anthropometric attributes (height, weight, and body mass index (BMI)) from facial imagery supports emerging applications in telemedicine, soft biometrics, and large-scale population screening. Existing...
- SGAFusion: a semantic-guided adaptive fusion framework for infrared and degraded visible images
- Lightweight adaptation of CLIP for few-shot plant disease recognition
- DCAFNet: a lightweight network with dynamic context-aware fusion for image deblurring
- Reducing image bias: collaborative multi-role reasoning with adaptive modality filtering for multimodal stance detection (ChinaMM2025–PaperID:119)
- GCGV: a dual-branch hybrid network integrating graph attention, CNNs, and vision transformers for enhanced hyperspectral image classification
- GPLMv2: an edge-ready post-training quantization framework for deploying complex underwater image enhancement models
- A transformer network for video inpainting with optical flow guidance and spatio-temporal decoupling
- Cross-branch knowledge distillation via shallow layer guidance
- Smile: enhancing low-light images in lightweight networks via exposure-aware non-reference losses
- FER-YOLO: a YOLO-based classifier for facial expression recognition
- Enhanced hyperspectral image classification via attention-augmented LSTM-ConvNet (LA-HybridSN)
- Enhancing infrared and visible image fusion through asymmetric Bi-scale decomposition with a novel pyramid filter
- FLIRL-Net: fuzzy logic-driven important relationship learning for scene graph generation
- LATrack: enhancing transformer visual tracking via locality-aware attention
- Dynamic frequency-band filtering domain generalization for mammogram classification
- Cross-view attention enhancement and entropy-constrained contrastive learning for multi-view clustering
- Low-frequency SNR-guided CNN-transformer network for high-frequency restoration in low-light image enhancement
- LEA-depth: a lightweight self-supervised monocular depth estimation with attention fusion and edge-aware distillation
- A method for detecting key points of back acupoints based on deep learning
- CGR: calibrating generative replay for exemplar-free class-incremental learning
- Ultra-lightweight 6-DoF VSLAM with absolute size restoration using low-cost laser beam priors
- An last mile delivery path optimization method aiming at solving the cold start of new users: the migration of user profiling technology in logistics and distribution field
- SpectraMixNet: lightweight multi-scale spectral-frequency attention network for single image dehazing
- Scganet: finger vein recognition based on SCGA modules with a two-way cascade structure