Multimedia Systems
Издатель: Springer Nature · ISSN 0942-4962,1432-1882 · 1223 статей
- Vision-language integrated video editing: a novel framework for enhanced automatic short video editing
- Geometric and sentence-level semantic information transfer learning for YOLO based saffron stigma detection
- Enhancing object tracking via spatio-temporal collaboration in frame-event networks
- Motion-guided local–global state prediction for 1-ms anomaly detection in fast-moving industrial scenarios
- SUFERNOBWA: satellite image utilization for dehazing with Swin transformer-hybrid U-Net and watershed loss
- All-in-one image restoration via foundation-model-guided dynamic expert kernels and aggregated spectral masking
- DSPPL-MSLU: dynamic exemplar selection with progressive prompt learning model for few-shot multi-intent spoken language understanding
- An image-video framework for LPG leakage detection via weak-structure recovery and temporal evolution modeling
- Captioning daily activity images in early childhood education: benchmark and algorithm
- CCANet: enhancing few-shot semantic segmentation with channel context aggregation
- Edge-UAVDet: a lightweight and efficient real-time small target detection network for UAV traffic scenes
- Synthetic cloud generation using 3D spectral filtering for improved generalization in cloud removal
- Cross-modal consistency gating for reliable LLM reasoning in multimodal sentiment analysis
- CAG-HUGS: context-aware and geometry-constrained 3D Gaussian avatar generation
- IAGDRec: interaction-anchor guided denoising for multimodal recommendation
- TMDKD: tutor-guided multi-dimensional difficulty-aware knowledge distillation
- HiRBP: a VLM-based hierarchical decision-making framework for long-horizon robotic behavior planning (ChinaMM 2026)
- Efficient light field spatial super-resolution via alternating epipolar mamba-transformer modeling
- Detecting video game addiction using facial expression classification: systematic review
- Resource allocation for multimedia’s multicast and broadcast services (MBS) over the vehicular environment based on the novel k-means-di subgrouping mechanism
- Spatiotemporal evolution prediction of coal fissure stress morphology integrating IST-LSTM and E-UNet
- HACI-Net: a hybrid attention and channel interaction network for food image recognition
-
VR video user experience evaluation under visual and temporal variations and machine learning–based cybersickness prediction
Abstract Virtual reality (VR) allows users to experience an engaging and interactive virtual environment. Such experience is often limited by cybersickness, a perceptual discomfort that varies among individuals. Understanding and...
- PolypMSAM-BoxTS: a MedSAM prior-guided weakly supervised polyp segmentation method using bounding boxes
- NF-SAM: frequency-noise collaborative learning for robust image manipulation localization with Segment Anything Model
- Degradation-aware generative stereo image restoration
- SAP2C: automated Eulerian cinemagraph synthesis from a single ancient painting
- ColorFuseNet: hierarchical priority-guided tri-stream diffusion for controllable garment image generation
- MoMKE-AVSR: an audio–visual speech recognition framework based on mixture of modality knowledge experts
- Personal interaction-aware robust multi-domain representation learning for skeleton-based action recognition via asymmetric contrastive learning