Multimedia Systems
Издатель: Springer Nature · ISSN 0942-4962,1432-1882 · 1223 статей
- A deep unfolding framework for blind super-resolution with Fourier-based estimation and cascaded residual network priors
- LECF-DETR: layer-enhanced collaborative fusion DETR for multispectral object detection
- Fusing object interaction awareness with spatio-temporal rotation for surveillance video synopsis
- HiPDA: hierarchical perceiver-style injection and dual-anchor alignment for multimodal sentiment analysis
-
GameRule: a multi-agent architecture for game behavior specification
Abstract The specification of video-game behavior is commonly expressed through general-purpose scripting, coupling behavior definition to the components, callbacks, and APIs of a particular engine. This paper introduces GameRule , a...
- CSP-HD: confidence-sensitive progressive hierarchical distillation in cross-view geo-localization
- DRARec: diffusion-based representation augmentation for multimodal recommendation
- Co-occurrence graph neural network for recommender systems
- DPCDNet: dual-path color-decoupled network for low-light image enhancement
- Adaptive feature interaction and edge refinement networks for camouflaged object detection
- Structured context augmentation for multimodal LLMs in character art analysis
- Unified feature Gaussian representation for robust camera relocalization
- Register-augmented attention and self-calibrated fusion for robust multimodal sentiment analysis
-
Biovid dataset and challenge: biometric user recognition on smartphone data in real-world conditions
Abstract User authentication is more and more crucial in everyday life, with researchers developing sophisticated, yet easy-to-use, approaches to enforce secure authentication while providing a smooth user experience. This is...
- Multiuser immersive cultural experiences enabled by 5G, AI and free-viewpoint video
- CG-MVC: structure-aware multi-view clustering with entropy-quantile curriculum learning
- Edge-guided attention and multi-scale fusion for high-quality multi-modal image fusion
- Curriculum-based inter-modality contrastive learning for semi-supervised cross-modal retrieval
- DFC-SA-UNet: dynamic fusion with lightweight self-attention for multi-domain semantic segmentation
- Semantic-conditioned temporal structure distillation for audio-text retrieval
- Enhancing target identification and query discrimination for visual grounding
- FSSM: integrating feature modulation and state space model for enhanced ancient mural restoration
- Z-AdaNeRF: Bridging Fidelity and Efficiency via Uncertainty-Driven NeRF for Zero-Shot Arbitrary-Scale Medical Super-Resolution
- CMCL-GF: cross-modal contrastive learning with gated fusion for multimodal depression detection
- ROD-Net: a residual orthogonal decoupling network with semantic-guided interaction for breast ultrasound analysis
- Caspnet:cross-level semantic alignment and structure preservation network for style transfer
- Frequency-aware multimodal fusion framework for emotion recognition in conversation
- Multi-guided and pixel enhancement model for radiology report generation
- Enhancing stylistic discrimination in digital art: a multi-channel fractal descriptor for large-scale image analysis
- An intelligent composition system for Chinese art songs via a cascaded pipeline of symbolic music generation and LLM-based lyric writing