Multimedia Systems
Издатель: Springer Nature · ISSN 0942-4962,1432-1882 · 1223 статей
-
FADE: feature-aware deterministic pruning for real-time edge video analytics
Multi-stream pedestrian surveillance must adapt to changing crowd conditions under limited edge resources. Our observations motivate jointly adapting resolution, encoding bitrate, and analytics frame rate to maintain detection and...
-
MemSAS: prototype-driven spatio-temporal memory with task-adaptive decoupled features for skeleton-based action segmentation
Skeleton-based temporal action segmentation aims to perform fine-grained action label prediction for each frame on long untrimmed skeleton sequences. However, existing methods often overlook the variations in spatial joint relationships...
-
Evaluation of image person removal tasks: when data synthesis encounters 3D reconstruction
Data synthesis has become an important means of addressing the shortage of data for training deep networks, especially when image–label pairs are hard to collect. This problem is particularly evident in the image person removal task,...
-
Reciprocal multimodal interaction and global semantic calibration for visible-depth-thermal salient object detection
Visible-Depth-Thermal (VDT) salient object detection (SOD) combines complementary appearance, geometric, and thermal cues to locate salient objects reliably in complex environments, especially when individual modalities are degraded....
-
NMGM-VAD: normal memory-guided MIL for weakly-supervised multimodal video anomaly detection
Video anomaly detection (VAD) is critical for intelligent surveillance, yet capturing diverse normal patterns in complex scenes remains a significant challenge. This paper proposes a unified framework via normal memory-guided MIL for...
-
CCUCB-FR: An optimization approach for edge-client collaborative foveated rendering in virtual reality
The rendering of immersive virtual reality (VR) frames currently demands significant computational power to provide users with an optimal VR experience. Edge computing technology is anticipated to offer computational support for VR...
-
CD-SIPO: a cross-dimensional sentiment analysis framework with semantic interaction and path optimization
In Aspect-Based Sentiment Analysis (ABSA), accurately identifying sentiment polarity remains challenging, particularly for sentences with complex structures. Existing methods usually model the relationships between aspects and...
-
ACME: aspect-aware cross-modal mutual enhancement for multimodal aspect sentiment analysis
Multimodal Aspect-Based Sentiment Analysis (MABSA) aims to integrate multimodal information from textual and visual sources to accomplish aspect term extraction and aspect-level sentiment classification in social media content. However,...
-
Recognizing ancient Chinese handwriting of limited samples and tiny variations by data augmentation and contrastive learning
Recognizing ancient Chinese handwriting helps people understand historical texts. However, recognizing ancient Chinese handwriting is challenging due to limited samples, subtle differences between distinct characters, and the lack of a...
-
Process-prior-constrained segmentation for interpretable quality assessment of wafer dicing marks
Wafer dicing marks are typically characterized by slender morphology, low contrast, and strong directional continuity, and their morphological quality directly affects chip yield and packaging reliability. Existing wafer defect...
-
Multi-candidate geometry collaboration for single-anchor 6-DoF pose estimation
Reliable relative pose estimation of previously unseen objects from limited references is important for RGB-D scene analysis and 3D object alignment. Single-anchor 6-DoF pose estimation addresses this task using only one RGB-D anchor...
-
A coarse-to-fine human pose estimation method based on two-stage distillation and progressive graph neural network
Human pose estimation has been widely applied in the human-centric understanding and generation, but most existing state-of-the-art human pose estimation methods require heavy computational resources for accurate predictions. In order...
-
A fast coding unit partition algorithm for VVC intra coding based on a lightweight two-stage neural network decision
Versatile Video Coding (VVC) significantly improves video compression efficiency by introducing a combined partitioning structure comprising quadtrees and multi-type trees (QT + MTT), but this also results in higher encoding complexity....
-
High-fidelity semantic segmentation for dynamic small objects in autonomous driving scenes
Autonomous driving perception relies on accurate semantic segmentation, especially for small, high-dynamic objects such as pedestrians and traffic cones. Existing methods suffer from severe information loss during downsampling, detail...
-
Dual feature modulation for hybrid neural representation-based video compression
Neural representation-based video compression simplifies the coding pipeline and enables fast decoding by mapping video contents into neural network parameters. However, existing methods often suffer from performance degradation in the...
-
Training-free grounded attention decoupling for reliable multi-entity attribute binding in text-to-image diffusion
Text-to-image diffusion models often struggle to bind distinct attributes to multiple entities, particularly when objects share the same semantic class or appear in crowded layouts. We present GSA-Diffusion, a training-free grounded...
-
Full-reference screen content image quality assessment via adaptive fusion of text integrity and visual characteristics
Objective visual quality assessment of screen content images (SCIs) has received increasing attention in recent years due to the increased amount of SCIs on the Internet. In this paper, an effective full-reference SCI quality assessment...
-
Adaptive peer-referenced multimodal learning for robust depression assessment under population heterogeneity
Automated depression assessment using multimodal behavioral signals has shown promising potential for scalable and objective screening. However, achieving reliable performance remains challenging under population heterogeneity,...
-
Lightweight pavement crack detection via feature preservation, enhancement, and propagation
Accurate pavement crack detection is essential for efficient road inspection; however, fine and low-contrast cracks are easily weakened during feature extraction and confused with complex pavement textures. To address these challenges,...
-
SiP-DIF: Siddon sampling-enabled deep intensity field with physical consistency supervision for sparse-view CBCT reconstruction
Cone-beam computed tomography (CBCT) is an important imaging technique that is widely used clinically. However, CBCT scans generate radiation, which may pose health risks to patients. Reducing the number of projection views is one of...
-
GaborMix: Adaptive Gabor configuration mixing for boundary-aware medical image segmentation
Medical image segmentation on 2D images remains challenging, largely due to the ambiguous boundaries between target structures and surrounding tissues. To address this issue, we enhance the boundary representation capability of...
-
Factorized representation disentanglement for unsupervised domain adaptation in video action recognition
Unsupervised domain adaptation (UDA) aims to leverage labeled source-domain data to improve model performance on unlabeled target-domain data with different distributions. Although UDA has been extensively studied in image recognition,...
-
A multidimensional evaluation system for theme-based music generation using AE-VGAN modeling
Recent advances in deep learning have substantially improved the quality of symbolic music generation, but reliable evaluation remains difficult. Existing metrics often focus on isolated statistical or music-theoretical properties and...
-
A unified dual-branch framework for tri-modal medical image fusion and super-resolution
Multimodal medical imaging provides complementary anatomical and functional information for clinical diagnosis, yet low spatial resolution and separated fusion–super-resolution pipelines often weaken modality-specific details and reduce...
-
Zero-shot JPEG image deblocking: leveraging non-local self-similarity for enhanced restoration
JPEG compression produces visually distracting blocking artifacts due to the independent coding of $$8\times 8$$ blocks. This paper presents a dataset-free, single-image internal-learning method for JPEG artifact removal. For each input...
- Damage-aware diffusion restoration of intangible heritage brocade images with pattern-consistency loss
- Sure-detr: semantically unified and resolution-enhanced DETR for UAV object detection
- Bridging spectral and camera gaps: cross-modal self-attention and camera-aware feature calibration for multispectral re-identification
- Lightweight visual detection framework for complex background grape leaf disease detection
- Cross-modal topology preservation for class-incremental audio-visual video recognition