The Visual Computer publishes articles on all research fields of capturing, recognizing, modelling, analysing and generating shapes and images. It includes image understanding, machine learning for graphics and 3D fabrication.3D ReconstructionComputer AnimationComputational FabricationComputational Geometry Computational Photography Computer Vision for Computer Graphics Data Compression for GraphicsGeometric ModellingGeometric ProcessingHCI and Computer GraphicsHuman ModellingImage AnalysisImage Based Rendering Image ProcessingMachine Learning for GraphicsMedical Imaging Pattern RecognitionPhysically Based ModellingIllumination and Rendering Methods Robotics and VisionSaliency Methods Scientific VisualizationShape and Surface ModellingShape Analysis and Image RetrievalShape MatchingSketch-based ModellingSolid ModellingStylized renderingTexturesVirtual and Augmented RealityVisual AnalyticsVolume RenderingAll papers are subject to thorough review and, if accepted, will be revised accordingly. Original contributions, describing advances in the theory in the above mentioned fields as well as practical results and original applications, are invited.
《视觉计算机》发表了关于捕捉、识别、建模、分析和生成形状和图像的所有研究领域的文章。它包括图像理解、用于图形和3D制造的机器学习。3D重建计算机动画计算制造计算几何计算摄影计算机视觉图形数据压缩几何建模几何处理HCI和计算机图形人体建模图像分析基于图像的渲染图像处理图形机器学习医学成像模式识别基于物理的建模照明和渲染方法机器人和视觉显著性方法科学可视化形状和表面建模形状分析和图像检索形状匹配基于草图的建模实体建模风格化渲染纹理虚拟现实和增强现实视觉分析体渲染所有论文都要经过全面审查，如果被接受，将进行相应的修改。欢迎对上述领域的理论进展、实际结果和原始应用进行描述的原始贡献。
Deep convolutional BiLSTM fusion network for facial expression recognition
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01636-3
Joint bilateral propagation upsampling for unstructured multi-view stereo
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01688-5
Stylistic scene enhancement GAN: mixed stylistic enhancement generation for 3D indoor scenes
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01691-w
A lightweight methodology of 3D printed objects utilizing multi-scale porous structures
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01672-z
Cancelable multi-biometric recognition system based on deep learning
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01715-5
An integrated approach for medical abnormality detection using deep patch convolutional neural networks
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01775-7
Dual-modality spatiotemporal feature learning for spontaneous facial expression recognition in e-learning using hybrid deep neural network
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01660-3
Salient object detection via hybrid upsampling and hybrid loss computing
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01659-w
Deep binocular tone mapping
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01669-8
Huber-$$L_1$$L1-based non-isometric surface registration
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01670-1
DTW-CNN: time series-based human interaction prediction in videos using CNN-extracted features
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01722-6
Development and evaluation of a self-training system for tennis shots with motion feature assessment and visualization
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01662-1
Single-image super-resolution via patch-based and group-based local smoothness modeling
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01756-w
Effect of layer-wise fine-tuning in magnification-dependent classification of breast cancer histopathological image
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01768-6
Latent transformations neural network for object view synthesis
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01755-x
Density-based label placement
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01686-7
Fuzzy weighted sparse reconstruction error-steered semi-supervised learning for face recognition
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01746-y
Residual feature pyramid networks for salient object detection
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01779-3
Precomputed optimal one-hop motion transition for responsive character animation
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01693-8
An automatic 3D registration method for rock mass point clouds based on plane detection and polygon matching
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01648-z
High-performance intra-mode accelerator for HEVC
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01764-w
Stereoscopic image stitching with rectangular boundaries
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01694-7
Physically based modeling and animation of landslides with MPM
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01709-3
Tracking and frame-rate enhancement for real-time 2D human pose estimation
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01757-9
Three-dimensional salient point detection based on the Laplace–Beltrami eigenfunctions
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01658-x
Restricted Boltzmann machine as an aggregation technique for binary descriptors
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01782-8
Video stitching based on multi-view spatiotemporal feature points and grid-based matching
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01780-w
Two-attribute e-commerce image classification based on a convolutional neural network
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01763-x
Image-based translucency transfer through correlation analysis over multi-scale spatial color distribution
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01676-9
Segmentation of crowd flow by trajectory clustering in active contours
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01713-7
Interactive animation generation of virtual characters using single RGB-D camera
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01678-7
Robust dense correspondence using deep convolutional features
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01656-z
Depth image upsampling based on guided filter with low gradient minimization
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01748-w
Generation of crowd arrival and destination locations/times in complex transit facilities
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01761-z
Automatic darkest filament detection (ADFD): a new algorithm for crack extraction on two-dimensional pavement images
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01742-2
Preface
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01640-7
Deep generative smoke simulator: connecting simulated and real data
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01738-y
Learning semantic dependencies with channel correlation for multi-label classification
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01731-5
Expressive facial style transfer for personalized memes mimic
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01695-6
A novel deep network and aggregation model for saliency detection
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01781-9
Maximum spatial–temporal isometric cluster for dynamic surface correspondence
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01655-0
Video-based social behavior recognition based on kernel relevance analysis
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01754-y
The Visual SuperTree: similarity-based multi-scale visualization
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01696-5
Using pseudo voxel octree to accelerate collision between cutting tool and deformable objects modeled as linked voxels
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01716-4
Preface
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01712-8
Correction to: DeepLight: light source estimation for augmented reality using deep learning
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01765-9
Multiresolution visualization of massive black oil reservoir models
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01674-x
Correction to: Wire cut of double-sided minimal surfaces
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01629-2
Fine-grained action recognition using multi-view attentions
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01770-y
Correction to: Physics-preserving fluid reconstruction from monocular coupling with SFS and SPH
来源期刊：The Visual ComputerDOI：10.1007/s00371-019-01739-x
