Update Dates 1803

1803 * *ICIP
* 3-D mean-separation-type short-time DFT with its application to moving-image denoising
* 360-degree video stitching for dual-fisheye lens cameras based on rigid moving least squares
* 3D convolutional neural network with multi-model framework for action recognition
* 3D convolutional neural networks by modal fusion
* 3D georegistration of wide area motion imagery by combining SFM and chamfer alignment of vehicle detections to vector roadmaps
* 3D Mesh coding with predefined region-of-interest
* 3D point cloud registration with shape constraint
* 4D effect classification by encoding CNN features
* 4K-UHD real-time HEVC encoder with GPU accelerated motion estimation
* Abnormal event detection in videos using generative adversarial nets
* Abnormal motion detection in video using statistics of spatiotemporal local kinematics pattern
* Accelerated RANSAC for 2D homography estimation based on global brightness consistency
* Accelerating discrete wavelet transforms on GPUS
* Accelerating spectral unmixing by using clustered images
* Accuracy prediction for pedestrian detection
* Accurate dense stereo matching for road scenes
* Accurate heart-rate estimation from face videos using quality-based fusion
* Accurate mesh-based alignment for ground and aerial multi-view stereo models
* accurate saliency prediction method based on generative adversarial networks, An
* Accurate small object detection via density map aided saliency estimation
* Accurate tumor segmentation in FDG-PET images with guidance of complementary CT images
* Action recognition in RGB-D egocentric videos
* Action recognition using spatio-temporal differential motion
* Action recognition with gradient boundary convolutional network
* Active convolutional neural networks for cancerous tissue recognition
* Adaboost-based detection and segmentation of bioresorbable vascular scaffolds struts in IVOCT images
* Adaptive cascade threshold learning from negative samples for deformable part models
* Adaptive code embedding for reversible data hiding in encrypted images
* Adaptive feature representation for visual tracking
* Adaptive image contrast enhancement using artificial bee colony optimization
* Adaptive interpolated motion compensated prediction
* Adaptive interpolation filter scheme in AV1
* Adaptive local spatial modeling for online change detection under abrupt dynamic background
* Adaptive optimal bit-depth estimation in compressed video sensing
* Adaptive people detection based on cross-correlation maximization
* adaptive perceptual quantization method for HDR video coding, An
* Adaptive thresholding HOSVD algorithm with iterative regularization for image denoising
* Addressing ambiguity in multi-target tracking by hierarchical strategy
* ADMM penalty parameter selection with Krylov subspace recycling technique for sparse coding
* aerial change detection system using multiple detector fusion and adaboost classification, An
* Age group classification in the wild with deep RoR architecture
* Age-dependent saccadic models for predicting eye movements
* Air-writing recognition using reverse time ordered stroke context
* Aligned discriminative pose robust descriptors for face and object recognition
* Alignment of optic nerve head optical coherence tomography B-scans in right and left eyes
* All the people around me: Face discovery in egocentric photo-streams
* Analysis-operator guided simultaneous tensor decomposition and completion
* Analysis/synthesis coding of dynamic textures based on motion distribution statistics
* Anomaly detection in thermal images using deep neural networks
* Appearance and motion based deep learning architecture object detection in moving camera
* ArtGAN: Artwork synthesis with conditional categorical GANs
* Asymmetric circular projection for dynamic virtual reality video stream switching
* Attribute-controlled face photo synthesis from simple line drawing
* Audio-visual attention: Eye-tracking dataset and analysis toolbox
* Augmented convolutional feature maps for robust CNN-based camera model identification
* Automated 3D Muscle Segmentation from MRI Data Using Convolutional Neural Network
* Automatic 2D-to-3D conversion using multi-scale deep neural network
* Automatic 3-D muscle and fat segmentation of thigh magnetic resonance images in individuals with spinal cord injury
* Automatic 3D modelling for prostate cancer brachytherapy
* Automatic delineation of macular regions based on a locally defined contrast function
* Automatic estimation of deterioration level on transmission towers via deep extreme learning machine based on local receptive field
* Automatic estimation of ice bottom surfaces from radar imagery
* automatic image registration evaluation model on dense feature points by pinhole camera simulation, An
* Automatic martian dust storm detection via decision level fusion basedondeep extreme learning machine
* Automatic recognition of common Arabic handwritten words based on OCR and N-GRAMS
* Avoiding bleeding in image blending
* Bact-3D: A level set segmentation approach for dense multi-layered 3D bacterial biofilms
* BAFT: Binary affine feature transform
* Batch-normalized recurrent highway networks
* Bee pose estimation from single images with convolutional neural network
* Better than real: Complex-valued neural nets for MRI fingerprinting
* Bi-directional long short-term memory architecture for person re-identification with modified triplet embedding
* bidirectional adaptive bandwidth mean shift strategy for clustering, A
* Binary hashing using siamese neural networks
* Blind high dynamic range image quality assessment using deep learning
* Blind hyperspectral image super resolution via simultaneously sparse and TV constraint
* Blind image deblurring using class-adapted image priors
* Blind image quality assessment in the complex frequency domain
* Blind image restoration utilizing total variation regularization, shock filter and gradient reliability map
* Blind quality assessment of multiply-distorted images based on structural degradation
* Blind video quality assessment based on spatio-temporal internal generative mechanism
* Block-wise lensless compressive camera
* Blurriness-guided unsharp masking
* Boundary aware image segmentation with unsupervised mixture models
* Building an ensemble classifier using ensemble margin. Application to image classification
* BYNET-SR: Image super resolution with a bypass connection network
* Camera model identification with residual neural network
* Camera spectral sensitivity, illumination and spectral reflectance estimation for a hybrid hyperspectral image capture system
* Camera-specific image quality enhancement using a convolutional neural network
* Can no-reference image quality metrics assess visible wavelength iris sample quality?
* Cardiac motion estimation in ultrasound images using spatial and sparse regularizations
* Cascade support vector regression-based facial expression-aware face frontalization
* cascaded long short-term memory (LSTM) driven generic visual question answering (VQ
* Cascaded temporal spatial features for video action recognition
* Category independent object proposals using quantum superposition
* Cell segmentation based on spatial information improved intuitionistic fcm combined with FOPSO
* CGAN-plankton: Towards large-scale imbalanced class generation and fine-grained classification
* CHAM: Action recognition using convolutional hierarchical attention model
* Chroma adjustment for HDR video
* Circle detection by arc-support line segments
* Circlet based framework for optic disk detection
* Class-specific image denoising using importance sampling
* Class-specific poisson denoising by patch-based importance sampling
* Classification approach based on the product of riemannian manifolds from Gaussian parametrization space
* Classification of multi-focal nematode image stacks using a projection based multilinear approach
* Cloud tracking for solar irradiance prediction
* Cluster convolutional neural networks for facial age estimation
* CNN based post-processing to improve HEVC
* CNN-based pre-processing and multi-frame-based view transformation for fisheye camera-based AVM system
* CNN-LSTM framework for authorship classification of paintings, A
* Co-saliency detection via seed propagation over the integrated graph with a cluster layer
* Coding block-level perceptual video coding for 4:4:4 data in HEVC
* Coding sensitive based approximation algorithm for power efficient VBS-DCT VLSI design in HEVC hardwired Intra encoder
* Color correction of underwater images based on multi-illuminant estimation with exposure bracketing imaging
* Color reduction based on human categorical perception
* Color representation in deep neural networks
* Color transfer for underwater dehazing and depth estimation
* Colour normalization of fundus images based on geometric transformations applied to their chromatic histogram
* Combining gaze and demographic feature descriptors for autism classification
* Community detection using random-walk similarity and application to image clustering
* Comp-LOP: Complex form of local orientation plane for object tracking
* Compact image representation by binary component analysis
* Compact LBP and WLBP descriptor with magnitude and direction difference for face recognition
* Comparing optical to digital metrics: What is the optimal defocus in a rotationally symmetric system?
* comparison of modified evolutionary computation algorithms with applications to three-dimensional endoscopic camera motion tracking, A
* Comparison of objective functions in CNN-based prostate magnetic resonance image segmentation
* Complementary features for radiomic analysis of malignant and benign mediastinal lymph nodes
* Complex coefficient representation for IIR bilateral filter
* Complex nonseparable oversampled lapped transform for sparse representation of millimeter wave radar image
* comprehensive framework for early assessment of lung injury, A
* Compressed sensing MRI using total variation regularization with K-space decomposition
* Compressed-domain video classification with deep neural networks: There's way too much information to decode the matrix
* Compression efficiency of the emerging video coding tools
* Compression of 3-D point clouds using hierarchical patch fitting
* Compressive image recovery using recurrent generative model
* Computed Tomography Super-Resolution Using Convolutional Neural Networks
* consistent two-level metric for evaluation of automated abandoned object detection methods, A
* Construction of polarization images from a multimod light field camera based on the aliasing model
* Content adaptive quantization parameter cascading for random-access structure in HEVC
* Content adaptive video summarization using spatio-temporal features
* Content-aware neuron image enhancement
* Context multi-task visual object tracking via guided filter
* Context-aware cascade network for semantic labeling in VHR image
* Context-based occlusion detection for robust visual tracking
* Context-based octree coding for point-cloud video
* Continuous detection and recognition of actions of interest among actions of non-interest using a depth camera
* Continuous facial expression recognition for affective interaction with virtual avatar
* Contrast-accumulated histogram equalization for image enhancement
* Contrastive-center loss for deep neural networks
* Contribution-based feature transfer for JPEG mismatched steganalysis
* Convex dictionary learning for single image super-resolution
* Convolutional cost aggregation for robust stereo matching
* Convolutional factor analysis inspired compressive sensing
* Convolutional feature pyramid fusion via attention network
* Convolutional gated recurrent networks for video segmentation
* convolutional neural network framework for blind mesh visual quality assessment, A
* Convolutional neural network-based depth image artifact removal
* Convolutional neural networkasa feature extractor for automatic polyp detection
* Convolutional neural networks and training strategies for skin detection
* Convolutional neural networks for license plate detection in images
* Copy move forgery detection with similar but genuine objects
* Correlation model selection for interactive video communication
* Correlation preserving on graphs for image denoising
* Correlation-based deblurring leveraging multispectral chromatic aberration in color and near-infrared joint acquisition
* Cost efficient subcategory-aware CNN for object detection
* Coupled analysis-synthesis dictionary learning for person re-identification
* Coupled cascade regression for simultaneous facial landmark detection and head pose estimation
* critical analysis of the methods of evaluating MRI brain segmentation algorithms, A
* Cross-age face recognition using reference coding with kernel direct discriminant analysis
* Cross-scale color image restoration under high density Salt-and-Pepper Noise
* CSFM: Community-based structure from motion
* CSMSDL: A common sequential dictionary learning algorithm for multi-subject FMRI data sets analysis
* CVIQD: Subjective quality evaluation of compressed virtual reality images
* Dancing like a superstar: Action guidance based on pose estimation and conditional pose alignment
* Data driven coded aperture design for depth recovery
* data-driven approach to feature space selection for robust micro-endoscopic image reconstruction, A
* Data-driven assimilation of irregularly-sampled image time series
* database for perceptual evaluation of image aesthetics, A
* DCT-based image up-sampling using anchored neighborhood regression
* Dct/dwt blind multiplicative watermarking through student-t distribution
* Decoder side merge mode and AMVP in HEVC screen content coding
* Deep active learning for image classification
* Deep blind image quality assessment by employing FR-IQA
* Deep class-aware image denoising
* deep CNN method for underwater image enhancement, A
* Deep CNN with color lines model for unmarked road segmentation
* Deep convolutional particle filter for visual tracking
* Deep Decomposition of Circularly Symmetric Gabor Wavelet for rotation-invariant texture image classification
* Deep dictionary learning for fine-grained image classification
* Deep discovery of facial motions using a shallow embedding layer
* Deep embedding network for robust age estimation
* Deep feature matching for dense correspondence
* Deep joint discriminative learning for vehicle re-identification and retrieval
* Deep learning architecture for pedestrian 3-D localization and tracking using multiple cameras
* Deep learning for 3D shape classification from multiple depth maps
* deep learning network for vision-based vacant parking space detection system, A
* Deep learning prototype domains for person re-identification
* Deep multi-resolution color constancy
* Deep multi-task learning for gait-based biometrics
* Deep network for image super-resolution with a dictionary learning layer
* Deep network-based image coding for simultaneous compression and retrieval
* Deep neural networks on graph signals for brain imaging analysis
* Deep partial person re-identification via attention model
* Deep pedestrian attribute recognition based on LSTM
* Deep regional feature pooling for video matching
* Deep saliency map estimation of hand-crafted features
* Deep stereo confidence prediction for depth estimation
* Deep tracking with objectness
* Deep-based fisher vector for mobile visual search
* Deep-learning-assisted visualization for live-cell images
* Deep-mapnets: A residual network for 3D environment representation
* Deformable multi-scale scheme for biometric personal identification
* Deformation transfer of 3D human shapes and poses on manifolds
* Demonstration abstract: Motion-consistent video inpainting
* Demonstration of a simple free viewpoint television system
* Demonstration of an HMM-based photorealistic expressive audio-visual speech synthesis system
* Demonstration of rapid frequency selective reconstruction for image resolution enhancement
* Denoising radio interferometric images by subspace clustering
* Dense non-rigid structure-from-motion made easy: A spatial-temporal smoothness based solution
* Densely connected deconvolutional network for semantic segmentation
* DenseNet for dense flow
* Depth map super-resolution using non-local higher-order regularization with classified weights
* Depth modelling mode decision for depth intra coding via good feature
* Depth prediction from a single image with conditional adversarial networks
* Depth upsampling by depth prediction
* Depth-aware object instance segmentation
* Depth-weighted correlation method for visual tracking with occlusion detection
* Detect face in the wild using CNN cascade with feature aggregation at multi-resolution
* Detecting anti-forensic attacks on demosaicing-based camera model identification
* Detection of gastric cancer risk from X-ray images via patch-based convolutional neural network
* Detection of microaneurysm using local rank transform in color fundus images
* Detector with focus: Normalizing gradient in image pyramid
* Dictionary learning-based image compression
* Diffuse-specular separation of multi-view images under varying illumination
* Digital image correlation to analyze nonlinear elastic behavior of materials
* Direct multi-scale dual-stream network for pedestrian detection
* directed graph approach to active contours, A
* Discriminative canonical correlation analysis network for image classification
* Disparity adapted weighted aggregation for local stereo
* Diversity encouraging ensemble of convolutional networks for high performance action recognition
* Diversity-induced weighted classifier ensemble learning
* divisive normalization transform based reduced-reference image quality assessment in the shearlet domain, The
* Do we really need more training data for object localization
* Double random scrambling encoding in the RPMPFrHT domain
* Dual domain video denoising with optical flow estimation
* Dynamic texture recognition using multiscale PCA-learned filters
* Edge-aware integration model for semantic labeling of rare classes
* Edge/structure preserving smoothing via relativity-of-Gaussian
* Effect of visualization techniques on subjective quality of light field images
* Effect of wavelet and hybrid classification on action recognition
* Efficient cloud detection in remote sensing images using edge-aware segmentation network and easy-to-hard training strategy
* efficient deep neural networks training framework for robust face recognition, An
* Efficient directional and L1-optimized intra-prediction for light field image compression
* Efficient estimation of target detection quality
* efficient haze removal algorithm using chromatic properties, An
* Efficient improvement method for separation of reflection components based on an energy function
* efficient intra coding algorithm based on statistical learning for screen content coding, An
* efficient local method for stereo matching using daisy features, An
* Efficient similarity learning for asymmetric hashing
* Efficient symmetry-driven fully convolutional network for multimodal brain tumor segmentation
* Efficiently building 3D line model with points
* Elmnet: Feature learning using extreme learning machines
* Encyclopedia enhanced semantic embedding for zero-shot learning
* End-to-end binary representation learning via direct binary embedding
* Energy based fast event retrieval in video with temporal match kernel
* Enhanced dictionary pair learning sparse representation model for facial expression classification
* Enhanced object detection via fusion with prior beliefs from image classification
* Enhanced trajectory-based action recognition using human pose
* Enhancement of phase detection for autofocus
* Enhancing feature discrimination for unsupervised hashing
* Enhancing the perception of a hazy visual world using a see-through head-mounted device
* Ensemble diversity analysis on remote sensing data classification using random forests
* Ensemble of active contour based image segmentation
* error-resilient video coding framework with soft reset and end-to-end distortion optimization, An
* Estimation of signal-dependent noise level function using multi-column convolutional neural network
* Evaluating the quality of binary partition trees based on uncertain semantic ground-truth for image segmentation
* evaluation of region based object detection strategies within X-ray baggage security imagery, An
* Evidence of change blindness in subjective image fidelity assessment
* Exploiting probabilistic relationships between action concepts for complex event classification
* Exploring the influence of feature representation for dictionary selection based video summarization
* Exponential coordinates based rotation stabilization for panoramic videos
* Extended conjugate polar fourier transform in convolution network
* Extending the FOV from disparity and color consistencies in multiview light fields
* Extracting key frames from first-person videos in the common space of multiple sensors
* Fabric defect detection based on improved low-rank and sparse matrix decomposition
* Face aging with conditional generative adversarial networks
* Face anti-spoofing via deep local binary patterns
* Face hallucination using region-based deep convolutional networks
* Face recognition by facial attribute assisted network
* Face recognition by landmark pooling-based CNN with concentrate loss
* Face Recognition Using Multi-Modal Low-Rank Dictionary Learning
* Face spoofing detection by fusing binocular depth and spatial pyramid coding micro-texture features
* Facial analysis in the wild with LSTM networks
* Facial expression recognition using SVM classification on mic-macro patterns
* family of risk estimators as criteria for PSF estimation: From SURE to GCV, A
* Fast action localization based on spatio-temporal path search
* Fast aircraft detection based on region locating network in large-scale remote sensing images
* Fast and accurate image recognition using Deeply-Fused Branchy Networks
* Fast and accurate segmentation of the LV in MR volumes using a deformable model with dynamic programming
* Fast and reliable human action recognition in video sequences by sequential analysis
* Fast camera fingerprint matching in very large databases
* Fast de-streaking method using plain neural network
* Fast exposure fusion using exposedness function
* Fast high-dimensional filtering using clustering
* Fast initialization for feature-based monocular slam
* Fast mode decision algorithm for HEVC screen content intra coding
* Fast point cloud compression via reversible cellular automata block transform
* Fast template matching for intra prediction
* Feature extraction using gaze of participants for classifying gender of pedestrians in images
* Feature sampling strategies for action recognition
* Filling the gaps: Reducing the complexity of networks for multi-attribute image aesthetic prediction
* Fingertip detection based on protuberant saliency from depth image
* Fisher vector based CNN architecture for image classification
* Fitness heart rate measurement using face videos
* Flexible 3D neighborhood cascade deformable part models for object detection
* Flicker removal and superpixel-based motion tracking for high speed videos
* Focus prior estimation for salient object detection
* Foreground detection in camouflaged scenes
* Fovea weighting of multiview computational displays for enhanced user experience
* Foveated neural network: Gaze prediction on egocentric videos
* Foveated nonlocal dual denoising
* frame rate dependent video quality metric based on temporal wavelet decomposition and spatiotemporal pooling, A
* From foot to head: Active face finding using deep Q-learning
* From neonatal to adult brain MR image segmentation in a few seconds using 3D-like fully convolutional network and transfer learning
* FSVO: Semi-direct monocular visual odometry using fixed maps
* Full-reference stereoscopic image quality assessment accounting for binocular combination and disparity information
* Fully automated highly accurate 3D reconstruction from multiple views
* Fully connected CRF with data-driven prior for multi-class brain tumor segmentation
* Fusing shape and motion matrices for view invariant action recognition using 3D skeletons
* Fusion of multi-angular aerial images based on epipolar geometry and matrix completion
* Gabor feature fusion framework for hyperspectral imagery classification, A
* Gate connected convolutional neural network for object tracking
* Gated additive skip context connection for object detection
* Gaussian blur estimation for photon-limited images
* Gaussian process dynamic modeling of bat flapping flight
* Gender classification in live videos
* general form of illumination-invariant descriptors in variational optical flow estimation, A
* Generalized pooling pyramid with hierarchical dictionary sparse coding for event and object recognition
* Generating adaptive and robust filter sets using an unsupervised learning framework
* Geometric derived motion vector for motion prediction in block-based video coding
* Geometric distortion metrics for point cloud compression
* Gland segmentation guided by glandular structures: A level set framework with two levels
* Global and locally adaptive warped motion compensation in video compression
* Global multiview registration using non-convex ADMM
* Global quality of assessment and optimization for the backward-compatible stereoscopic display system
* Good group sparsity prior for light field interpolation
* GPGPU implementation of VP9 in-loop deblocking filter and improvements for AV1 codec
* GPU Based fast MPEG-CDVS encoder
* GPU-friendly EBCOT variant with single-pass scan order and raw bit plane coding
* GraDED: A graph-based parametric dictionary learning algorithm for event detection
* Grain segmentation of multi-angle petrographic thin section microscopic images
* Granularity-based interactive image display
* Graph fourier transform with negative edges for depth image coding
* graph laplacian matrix learning method for fast implementation of graph fourier transform, A
* graph-based approach for feature extraction and segmentation of multimodal images, A
* Graph-based light fields representation and coding using geometry information
* Graph-theoretic spatiotemporal context modeling for video saliency detection
* Greedy Bayesian double sparsity dictionary learning
* Greedy deep transform learning
* Ground2sky label transfer for fine-grained aerial car recognition
* Group-based truncated L1_2 model for image inpainting
* Hand gesture recognition based on Bayesian sensing hidden Markov models and Bhattacharyya divergence
* Hand gesture recognition using a skeleton-based feature representation with a random regression forest
* hand pose tracking benchmark from stereo matching, A
* Hardware-friendly inter prediction techniques for AV1 video coding
* HazeRD: An outdoor scene dataset and benchmark for single image dehazing
* Head pose estimation using learned discretization
* Heterogeneous face recognition via grassmannian based nearest subspace search
* HEVC-based compression of high bit-depth 3D seismic data
* HGO-CNN: Hybrid generic-organ convolutional neural network for multi-organ plant classification
* Hierarchical bilinear network for high performance face detection
* hierarchical feature model for multi-target tracking, A
* High angular resolution light field reconstruction with coded-aperture mask
* High dynamic range imaging using camera arrays
* High quality reconstruction of dynamic objects using 2D-3D camera fusion
* High-order local normal derivative pattern (LNDP) for 3D face recognition
* High-resolution spectral image reconstruction based on compressed data fusion
* highly accurate facial region network for unconstrained face detection, A
* Highly parallel HEVC motion estimation based on multiple temporal predictors and nested diamond search
* HMM based speech-driven 3D tongue animation
* HOGMep: Variational Bayes and higher-order graphical models applied to joint image recovery and segmentation
* Human action recognition by fusing deep features with Globality Locality Preserving Canonical Correlation Analysis
* Human skeleton tree recurrent neural network with joint relative motion feature for skeleton based action recognition
* Human visual system inspired saliency guided edge preserving tone-mapping for high dynamic range imaging
* Human-human interaction recognition based on spatial and motion trend feature
* Hybrid salient motion detection using temporal differencing and Kalman filter tracking with non-stationary camera
* Hybrid structure hypergraph for online deformable object tracking
* Hyper-parameter optimization for convolutional neural network committees based on evolutionary algorithms
* Hyper-voxel based deep learning for hyperspectral image classification
* Hyperlapse generation of omnidirectional videos by adaptive sampling based on 3D camera positions
* Hyperspectral image classification via shape-adaptive deep learning
* Hyperspectral image coding using graph wavelets
* Hyperspectral image denoising based on global and non-local low-rank factorizations
* Hyperspectral image inpainting based on collaborative total variation
* Hyperspectral image super-resolution based on non-factorization sparse representation and dictionary learning
* Hyperspectral image super-resolution via convolutional neural network
* I2T2I: Learning text to image synthesis with textual data augmentation
* Identifying photorealistic computer graphics using convolutional neural networks
* Image deblurring in the presence of salt-and-pepper noise
* Image denoising using group sparsity residual and external nonlocal self-similarity prior
* Image enhancement method for underwater images based on discrete cosine eigenbasis transformation
* Image filter identification using demosaicing residual features
* Image fusion via dynamic gradient sparsity and anisotropic spectral-spatial total variation
* Image guided depth enhancement via deep fusion and local linear regularizaron
* Image level color classification for colorblind assistance
* Image noise estimation and removal considering the bayer pattern of noise variance
* Image quality assessment to enhance infrared face recognition
* image reconstruction framework based on deep neural network for electrical impedance tomography, An
* Image retrieval based on LRGA algorithm and relevance feedback for insect identification
* Image retrieval by subspace-projected color and texture features
* Image segmentation using contour, surface, and depth cues
* Image super-resolution via deep dilated convolutional networks
* Image-Based Air Quality Analysis Using Deep Convolutional Neural Network
* Image-based measurement of cargo traffic flow in complex neurite networks
* IMM filter based local graph matching for plant cell lineage estimation
* Improved image selection for focus stacking in digital photography
* Improved scene capture in unfavorable lighting conditions
* Improving 3D reconstruction tracks using denoised euclidean distance matrices
* Improving channel features using statistical analysis for pedestrian detection
* Improving human action recognitionby temporal attention
* Improving spatial image adaptive steganalysis incorporating the embedding impact on the feature
* Improving the discrimination between foreground and background for semantic segmentation
* In-bed patient motion and pose analysis using depth videos for pressure ulcer prevention
* Incorporating a locally estimated appearance model in the graphcuts algorithm to extract small hepatic vessels
* Incremental zero-shot learning based on attributes for image classification
* Individual trait oriented scanpath prediction for visual attention analysis
* Inner cell mass segmentation in human HMC embryo images using fully convolutional network
* Inpainting-Based camera anonymization
* Instance flow based online multiple object tracking
* Integrated 3D feature augmentation and view selection in commercial product search
* integrated approach to visual attention modelling using spatial-temporal saliency and objectness, An
* Integrated deep and shallow networks for salient object detection
* Integrated metric learning with adaptive constraints for person re-identification
* Integrating thor tools into the emerging AV1 codec
* Integration of discriminative features and similarity-preserving encoding for finger vein image retrieval
* Integration of precise iris localization into active appearance models for automatic initialization and robust deformable face tracking
* Intelligent detail enhancement for differently exposed images
* Inter-camera tracking based on fully unsupervised online learning
* Interaction-free hand segmentation using kinect camera
* Interactive exploration of microstructural features in gigapixel microscopy images
* Interpreting plenoptic images as multi-view sequences for improved compression
* Intra prediction using fully connected network for video coding
* Investigating the impact of high frame rates on video compression
* IOD-CNN: Integrating object detection networks for event recognition
* Iterative convolutional neural network for noisy image super-resolution
* Iterative fitting after elastic registration: An efficient strategy for accurate estimation of parametric deformations
* Iterative fitting after elastic registration: An efficient strategy for accurate estimation of parametric deformations
* Joint coarse-and-fine reasoning for deep optical flow
* Joint demosaicing and denoising of noisy bayer images with ADMM
* Joint denoising and decompression: A patch-based Bayesian approach
* Joint effect of stalling and presentation quality on the quality-of-experience of streaming videos
* Joint label-interaction learning for human action recognition
* joint multi-scale convolutional network for fully automatic segmentation of the left ventricle, A
* Joint nonlocal sparse representation for depth map super-resolution
* Joint texture and depth map coding for error-resilient 3-D video transmission
* Joint tracking and gait recognition of multiple people in video
* Joint weber-based rotation invariant uniform local ternary pattern for classification of pulmonary emphysema in CT images
* Kernel estimation for motion blur removal using deep convolutional neural network
* Kernel generalized Gaussian and robust statistical learning for abnormality detection in medical images
* Keyword-based image color re-rendering with semantic segmentation
* Kinetic measures for distinguishing vulnerable from stable atherosclerotic plaque with dynamic contrast-enhanced MRI
* Kinship verification based on status-aware projection learning
* Label consistent matrix factorization based hashing for cross-modal retrieval
* Label propagation based saliency detection via graph design
* Lagrangian method based Rate-Distortion Optimization revisited for dependent video coding
* Landmark based head pose estimation benchmark and method
* Large receptive field convolutional neural network for image super-resolution
* Latent fingerprint enhancement using Gabor and minutia dictionaries
* Layered-givens transforms: Tunable complexity, high-performance approximation of optimal non-separable transforms
* Leaf classification based on a quadratic curved axis
* Leaf classification using marginalized shape context and shape-texture dual-path deep convolutional neural network
* Learnable contextual regularization for semantic segmentation of indoor scene images
* Learning a cross-modal hashing network for multimedia search
* Learning a low-coherence dictionary to address spectral variability for hyperspectral unmixing
* Learning autoencoders with low-rank weights
* Learning circulant support vector machines for fast image search
* Learning deep and compact models for gesture recognition
* Learning discriminant grassmann kernels for image-set classification
* Learning natural statistics of binocular contrast for no reference quality assessment of stereoscopic images
* Learning optimal parameters for binary sensing image reconstruction algorithms
* Learning separable transforms by inverse covariance estimation
* Learning supervised binary hashing: Optimization vs diversity
* Learning the weight matrix for sparsity averaging in compressive imaging
* Learning to generate images with perceptual similarity metrics
* Learning to segment on tiny datasets: A new shape model
* Learning-based human detection applied to RGB-D images
* Learning-based tone mapping operator for image matching
* Lenslet image compression using adaptive macropixel prediction
* Lesion detection using T1-weighted MRI: A new approach based on functional cortical ROIs
* level set method for convexity preserving segmentation of cardiac left ventricle, A
* level-map approach to transform coefficient coding, A
* Level-set formulation based on Otsu method with morphological regularization
* Lidarbox: A fast and accurate method for object proposals VIA lidar point clouds for autonomous vehicles
* Lifting-based Illumination Adaptive Transform (LIAT) using mesh-based illumination modelling
* Light field image coding via linear approximation prior
* Light field local binary patterns description for face recognition
* Light field super-resolution using internal and external similarities
* Light transport component decomposition using multi-frequency illumination
* Light-field flow: A subpixel-accuracy depth flow estimation with geometric occlusion model from a single light-field image
* Light-field image compression based on variational disparity estimation and motion-compensated wavelet decomposition
* Linear approximation of mean curvature
* local descriptor for high-speed and high-performance pictogram matching, A
* Local voxelized structure for 3D local shape description: A binary representation
* Localized multi-kernel discriminative canonical correlation analysis for video-based person re-identification
* Localizing body joints from single depth images using geodetic distances and random tree walk
* Locally preserving projection on symmetric positive definite matrix lie group
* Locally-adapted convolution-based super-resolution of irregularly-sampled ocean remote sensing data
* Long-term object tracking based on siamese network
* Loosecut: Interactive image segmentation with loosely bounded boxes
* Lossless compression of CFA sampled image using decorrelated Mallat wavelet packet decomposition
* Lossy compression of lenslet images from plenoptic cameras combining sparse predictive coding and JPEG 2000
* Low complexity image fusion in bayer domain using a monochrome sensor and bayer sensor
* Low complexity video coding based on spatial resolution adaptation
* Low power depth estimation for time-of-flight imaging
* low-complexity metric for the estimation of perceived chrominance sub-sampling errors in screen content images, A
* Low-light image enhancement using CNN and bright channel prior
* Low-light pedestrian detection from RGB images using multi-modal knowledge distillation
* Low-rank matrix completion against missing rows and columns with separable 2-D sparsity priors
* LRR-based hyperspectral image restoration by exploiting the union structure of spectral space and with robust dictionary estimation
* Lucky DCT aggregation for camera shake removal
* Luma-aware multi-model rate-control for HDR content in HEVC
* Making the torch lighter: Areinforced active sampling framework for image classification
* Malignancy characterization of hepatocellular carcinoma using hybrid texture and deep features
* map estimation algorithm for Bayesian polynomial regression on riemannian manifolds, A
* Mass segmentation in mammograms: A cross-sensor comparison of deep and tailored features
* Meshflow video denoising
* method for resizing images by content perception, A
* Metric learning based on attribute hypergraph
* MF-LRTC: Multi-filters guided low-rank tensor coding for image restoration
* Microstructure analysis of silk samples using mueller matrix determination and sparse representation
* Microvasculature segmentation of arterioles using deep CNN
* Mixed sparsity regularized multi-view unsupervised feature selection
* model for automatically tracing object boundaries, A
* model-based approach for human head-and-shoulder segmentation, A
* Modeling structural dissimilarity based on shape embodiment for cell segmentation
* MomentsNet: A simple learning-free method for binary image recognition
* Mondrian stereo
* Mooney face classification and prediction by learning across tone
* More for less: Insights into convolutional nets for 3D point cloud recognition
* Motion blur removal via coupled autoencoder
* Motion compensation using critically sampled DWT subbands for low-bitrate video coding
* Motion feature augmented recurrent neural network for skeleton-based dynamic hand gesture recognition
* Motion-compensated compression of point cloud video
* Motion-compensated frame interpolation for multiview video using inter-view and intra-view correlations
* Motion-consistent video inpainting
* MR images segmentation and bias correction via LIC model
* MSFE: Blind image quality assessment based on multi-stage feature encoding
* Multi layer multi objective extreme learning machine
* Multi-Block N-ary trie structure for exact r-neighbour search in hamming space, A
* multi-direction image fusion based approach for classification of multi-focal nematode image stacks, A
* Multi-dropout regression for wide-angle landmark localization
* Multi-feature fusion based background subtraction for video sequences with strong background changes
* Multi-glimpse LSTM with color-depth feature fusion for human detection
* multi-layer image representation using regularized residual quantization: Application to compression and denoising, A
* Multi-layer linear model for top-down modulation of visual attention in natural egocentric vision
* Multi-modal 3d reconstruction and measurements of zebrafish larvae and its organs using axial-view microscopy
* Multi-modal joint embedding for fashion product retrieval
* Multi-modal metric learning for vehicle re-identification in traffic surveillance environment
* Multi-modal/multi-scale convolutional neural network based in-loop filter design for next generation video codec
* Multi-object tracking by virtual nodes added min-cost network flow
* Multi-output speckle reduction filter for ultrasound medical images based on multiplicative multiresolution decomposition
* Multi-part compact bilinear CNN for person re-identification
* Multi-scale 3D deep convolutional neural network for hyperspectral image classification
* Multi-scale convolutional neural networks for crowd counting
* Multi-stream switching for interactive virtual reality video streaming
* multi-task convolutional neural network with spatial transform for parking space detection, A
* Multi-view deep metric learning for image classification
* Multi-view human activity recognition using motion frequency
* Multi-view network-based social-tagged landmark image clustering
* Multi-view task-driven recognition in visual sensor networks
* Multi-view visual speech recognition based on multi task learning
* Multichannel guided image filter
* Multicolor removal based on color lines and improved hough transform for SFS
* Multigap: Multi-pooled inception network with text augmentation for aesthetic prediction of photographs
* multihypothesis-based residual reconstruction scheme in compressed video sensing, A
* Multimodal fusion via a series of transfers for noise removal
* Multiple path search for action tube detection in videos
* Multispectral focal stack acquisition using a chromatic aberration enlarged camera
* Multispectral human co-segmentation via joint convolutional neural networks
* Multiview pedestrian localisation via a prime candidate chart based on occupancy likelihoods
* Museed: A mobile image analysis application for plant seed morphometry
* Mutual reference frame-quality assessment for first-person videos
* MVIRT, a toolbox for manifold-valued image restoration
* MvLFDA-based video preference estimation using complementary properties of features
* Naturalness-preserved tone mapping in images based on perceptual quantization
* Nested polygonal chain mapping of omnidirectional video
* Neural network with saliency based feature selection ability
* new blind color image watermarking based on a psychovisual model and quantization approaches, A
* new deep-learning approach for early detection of shape variations in autism using structural mri, A
* new framework for incorporating appearance and shape features of lung nodules for precise diagnosis of lung cancer, A
* new fusion method for remote sensing images based on salient region extraction, A
* new high precision eye center localization technique, A
* new motion estimation method for motion-compensated frame interpolation using a convolutional neural network, A
* new motion model for panoramic video coding, A
* new tone-mapped image quality assessment approach for high dynamic range imaging system, A
* Nighttime sky/cloud image segmentation
* No-reference image quality assessment with orientation selectivity mechanism
* no-reference video quality predictor for compression and scaling artifacts, A
* Noise-tolerant deep learning for histopathological image segmentation
* Non-local similarity based tensor decomposition for hyperspectral image denoising
* Non-rigid image deformation algorithm based on MRLS-TPS
* NON-rigid structure from motion via sparse self-expressive representation
* Nonlinear subspace clustering
* nonlocal operator model for morphological image processing, A
* novel adaptive kernel correlation filter tracker with multiple feature integration, A
* novel angle-restricted test zone search algorithm for performance improvement of HEVC, A
* novel CAD system for local and global early diagnosis of Alzheimer's disease based on PIB-PET scans, A
* Novel evaluation metrics for seam carving based image retargeting
* novel framework to integrate convolutional neural network with compressed sensing for cell detection, A
* novel kinect V2 registration method for large-displacement environments using camera and scene constraints, A
* novel method to regenerate an optimal CNN by exploiting redundancy patterns in the network, A
* Novel representation for driver emotion recognition in motor vehicle videos
* novel satd based fast intra prediction for HEVC, A
* novel SRC based method for face recognition with low quality images, A
* novel variational model for retinex in presence of severe noises, A
* object based graph representation for video comparison, An
* Object detection via feature fusion based single network
* Object localization by optimizing convolutional neural network detection score using generic edge features
* Object segmentation in the deep neural network feature domain from highly cluttered natural scenes
* Object tracking with adaptive elastic net regression
* Occlusion detection in dense stereo estimation with convex optimization
* occlusion model for improving rendering quality of view, An
* Occlusion robust face recognition based on mask learning
* Occlusion-aware face inpainting via generative adversarial networks
* Offset aperture based hardware architecture for real-time depth extraction
* On generalizing the estimation-theoretic framework to scalable video coding with quadtree structured block partitions
* On some global topological aspects of manifold learning
* On the accuracy and robustness of deep triplet embedding for fingerprint liveness detection
* On the use of deep neural networks for the detection of small vehicles in ortho-images
* Online convolutional dictionary learning
* Online convolutional dictionary learning for multimodal imaging
* Online data-driven dynamic image restoration using DINO-KAT models
* Online multi-object tracking based on hierarchical association and sparse representation
* Online multi-object tracking with convolutional neural networks
* Online multiple object tracking via flow and convolutional features
* Online SVM and backward model validation based visual tracking
* Optimistic and pessimistic neural networks for object recognition
* Optimization of regularization parameter for sparse reconstruction based on predictive risk estimate
* Optimized inter-view prediction based light field image compression with adaptive reconstruction
* Optimizing landmark insertions for interactive light field streaming
* parallel convolutional neural network architecture for stereo vision estimation, A
* parallel linearized ADMM with application to multichannel tgv-based image restoration, A
* Part-based convolutional neural network for visual recognition
* Part-based fine-grained bird image retrieval respecting species correlation
* Passive millimeter wave image classification with large scale Gaussian processes
* Patch-based fully convolutional neural network with skip connections for retinal blood vessel segmentation
* PCA-coded aperture for light field photography
* Pedestrian detection with dynamic iterative bootstrapping
* Pedestrian proposal generation using depth-aware scale estimation
* Perceptual aliasing factors and the impact of frame rate on video quality
* Perceptual evaluation of single-image super-resolution reconstruction
* Perceptual metric for color transfer methods
* Perceptual quality assessment of HDR deghosting algorithms
* Perceptual quality assessment of HEVC main profile depth map compression for six degrees of freedom virtual reality video
* perceptually relevant shearlet-based adaptation of the PSNR, A
* Performance analysis of reconstruction-based super-resolution for camera arrays
* Performance comparison of Bayesian iterative algorithms for three classes of sparsity enforcing priors with application in computed tomography
* Persistent multiple hypothesis tracking for wide area motion imagery
* Person identification using spatiotemporal motion characteristics
* Person re-identification using visual attention
* Person re-identification with coarse-to-fine visual attention
* Person re-identification with deep dense feature representation and Joint Bayesian
* Personalized pose estimation for body language understanding
* Photorealistic adaptation and interpolation of facial expressions using HMMS and AAMS for audio-visual speech synthesis
* PIX2NVS: Parameterized conversion of pixel-domain video frames to neuromorphic vision streams
* Plant leaf segmentation for estimating phenotypic traits
* Point density-invariant 3D object detection and pose estimation
* Point process modeling for determining detection accuracy of mammographic microcalcifications
* Polsar data online classification based on multi-view learning
* Polygonization of remote sensing classification maps by mesh approximation
* pool of deep models for event recognition, A
* Pre-demosaic light field image compression using graph lifting transform
* Precoding and postcoding schemes for wireless video transmission in overloaded MIMO systems
* Preserving perceptual contrast in decolorization with optimized color orders
* Principal curvature of point cloud for 3D shape recognition
* Principal noiseless color component extraction by linear color composition with optimal coefficients
* Probabilistic graphical model based fast HEVC inter prediction
* Progressive communication for interactive light field image data streaming
* Progressive graph-signal sampling and encoding for static 3D geometry representation
* Projection based advanced motion model for cubic mapping for 360-degree video
* Propagation based saliency detection for infrared pedestrian images
* Prostate detection and segmentation based on convolutional neural network and topological derivative
* Provenance filtering for multimedia phylogeny
* Pseudo reversible symmetric extension for lifting-based nonlinear-phase paraunitary filter banks
* Ptychnet: CNN based fourier ptychography
* Quality assessment of images undergoing multiple distortion stages
* Quality assessment of MPEG-4 AVC/H.264 and HEVC compressed video in a telemedicine context
* Quality-adaptive deep learning for pedestrian detection
* Quasi rate distortion optimization for binary hashing
* Query-by-example word spotting using multiscale features and classification in the space of representation differences
* Random access point period optimization for viewport adaptive tile based streaming of 360 video
* Ranking video segments with LSTM and determinantal point processes
* Real-time 3-D image reconstruction from multi-focus images by efficient linear filtering with multi-dimensional symmetry
* Real-time 3D face reconstruction from one single image by displacement mapping
* Real-time monocular 6-DOF head pose estimation from salient 2D points
* Real-time object detection by a multi-feature fully convolutional network
* Real-time video stitching
* Real-time walkthrough of outdoor scenes using TRI-view morphing
* Realistic image composite with best-buddy prior of natural image patches
* Recognition of patterns in vector fields by Gaussian-hermite invariants
* Recognizing offensive tactics in broadcast basketball videos via key player detection
* Reconstruction of highly structured image by entropy optimization
* Reconstruction of respiratory-binned cardiac spect using a robust smoothing prior
* Recovering complex non-rigid 3D structures from monocular images by union of nonlinear subspaces
* Reduced-reference quality metric for screen content image
* Reducing noisy labels in weakly labeled data for visual sentiment analysis
* Reflectance-based surface saliency
* Reflection correspondence for exposing photograph manipulation
* Reflection separation using guided annotation
* Region average pooling for context-aware object detection
* Region based image retrieval with query-adaptive feature fusion
* Region ensemble network: Improving convolutional network for hand pose estimation
* Region-aware scattering convolution networks for facial beauty prediction
* Region-based depth recovery for highly sparse depth maps
* Region-based fully convolutional siamese networks for robust real-time visual tracking
* Registration of multitemporal GF-1 remote sensing images with weighting perspective transformation model
* Regularized selection: A new paradigm for inverse based regularized image reconstruction techniques
* Regularizing face verification nets for pain intensity regression
* Reliable pedestrian detection using a deep neural network trained on pedestrian counts
* Representative pixels compression algorithm using graph signal processing for colorization-based image coding
* Resfeats: Residual network based features for image classification
* Residual-based forensic comparison of video sequences
* Rethinking the high capacity 3D steganography: Increasing its resistance to steganalysis
* Retinal blood vessel extraction method based on basic filtering schemes
* Retrain-free fully connected layer optimization using matrix factorization
* RGB-D data fusion in complex space
* Roadesic distance: Flow-aware tracklet association cost for wide area surveillance
* Robust active contours for mammogram image segmentation
* Robust ellipse detection via arc segmentation and classification
* Robust face alignment with cascaded coarse-to-fine auto-encoder network
* Robust face recognition based on iterative sparse coding and pixel selection
* Robust image identification with secure features for JPEG images
* Robust image-based crack detection in concrete structure using multi-scale enhancement and visual features
* Robust joint sparsity model for hyperspectral image classification
* Robust linear unmixing with enhanced sparsity
* Robust object tracking based on discriminative analysis and local sparse representation
* Robust object tracking by interleaving variable rate color particle filtering and deep learning
* Robust object tracking via multi-task based collaborative model
* Robust photometric stereo using learned image and gradient dictionaries
* Robust plane-based calibration for linear cameras
* Robust recovery for aperture synthesis imaging
* Robust shape regularity criteria for superpixel evaluation
* Robust surface reconstruction from gradients via adaptive dictionary regularization
* Robust synthetic basis feature descriptor
* Robust visual tracking via multi-view discriminant based sparse representation
* Robustness analysis of a passive printer identification scheme for halftone images
* Rotated region based CNN for ship detection
* rotation invariant 3D indoor scene labeling approach based on conditional random fields, A
* Saccade gaze prediction using a recurrent neural network
* Saliency detection by forward and backward cues in deep-CNN
* Saliency detection for seismic applications using multi-dimensional spectral projections and directional comparisons
* Saliency detection via local single Gaussian model
* Saliency prediction based on new deep multi-layer convolution neural network
* Saliency-based change detection for aerial and remote sensing imageries
* Salient object detection via a linear feedback control system
* Salprop: Salient object proposals via aggregated edge cues
* Sampling pattern design algorithm for atomic force microscopy images
* SAR image despeckling by combination of fractional-order total variation and nonlocal low rank regularization
* Scalable light field compression scheme using sparse reconstruction and restoration
* Scaled fixed-point frequency selective extrapolation for fast image error concealment
* Scene text detection based on skeleton-cut detector
* SCNN: Sequential convolutional neural network for human action recognition in videos
* Search video action proposal with recurrent and static YOLO
* Segmentation of Dermoscopy Images Based on Fully Convolutional Neural Network
* Selecting attentive frames from visually coherent video chunks for surveillance video summarization
* Selective motion estimation strategy based on content classification for HEVC screen content coding
* Self-paced least square semi-coupled dictionary learning for person re-identification
* Semantic background subtraction
* Semantic boundary refinement by joint inference from edges and regions
* Semantic image content filtering via edge-preserving scale-aware filter
* Semantic image segmentation using the ICM algorithm
* Semantic segmentation based on iterative contraction and merging
* Semantic segmentation with multi-path refinement and pyramid pooling dilated-resnet
* Semantics-guided multi-level RGB-D feature fusion for indoor semantic segmentation
* semi-global motion estimation of a repetition pattern region for frame interpolation, A
* Semi-supervised domain adaptation via convolutional neural network
* Semi-supervised multi-output image manifold regression
* Semicca: A new semi-supervised probabilistic CCA model for keyword spotting
* Shadow removal based on clustering correction of illumination field for urban aerial remote sensing images
* Shallow and deep convolutional networks for image super-resolution
* Shape recognition by bag of contour fragments with a learned pooling function
* Shape retrieval using multiscale ellipse descriptor
* Shape-aware spatio-temporal descriptors for interaction classification
* shortest matching path based on novel cycle consistency, The
* Siamese recurrent architecture for visual tracking
* Simple online and realtime tracking with a deep association metric
* Single depth image super-resolution and denoising based on sparse graphs via structure tensor
* Single image depth prediction using super-column super-pixel features
* Single image haze removal based on saliency detection and dark channel prior
* Single image super-resolution with dilated convolution based multi-scale information learning inception module
* Single shot object detection with top-down refinement
* Skellam distribution based adaptive two-stage non-local methods for photon-limited poisson noisy image reconstruction
* Sketch based image retrieval via image-aided cross domain learning
* Sketch-based aerial image retrieval
* Sliding window filter based unknown object pose estimation
* So-BRIEF: Fast recognition of rectangular objects
* Soft segmentation-guided bipartite graph image stylization
* sparse approach to pedestrian trajectory modeling using multiple motion fields, A
* Sparse nonnegative dynamic mode decomposition
* Spatial pyramid alignment for sparse coding based object classification
* Spatial-sequential-spectral context awareness tracking
* Spatially adaptive image compression using a tiled deep network
* Spatio-spectral deconvolution of vector valued images using total nuclear variation
* spearman correlation based star pattern recognition, A
* Specialized gaze estimation for children by convolutional neural network and domain adaptation
* Spectral pre-adaptation for two-step arbitrary-shape-support image restoration
* Speeding up the Kohler's method of contrast thresholding
* Spike and slab variational inference for blind image deconvolution
* Spotting the difference: Context retrieval and analysis for improved forgery detection and localization
* Square to hexagonal lattice conversion in the frequency domain
* SSGD: Superpixels using the Shortest Gradient Distance
* SSPP-DAN: Deep domain adaptation network for face recognition with single sample per person
* Stable and improved generative adversarial nets (GANS): A constructive survey
* Stacking-based deep neural network: Deep analytic network on convolutional spectral histogram features
* statistic manifold kernel with graph embedding discriminant analysis for action and expression recognition, A
* Statistical analysis of longitudinal data and applications to neuro-imaging
* Stereo ambiguity index for semi-global matching
* Stereoscopic cloud base reconstruction using high-resolution whole sky imagers
* Street-to-shop shoe retrieval with multi-scale viewpoint invariant triplet network
* Stripe noise removal of remote sensing image with a directional L_0 sparse model
* Stromule branch tip detection based on accurate cell image segmentation
* Structure-adaptive vector median filter for impulse noise removal in color images
* Structured binary feature extraction for hyperspectral imagery classification
* study of CNN outside of training conditions, A
* Study of subjective and objective quality assessment for screen content images
* study on content-based video recommendation, A
* study on quantization effects of DCT based compression, A
* Subjective and objective quality evaluation of sonar images for underwater acoustic transmission
* Submodular video object proposal selection for semantic object segmentation
* Subproblem coupling in convolutional dictionary learning
* Subspace clustering via independent subspace analysis network
* Summarization of human activity videos using a salient dictionary
* Superpixel-based color transfer
* Superpixel-based image inpainting with simple user guidance
* Supervised classification of hyperspectral images using local-receptive-fields-based kernel extreme learning machine
* Supervised hashing with jointly learning embedding and quantization
* Surveillance video coding with dynamic textural background detection
* Surveillance video coding with vehicle library
* switchable loop-restoration with side-information framework for the emerging AV1 video codec, A
* Synthesis of fine details in B picture for dynamic textures
* Synthesis-analysis deconvolutional network for compressed sensing
* TAD16K: An enhanced benchmark for autonomous driving
* Tag refinement based on multilingual tag hierarchies extracted from image folksonomy
* Tag tree creation of social image for personalized recommendation
* Targeted video denoising for decompressed videos
* Task-dependent saliency estimation from trajectories of agents in video sequences
* Temporal action localization with two-stream segment-based RNN
* Temporal corelation based hierarchical quantization parameter determination for HEVC video coding
* Tensor non-local low-rank regularization for recovering compressed hyperspectral images
* Tensorial compressive sensing of jointly sparse matrices with applications to color imaging
* Three-dimensional segmentation of vesicular networks of fungal hyphae in macroscopic microscopy image stacks
* Time samples selection in spiral acquisition for sparse magnetic resonance spectroscopic imaging
* Time-of-flight sensor depth enhancement for automotive exhaust gas
* Tiny head pose classification by bodily cues
* Touchless-to-touch fingerprint systems compatibility method
* Towards 3D convolutional neural networks with meshes
* Towards scheduling hard real-time image processing tasks on a single GPU
* Towards thinner convolutional neural networks through gradually global pruning
* Trademark image retrieval using hierarchical region feature description
* Training sample selection for deep learning of distributed data
* Trajectories-based motion neighborhood feature for human action recognition
* Transferring CNNS to multi-instance multi-label classification on small datasets
* Transforming photos to comics using convolutional neural networks
* Tunable color correction between linear and polynomial models for noisy images
* Two-stage absorbing Markov chain for salient object detection
* Two-Stage Convolutional Neural Network for Light Field Super-Resolution
* two-stage minimum spanning tree (MST) based clustering algorithm for 2D deformable registration of time sequenced images, A
* Two-step multi-illuminant color constancy for outdoor scenes
* TX-CNN: Detecting tuberculosis in chest X-ray images using convolutional neural network
* U-Phylogeny: Undirected provenance graph construction in the wild
* Understanding neural-network denoisers through an activation function perspective
* Underwater image enhancement based on structure-texture decomposition
* unique target representation and voting mechanism for visual tracking, A
* Unsupervised convolutional neural networks for large-scale image clustering
* Unsupervised deep hashing with stacked convolutional autoencoders
* Unsupervised domain adaptation with joint supervised sparse coding and discriminative regularization term
* Unsupervised feature selection by manifold regularized self-representation
* Unsupervised hyperspectral band selection via multi-feature information-maximization clustering
* Unsupervised person re-identification via re-ranking enhanced sample-specific metric learning
* Unsupervised segmentation of low depth of field images based on L0 regularized matting model
* Unsupervised stereo matching using correspondence consistency
* Using 2D ARMA-GARCH for ultrasound images denoising
* Using multiscale analysis for blind quality assessment of DIBR-synthesized images
* Variable block-size overlapped block motion compensation in the next generation open-source video codec
* Variation learning guided convolutional network for image interpolation
* Variational fusion of time-of-flight and stereo data using edge selective joint filtering
* Variational Pansharpening Approach Based on Reproducible Kernel Hilbert Space and Heaviside Function, A
* Vehicle detection and pose estimation by probabilistic representation
* Video decoding energy estimation using processor events
* Video quality enhancement via QP adaptation based on perceptual coding maps
* Video segmentation via boundary-aware flow
* Video super-resolution using motion compensation and residual bidirectional recurrent convolutional network
* View synthesis with hierarchical clustering based occlusion filling
* View-dependent virtual reality content from RGB-D images
* View-invariant object recognition using homography constraints
* Viewpoint adaptive display of HDR images
* Viewpoint calibration method based on point features for point cloud fusion
* Viewport-aware adaptive 360 video streaming using tiles for virtual reality
* Viewport-dependent 360 degree video streaming based on the emerging Omnidirectional Media Format (OMAF) standard
* Virtual reality content streaming: Viewport-dependent projection and tile-based techniques
* Virtual review of large scale image stack on 3D display
* Visibility enhancement of fluorescent substance under ambient illumination using flash photography
* Visibility enhancement via optimal gamma tone mapping for OST displays under ambient light
* Visual and textual sentiment analysis using deep fusion convolutional neural networks
* Visual comfort assessment of stereoscopic images using deep visual and disparity features based on human attention
* Visual entropy: A new framework for quantifying visual information based on human perception
* Visual quality prediction on distorted stereoscopic images
* Visual query compression with locality preserving projection on Grassmann manifold
* Visual salience and stack extension based ghost removal for high-dynamic-range imaging
* Visual saliency-based confidentiality metric for selective crypto-compressed JPEG images
* Visual tracking via structural patch-based dictionary pair learning
* Volume segmentation using convolutional neural networks with limited training data
* VR-HDR: A system for view-dependent rendering of HDR video in virtual reality
* Water surface reconstruction and truly random numbers generation from images of wind-generated gravity waves
* Weakly supervised food image segmentation using class activation maps
* Weakly supervised multiscale-inception learning for web-scale face recognition
* Weakly supervised object localization with deep convolutional neural network based on spatial pyramid saliency map
* Weakly-supervised localization of diabetic retinopathy lesions in retinal fundus images
* Weighted median-shift on graphs for geometric model fitting
* weighting strategy for Active Shape Models, A
* When saliency meets sentiment: Understanding how image content invokes emotion and sentiment
* WI-VI fingerprint: WiFi and vision integrated fingerprint for smartphone-based indoor self-localization
* Wide-angle image stitching using multi-homography warping
* Wits Intelligent Teaching System: Detecting student engagement during lectures using convolutional neural networks, The
* Wordfence: Text detection in natural images with border awareness
926 for 1803

Index for "1"


Last update:12-Nov-18 12:23:22
Use price@usc.edu for comments.