Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks453 from public data
- 1,046
- Group-Based Sparse Representation for Image Restoration768
The proposed group-based sparse representation (GSR) is able to sparsely represent natural images in the domain of group, which enforces the intrinsic local sparsity and nonlocal self-similarity of images simultaneously in a unified framework.
- 440
- Learning Convolutional Networks for Content-Weighted Image Compression421
The bit rate of the different parts of the image is adapted to local content, and the content-aware bit rate is allocated under the guidance of a content-weighted importance map so that the sum of the importance map can serve as a continuous alternative of discrete entropy estimation to control compression rate.
- 416
- Fast and robust text detection in images and video frames380
A novel coarse-to-fine algorithm that is able to locate text lines even under complex background is proposed and Experimental results show that this approach can fast and robustly detect text lines under various conditions.
- 274
- An End-to-End Compression Framework Based on Convolutional Neural Networks232
Experimental results validate that the proposed compression framework greatly outperforms several compression frameworks that use existing image coding standards with the state-of-the-art deblocking or denoising post-processing methods.
- Image Restoration Using Joint Statistical Modeling in a Space-Transform Domain191
A joint statistical modeling (JSM) in an adaptive hybrid space-transform domain is established, which offers a powerful mechanism of combining local smoothness and nonlocal self-similarity simultaneously to ensure a more reliable and robust estimation.
- 188
- Image compressive sensing recovery using adaptively learned sparsifying basis via L0 minimization181
This paper proposes a new framework for image compressive sensing recovery using adaptively learned sparsifying basis via L0 minimization, and proposes a split Bregman iteration based technique to solve the non-convex L 0 minimization problem efficiently.
- A Chinese sign language recognition system based on SOFM/SRN/HMM173
This paper uses the self-organizing feature maps (SOFM) as different signers' feature extractor for continuous hidden Markov models (HMM) so as to transform input signs into significant and low-dimensional representations that can be well modeled by the emission probabilities of HMM.
- Deep networks for compressed image sensing165
A deep network is proposed to recover the image, which imitates traditional compressed sensing reconstruction processes, and offers a very significant quality improvement compared against state-of-the-art ones.
- 162
- 155
- 152
- 150
- 148
- 140
- 130
- 129
- Object detection using spatial histogram features125
This paper employs Fisher criterion and mutual information to measure discriminability and features correlation of spatial histogram features, and trains a hierarchical classifier by combining cascade histogram matching and support vector machine.
- 119
- Joint video/depth rate allocation for 3D video coding based on view synthesis distortion model116
Experimental results show that the proposed distortion model is capable of approximately estimating the actual distortion for the synthesized view, and that the suggested rate allocation method can almost achieve the identical rate allocation performance as the full-search method at less computational cost.
- 112
- 109
- Image Compressed Sensing Using Non-Local Neural Network103
A novel image CS framework using non-local neural network (NL-CSNet) is proposed, which utilizes the non- local self-similarity priors with deep network to improve the reconstruction quality and outperforms existing state-of-the-art CS methods, while maintaining fast computational speed.
- CAS-PEAL Large-Scale Chinese Face Database and Evaluation Protocols102
The ICT-ISVISION Joint Research & Development Laboratory (JDL) for Face Recognition has constructed the CAS-PEAL face database, which contains 99,594 images of 1040 individuals with varying Pose, Expression, Accessory, and Lighting (PEAL).
- 88
- 87
- Structural Group Sparse Representation for Image Compressive Sensing Recovery84
This paper proposes a new framework for image compressive sensing recovery via structural group sparse representation (SGSR) modeling, which enforces image sparsity and self-similarity simultaneously under a unified framework in an adaptive group domain, thus greatly confining the CS solution space.
- Single image super-resolution with dilated convolution based multi-scale information learning inception module83
The novel dilated convolution based inception module is proposed to learn multi-scale information and design a deep network for single image super-resolution and Experimental results show that the proposed method outperforms many state-of-the-art single imagesuper-resolution methods.
- 81
- High-Resolution Depth Maps Imaging via Attention-Based Hierarchical Multi-Modal Fusion79
To effectively extract and combine relevant information from LR depth and HR guidance, a multi-modal attention based fusion (MMAF) strategy for hierarchical convolutional layers, including a feature enhancement block to select valuable features and a feature recalibration block to unify the similarity metrics of modalities with different appearance characteristics are proposed.
- 78
- No-reference perceptual image quality metric using gradient profiles for JPEG200078
This paper proposes a novel quality metric for JPEG2000 images that achieves performance competitive with the state-of-the-art no-reference metrics on public datasets and is robust to various image contents.
- 77
- Image super-resolution via dual-dictionary learning and sparse representation72
Extensive experimental results validate that by employing the proposed two-layer progressive scheme, more image details can be recovered and much better results can be achieved than the state-of-the-art algorithms in terms of both PSNR and visual perception.
- 72
- Guided Depth Map Super-Resolution: A Survey71
A comprehensive survey of recent progress in guided depth map super-resolution (GDSR), which aims to reconstruct a high-resolution depth map from a low-resolution observation with the help of a paired high- resolution color image, is presented.
- Convolutional Neural Networks Based Intra Prediction for HEVC71
An intra-prediction convolutional neural network (IPCNN) is proposed for intra prediction, which exploits the rich context of the current block and therefore is capable of improving the accuracy of predicting thecurrent block.
- 70
- 69
- 67
- 66
- 65
- 65
- Deep Attentional Guided Image Filtering63
This work proposes an attentional kernel learning module to generate dual sets of filter kernels from the guidance and the target and then adaptively combine them by modeling the pixelwise dependency between the two images.
- 63
- 61
- 61
- 59
- 58
- 57
- 57
- 55
- Stereoscopic video quality assessment based on visual attention and just-noticeable difference models54
An objective stereoscopic video quality assessment (SVQA) metric is proposed by incorporating stereoscopic visual attention (SVA) to SVQA metric based upon the multiple visual masking characteristics of HVS.
- D-cast54
D-cast is a new video multicast approach that is based on distributed source coding (DSC) theory, which helps D-cast to avoid error propagation but still achieve high compression efficiency in inter frame coding.
- Large vocabulary sign language recognition based on hierarchical decision trees52
A hierarchical decision tree is first presented for large vocabulary sign language recognition based on the divide-and-conquer principle and drastically reduces the recognition time by 11 times and also improves the recognition rate about 0.95% over single SOFM/HMM.
- 50
- 49
- 49
- 49
- 48
- 48
- 47
- Face recognition based on face‐specific subspace47
Extensive experiments on several academic databases show that the proposed individual appearance model based method, named face‐specific subspace (FSS), significantly outperforms Eigenface and template matching, which intensively indicates its robustness under variation in illumination, expression, and viewpoint.
- Quality assessment for real out-of-focus blurred images46
This paper constructs a dedicated out-of-focus blurred image dataset and proposes a specific objective quality metric for the blurred images, which combines image sharpness assessment and saliency-guided pooling strategy and demonstrates the proposed metric highly correlates with human judgements of image quality.
- 46
- Rate control for scalable video model46
An efficient rate control scheme is proposed for the SVM, which is derived from the state-of-the-art hybrid rate control schemes of JVT with some considerations for scalable video coding.
- 44
- Low-complexity and low-memory entropy coder for image compression42
The experimental results show that discrete cosine transform- and discrete wavelet transform-based LLEC outperforms baseline JPEG and embedded zerotree wavelet coding (EZW) at the given bit rates, respectively.
- Fast encoder decision for texture coding in 3D-HEVC41
A fast encoder decision algorithm to encode the dependent texture views in 3D-HEVC using an early merge mode decision algorithm and an early CU splitting termination algorithm to avoid unnecessary checks for larger depths.
- 41
- 41
- 41
- Spatial Histogram Features for Face Detection in Color Images41
A hierarchical classifier combining histogram matching and support vector machine is utilized to identify face and non-face and shows an excellent capability for face detection, and it is robust to lighting changes.
- Morphological representation of DCT coefficients for image compression41
It is shown that, by proper reorganization of its coefficients, the block-based DCT can have similar characteristics, such as energy compaction, cross-subband similarity, decay of magnitude across subband, etc., to the wavelet transform, and MRDCT is among the state-of-the-art DCT-based image coders reported in the literature.
- 40
- 39
- 39
- 38
- 38
- 37
- 36
- Fast intra-encoding algorithm for High Efficiency Video Coding35
A fast intra-encoding algorithm for HEVC, which is composed of the following four techniques, which can provide about 50% time savings with only 0.5% BD-rate loss on average when compared to HM 11.0 for the Main profile all-intra-configuration.
- 34
- DV-Hop Localization Based on Distance Estimation Using Multinode and Hop Loss in IoT33
A distance vector hop (DV-Hop) localization based on the distance estimation using the multinode (DEMN) and the hop loss in the wireless sensor networks is proposed to address the two issues of sensor location awareness and connection information.
- ChebyLighter: Optimal Curve Estimation for Low-light Image Enhancement33
The proposed model, ChebyLighter, learns to estimate pixel-wise adjustment curves for a low-light image recurrently to reconstruct an enhanced output and performs favorably against state-of-the-art low- light image enhancement algorithms.
- 33
- 3D object retrieval with multi-feature collaboration and bipartite graph matching33
The essential characters of 3D object in a view-based retrieval framework, which extracts complement descriptors from both the contour and the interior region of3D object effectively is explored.
- 33
- 32
- 32
- 32
- 32
- 31
- Context-Based 2D-VLC Entropy Coder in AVS Video Coding Standard30
A Context-based 2D Variable Length Coding (C2DVLC) method for coding the transformed residuals in AVS video coding standard is presented, which is a low complexity coder in terms of both computational time and memory requirement.
- 29
- 28
- 28
- Adaptive relevance feedback based on Bayesian inference for image retrieval28
An adaptive relevance feedback approach based on the Bayesian inference, rich get richer (RGR), which greatly reduces the user's efforts for composing a query and captures user's, intention efficiently.
- 28
- 27
- Hierarchical residual learning for image denoising27
Experimental results on several datasets show that the proposed hierarchical residual learning based CNN framework for image denoising method outperforms many state-of-the-art ones.
- 26
- Inter-block consistent soft decoding of JPEG images with sparsity and graph-signal smoothness priors26
- 24
- Multi-Stage Residual Hiding for Image-Into-Audio Steganography24
This paper presents a cross-modal steganography method for hiding image content into audio carriers while preserving the perceptual fidelity of the cover audio and proposes a multi-stage design of proposed framework to make hiding easier.
- Learning discriminative features for fast frame-based action recognition24
An instant action recognition method, which is able to recognize an action in real-time from only two continuous video frames, and the action recognition accuracy is comparable to the state-of-the-art approaches.
- AVS Video Coding Standard24
This chapter will give an overview of AVS standard, which includes Part 2 and Part 7, which is targeted to high resolution, high bit rate video applications, such as broadcasting and called AVS1-P2 in AVS.
- 24
- RD-optimized interactive streaming of multiview video with multiple encodings24
Experimental results demonstrate that the proposed method can achieve a significant end-to-end RD performance improvement over the selective streaming methods with simulcast coding or scalable multiview coding, and has better error-resilience performance to combat with packet-losses over the Internet protocol (IP) networks.
- Context-based entropy coding in AVS video coding standard24
The experimental results demonstrate that both C2DVLC and CBAC can achieve comparable or even slightly higher coding performance when compared to Context-Adaptive Variable Length Coding (CAVLC) in H.264/AVC baseline profile and Context-Based Adaptive Binary Arithmetic Coded (CABAC) in CABAC main profile respectively.
- Deep Unfolding Network for Image Compressed Sensing by Content-Adaptive Gradient Updating and Deformation-Invariant Non-Local Modeling23
In this article, inspired by the traditional Proximal Gradient Descent (PGD) algorithm, a novel DUN for image compressed sensing (dubbed DUN-CSNet) is proposed, which outperforms existing state-of-the-art CS methods by large margins.
- 23
- 23
- 23
- Deep Neural Network Based Sparse Measurement Matrix for Image Compressed Sensing22
A Deep neural network based Sparse Measurement Matrix (DSMM) is learned by the proposed convolutional network to reduce the sampling computational complexity and improve the CS reconstruction performance.
- 3D visual saliency detection model with generated disparity map22
The proposed model is based on a band-pass filtering method which coincides with the visual perceptual process in human visual system and achieves better detection performance with low computational cost among the existing 3D visual saliency detection models.
- 22
- Combining Skin Color Model and Neural Network for Rotation Invariant Face Detection22
An algorithm for rotation invariant face detection in color images of cluttered scenes is presented, which combines a skin color model, a neural network, and an upright face detector to determine whether or not the rotated window is a face.
- 21
- 21
- 21
- 21
- 21
- 21
- 20
- 20
- 20
- 20
- 19
- 19
- Learning-based image restoration for compressed images19
Experimental results have demonstrated that the proposed scheme can reproduce higher quality images in terms of both objective and subjective quality.
- Synthetic data generation technique in Signer-independent sign language recognition19
The mean shift algorithm is able to obtain the directions of maximum increase and decrease in the density function, so it is used to control the direction and the intensity of synthetic data generation.
- 19
- Fast Hierarchical Deep Unfolding Network for Image Compressed Sensing18
A novel fast hierarchical DUN, dubbed FHDUN, is proposed for image compressed sensing, in which a well-designed hierarchical unfolding architecture is developed to cooperatively explore richer contextual prior information in multi-scale spaces.
- 18
- Paragraph Generation Network with Visual Relationship Detection18
A paragraph generation network with introducing visual relationship detection that first detects regions which may contain important visual objects and then predicts their relationships, which shows that such strategy could improve paragraph generating performance from two aspects.
- 18
- Face hallucination and recognition in social network services18
A novel face hallucination method with an aim of improving face recognition performance with the photography in social media data, which is modeled as a progressive process which explores the specific face characteristics and priors based on frequency bands analysis.
- Image Primitive Coding and Visual Quality Assessment18
A new content-adaptive compression scheme, called image primitive coding, is introduced, which exploits the input image for training a dictionary, and a novel concept, entropy of primitives (EoP), is proposed for measuring image visual information.
- 18
- 18
- An automated framework for managing security vulnerabilities18
An automated framework is presented that is designed to provide a vendor‐independent means of vulnerability notification and rectification for system administrators and provides an auto-responding mechanism for notification management.
- 18
- 17
- Discriminating features learning in hand gesture classification17
A discriminating features extraction for HGR is proposed, in which features from red, green and blue (RGB) images and depth images are both explored and histogram of oriented gradient feature, local binary pattern feature, structure feature and three-dimensional voxel feature are extracted.
- Viewpoint-independent hand gesture recognition with Kinect17
A viewpoint-independent hand gesture recognition method based on the rules about gesturers posture under optimal viewpoint is presented, which performs satisfyingly on scale and rotation variant in HGR with robustness and high accuracy.
- Spatio-Temporal Context Based Adaptive Camcorder Recording Watermarking16
A novel spatio-temporal context based adaptive camcorder recording watermarking scheme STACR is proposed, which achieves high video quality and is robust to geometric attacks, compression, scaling, transcoding, recoding, frame rate changes and especially for camc recorder recording.
- 16
- An Efficient Deep Convolutional Laplacian Pyramid Architecture for Cs Reconstruction At Low Sampling Ratios16
A deep convolutional Laplacian Pyramid Compressed Sensing Network (LapC-SNet) for CS, which consists of a sampling sub-network and a reconstruction sub- network that is capable of reconstructing more details and sharper edges against the state-of-the-arts methods.
- 16
- 16
- Side information generation with auto regressive model for low-delay distributed video coding16
Experimental results demonstrate that the proposed auto regressive AR model to generate the high quality side information (SI) for Wyner-Ziv (WZ) frames in low-delay distributed video coding is able to achieve a higher performance compared to the existing SI generation methods.
- 16
- A Study on the Quantization Scheme in H.264/AVC and Its Application to Rate Control16
An efficient rate control scheme is developed based on the new rate-distortion (R-D) model and implemented into the H.264/AVC reference software, with which the better coding performance can be achieved.
- 15
- An Efficient Deep Quantized Compressed Sensing Coding Framework of Natural Images15
A novel deep network based CS coding framework of natural images that consists of three sub-networks that responsible for sampling, quantization and reconstruction, respectively that can be trained in the form of an end-to-end metric with a proposed rate-distortion optimization loss function.
- Compressive Sensing Based Soft Video Broadcast Using Spatial and Temporal Sparsity15
The nonlocal sparsity and hierarchical GOP structure is used to propose a novel CS based soft video broadcast scheme and the experimental results show that the proposed scheme provides better performance compared with the traditional SoftCast with up to 8 dB coding gain for some channel conditions.
- 15
- 15
- Robust Multi-view Face Detection Using Error Correcting Output Codes15
A novel method to solve multi-view face detection problem by Error Correcting Output Codes (ECOC) using spatial histograms as the representation, which provides an over-complete set of optional features that can be efficiently computed from the original images.
- Performance Comparison of AVS and H.264/AVC Video Coding Standards15
The experimental results show that the AVS1-P2 Jizhun profile has an average of 2.96% efficiency loss relative to H.264/AVC main profile in terms of bit-rate saving on HD progressive-scan sequences, and still possesses a valuable feature of lower computational complexity.
- NormalNet: Learning based Guided Normal Filtering for Mesh Denoising.14
The proposed deep learning based face normal filtering scheme for mesh denoising can generate accurate guidance normals and remove noise effectively while preserving original features and avoiding pseudo-features.
- 14
- Low complexity encoder optimization for HEVC14
A low complexity encoder optimization scheme is proposed by reducing the number of available candidates for evaluation in terms of the intra prediction mode decision, early termination of coding unit (CU) splitting and adaptive reference frame selection and can achieve more than 40% complexity reduction on average.
- 14
- 14
- 14
- 14
- 14
- 14
- Laplacian Distortion Model (LDM) for Rate Control in Video Coding14
First, a new distortion model with the assumption of Laplacian distribution of quantized DCT coefficients is deduced (called LaPlacian distortion model, LDM), and then a more accurate rate-distortion model is proposed based on LDM.
- 14
- 14
- 14
- 13
- Anchored neighborhood deep network for single-image super-resolution13
This paper establishes the relationship between the traditional sparse-representation-based single-image super-resolution methods and the deep-learning-based ones and uses transfer learning to make the proposed deep network take the image prior into account and shows that the proposed method outperforms many state-of-the-art single- image super- resolution methods.
- 13
- 13
- Learning-Based Image Restoration for Compressed Image through Neighboring Embedding13
Experimental results have demonstrated that the proposed scheme can reproduce higher-quality images in terms of visual quality and PSNR, especially the regions relating to the contours.
- 13
- B-picture coding in AVS video compression standard13
The proposed symmetrical mode that replaces the conventional bi-directional mode, in which only one motion vector is coded and another is derived from the coded one with the assumption of approximate constant-speed motion and improves the accuracy of derived motion vectors in temporal direct mode with division-free operations.
- 12
- Local Surface Descriptor for Geometry and Feature Preserved Mesh Denoising12
The local surface descriptor (LSD) is proposed, which is able to transform the local deformable surface around a face into 2D grid representation and thus facilitates the deployment of CNNs to generate denoised face normals.
- 12
- 12
- 11
- 11
- 11
- 11
- Frame Rate and Perceptual Quality for HD Video11
The impact of frame rate on the perceptual quality of High Definition HD video with high frame rates up to 120i¾źfps considered is discussed and some meaningful findings are proposed.
- Hierarchical frame based spatial–temporal recovery for video compressive sensing coding11
The proposed divide-and-conquer based hierarchical video compressive sensing coding framework is proposed, in which the whole video is independently divided into non-overlapped blocks of the hierarchical frames, which achieves better performance against many state-of-the-art still-image CS and video CS recovery algorithms.
- 11
- 11
- A Novel Macro-Block Group Based AVS Coding Scheme for Many-Core Processor11
A Macro-Block Group (MBG) parallel scheme for parallel AVS coding, where each MBG consists of more rows and less columns of macro-blocks than the slice-level scheme, and a vertical partitioning scheme is introduced.
- 11
- Semisupervised learning-based depth estimation with semantic inference guidance10
This paper proposes a novel semisupervised learning framework to infer the 3D structure from the given scene with semantic information employed to make the depth inference more accurate and makes both the depth estimation and semantic segmentation coarse-to-fine frameworks.
- Big data driven decision making and multi-prior models collaboration for media restoration10
A novel multi-prior models collaboration framework for image restoration with big data is proposed which improves the restoration performance significantly and provides a reasonable method for the relative exploration of big data driven decision making.
- 10
- 10
- 10
- A New Method for Constructing Spectral Emissivity Models for Measuring the Real Temperature of Targets10
The proposed single parameter dynamic search algorithm using the hybrid steepest descent and Newton’s method is proposed to optimize the training algorithm of the model, which can quicken the convergence speed of the combined neural network emissivity model (CNNE model).
- 10
- 9
- S 2 -CSNet: Scale-Aware Scalable Sampling Network for Image Compressive Sensing9
A novel scale-aware scalable CS network that achieves scale-aware adaptive sampling, fine granular scalability and high-quality reconstruction with one single model is proposed, which outperforms existing state-of-the-art CS methods.
- 9
- 9
- Depth Image Denoising via Collaborative Graph Fourier Transform9
A patch-wise depth image denoising algorithm which exploits intra-patch and inter-patch correlations represented by graph is proposed which outperforms state-of-the-art image Denoising methods in both objective results and subjective visual quality.
- 9
- 9
- 9
- Ant colony clustering analysis based intelligent fault diagnosis method and its application to rotating machinery9
An improved ant colony clustering algorithm is proposed to adjust comparison probability dynamically and detect outliers and has higher convergence speed to meet requirements of real-time analysis as well as further improvement of accuracy.
- 9
- Performance prediction methodology based on pattern recognition9
Results have shown that the proposed method can analyze drill degradation quantitatively, and predict problems before they occur, and has higher convergence speed to meet requirements of real-time analysis as well as further improvement of accuracy.
- Spatial-Aided Low-Delay Wyner-Ziv Video Coding9
Theoretical analysis proved that when a good tradeoff between the auxiliary information coding and WZ frame coding is achieved, SA-WZVC is able to achieve better rate distortion performance than the conventional MCE-based WZVC without auxiliary information.
- 9
- 9
- 9
- Deep Network for Image Compressed Sensing Coding Using Local Structural Sampling8
A new convolutional neural network based image CS coding framework using local structural sampling (dubbed CSCNet) that includes three functional modules: local structural sampling, measurement coding, and Laplacian pyramid reconstruction is proposed.
- Dual-stream Perception-driven Blind Quality Assessment for Stereoscopic Omnidirectional Images8
A novel dual-stream perception-driven network for blind quality assessment of stereoscopic omnidirectional images, integrating both ERP and CMP, marking the first attempt to bridge this gap in SOIQA, particularly through deep learning methodologies.
- Tree-Structured Data Clustering-Driven Neural Network for Intra Prediction in Video Coding8
This paper proposes a novel tree-structured data clustering-driven neural network (dubbed TreeNet) for intra prediction, which builds the networks and clusters the training data in a tree- Structured manner.
- 8
- 8
- Search-Based Depth Estimation via Coupled Dictionary Learning with Large-Margin Structure Inference8
This paper handles the depth estimation of local patches via a novel cross-modality retrieval scheme, which searches for the 3D patches with similar structure/appearance to the 2D query from a dataset with 2D-3D mappings, through a coupled dictionary learning formulation.
- 8
- 8
- 8
- Image Quality Assessment Using Spatial Frequency Component8
A novel IQA method that inspects distortions of both global and local information in the spatial frequency components of the image using a newly proposed abruptness weighting that describes the uniformity of the residual image.
- 8
- Video Coding by Texture Analysis and Synthesis Using Graph Cut8
Experimental results show that the proposed method can achieve compared visual quality for texture regions with H.264/AVC, while spending fewer bits.
- 8
- Adaptive Deinterlacing for Real-Time Applications8
This paper first proposes a directional adaptive algorithm for motion detection, and then introduces a reasonable and applicable adaptive MC/NMC deinterlacing mechanism to meet the requirements of real-time applications.
- Illumination-Aware Low-Light Image Enhancement with Transformer and Auto-Knee Curve7
A novel two-stage method to tackle the problem of uneven illumination distribution in low-light images by designing an illumination-aware transformer network for the first stage of image restoration and introducing the Illumination-aware Attention Block featured with Illumination-aware Multi-head Self-attention, which enhances the denoising and reconstruction capabilities of the restoration network.
- 7
- G2-DUN: Gradient Guided Deep Unfolding Network for Image Compressive Sensing7
By introducing the gradient map, the proposed message transmission system not only facilitates the informational communication between different functional modules within each phase, but also strengthens the inferential cooperation among cascaded phases.
- 7
- An enhanced entropy coding scheme for HEVC7
A modification to Context-based Adaptive Binary Arithmetic Coding in High Efficiency Video Coding (HEVC), which includes an improved context modeling for transform coefficient levels and a binary arithmetic coding (BAC) engine with low memory requirement is presented.
- 7
- 7
- Optimal filter based on scale-invariance generation of natural images7
This study adaptively estimates an optimal filter computation whose response distributions through scales have the least Kullback–Leibler divergence, and uses this data to model the statistics scale-invariance prior.
- 7
- 7
- 7
- 7
- 7
- Fast and Effective Interpolation Using Median Filter7
This paper proposes a fast and effective image interpolation algorithm using median filter that is comparable to the well-known NEDI algorithm in visual quality, however, with much lower computational complexity.
- 7
- 7
- 7
- 7
- 7
- 6
- Accurate entropy modeling in learned image compression with joint enchanced SwinT and CNN6
This paper reconstructs the main AE and hyper AE of LIC based on ESTCB, enhancing their global transformation capabilities and resulting in a more accurate coarse-grained entropy model, and combines ESTCB with the checkerboard mask and the channel autoregressive model to develop a spatial then channel fine-grained entropy model.
- Spatial and temporal pyramid-based real-time gesture recognition6
A spatial pyramid is applied to linguistically segment gesture sequence into linguistic units and a temporal pyramid is proposed to get a time-related histogram for each single gesture to improve the effectiveness and accuracy of HGR.
- Compressed Vision Information Restoration Based on Cloud Prior and Local Prior6
A compressed vision information restoration method based on two explored vision priors, which can be obtained from the nature images set in the cloud, and fields of experts is used to formulate the statistical character of the nature image contents as a high order Markov random field, is proposed.
- 6
- 6
- 6
- 6
- Rate control for consistent visual quality of H.264/AVC encoding6
Extensive experimental results exhibit that higher coding performance, consistent visual quality and compliant buffer constraint can be achieved by the proposed algorithm.
- 6
- 6
- 6
- Rate-distortion optimization with inter-view refreshment for stereoscopic video coding over error-prone networks6
An end-to-end distortion model for stereoscopic video coding is proposed which concurrently considers network conditions, inter-view refreshment, and error concealment tools, and a rate-distortion optimization algorithm is presented to adaptively select inter-View, inter and intra coding modes for error-resilient stereoscope video coding.
- An auto-regressive model for improved low-delay distributed video coding6
The experimental results have demonstrated that the proposed AR model can significantly improve the PSNR of the side information compared to existing motion extrapolation based approaches.
- 6
- 6
- Multi-view Video Coding with Flexible View-Temporal Prediction Structure for Fast Random Access6
This paper proposes an algorithm to flexibly regulate the viewtemporal prediction structure that is able to achieve a good trade-off between compression performance and random access ability.
- 6
- 6
- 5
- Probability-based Distance Estimation Model for 3D DV-Hop Localization in WSNs5
A probability-based average distance estimation (PADE) model that utilizes the probability distribution of node distances detected by an anchor node to derive the average distances of nodes detected by an anchor node at different hops is proposed.
- 5
- 5
- 5
- Game theory based no-reference perceptual quality assessment for stereoscopic images5
Inspired by the binocular rivalry mechanism, the observation annoyance perception is explained as a bargain process and an annoyance map is calculated to simulate the observer perception to show a high degree of consistency with the subjective scores.
- 5
- 5
- 5
- 5
- 5
- Low bit-rate image coding via interpolation oriented adaptive down-sampling5
Experimental results verify that utilizing the downsampled image by the proposed algorithm, an interpolated image with much higher quality can be achieved and is able to achieve superior performance than JPEG for low bit rate image coding.
- 5
- 5
- Enhanced Active Shape Models with Global Texture Constraints for Image Analysis5
This paper proposes to enhance ASMs by introducing global texture constraints expressed by its reconstruction residual in the texture subspace by firstly matched by its local profile in its current neighborhood and then re-shaped by the statistical shape constraint.
- Unified Framework For Classifying Facial Images Based On Facial Attribute- Specific Subspaces And Minimum Reconstruction Error5
A unified framework for classifying facial attributes is presented, motivated by, but essentially different from the conventional Eigenface based methods, since, in this framework, similarity is measured by the reconstruction error.
- 4
- Toward a Stable, Fair, and Comprehensive Evaluation of Object Hallucination in Large Vision-Language Models4
This paper presents the first systematic investigation into the effect of instructions on object hallucinations in LVLMs, with a focus on the role played by image description lengths, and introduces LeHaCE, which incorporates the curve slope as an innovative hallucination evaluation metric.
- 4
- Multi-scale Similarity Enhanced Guided Normal Filtering4
A novel mesh denoising scheme in which multi-scale similarity is exploited to improve the performance of non-local normal filtering for feature-preserved mesh restoration and which outperforms other local and non-scale-aware similarity based schemes in terms of both objective and subjective evaluations.
- Feature-Preserving Mesh Denoising Based on Guided Normal Filtering4
This paper proposes a feature-preserving denoising framework that uses joint bilateral filtering and partial neighborhood filtering to deal with the face normals these two kinds of faces.
- 4
- Model-based low bit-rate video coding for resource-deficient wireless visual communication4
Experimental results demonstrate that the proposed video coding scheme outperforms H.264/AVC and other state-of-the-art methods in rate-distortion performance at low bit-rates and achieves superior visual quality at medium bit rates as well, while with lower encoding computational complexity.
- 4
- 4
- 4
- 4
- Optimal entropy-constrained non-uniform scalar quantizer design for low bit-rate pixel domain DVC4
An optimal entropy-constrained non-uniform scalar quantizer is proposed for the pixel domain DVC and can improve the performance by 0.5 dB averagely compared to the uniform scalar quantization.
- 4
- 4
- A joint encoder–decoder error control framework for stereoscopic video coding4
The experimental results show that the proposed joint encoder-decoder error control framework has superior error robustness performance for stereoscopic video transmission over error-prone networks.
- 4
- A Rate Control Algorithm for Scalable Video Coding4
Comparing to the original rate control method which achieves the target bit rate through regulating quantization parameter(QP)step by step, the computation complexity of the proposed rate control algorithm base on experimental model is reduced drastically.
- Effort analysis in signer-independent sign gestures4
Based on the principles of movement observation science, specifically Laban Movement Analysis (LMA), a summary of the factors causing sign language data variation is presented, and a method for describing, sign language effort elements is proposed and then a strategy for standardizing signer-independent signlanguage data is provided.
- Region-based fusion strategy for side information generation in DMVC4
Experimental results demonstrate that the RCCM can more accurately model the "correlation channel" between the original frame and side information and thus, less bits are required for decoding a Wyner-Ziv frame.
- Fast rate allocation based on distortion estimation modeling in scalable video coding4
A fast rate allocation algorithm by modeling distortion estimation is proposed that results in a reduction in decoding time of nearly 50%, and save the runtime of rate allocation by 45.3%, while the PSNR loss of decoded sequence is only 0.04 dB on average.
- 4
- Embedded image coding based on novel organization of DCT coefficients4
In addition to the well known property of energy compaction, novel organization of block-based DCT coefficients has similar characteristics to wavelet transform when taking an image as a single DCT clustering entity and can be exploited to obtain higher compression performance and to widen DCT applications.
- 3
- DOC-GS: Dual-Domain Observation and Calibration for Reliable Sparse-View Gaussian Splatting3
A unified Dual-domain Observation and Calibration (DOC-GS) framework that models and corrects Gaussian reliability through the synergy of optimization-domain inductive bias and observation-domain evidence is proposed.
- FLAM: Foundation Model-Based Body Stabilization for Humanoid Locomotion and Manipulation3
Experimental results on a humanoid robot benchmark demonstrate that FLAM outperforms state-of-the-art RL methods, highlighting its effectiveness in improving stability and overall performance.
- Fast Noisy Image Quality Assessment Based on Free-Energy Principle3
A fast noisy image quality assessment approach under the theory of free-energy principle, in which the internal generative model is first generalized from AR simulation and then instantiated with simple but effective median function.
- Mesh Denoising with Local Guided Normal Filtering and Non-local Similarity3
Experimental results show that the proposed mesh denoising scheme outperforms the state-of-the-art techniques, in terms of both objective and perceptual metrics, especially for the meshes with regular structures.
- Arithmetic coding using hierarchical dependency context model for H.264/AVC video coding3
A hierarchical dependency context model (HDCM) is firstly proposed to exploit the statistical correlations of DCT (Discrete Cosine Transform) coefficients in H.264/AVC video coding standard, and can achieve similar coding performance as CABAC at low and high QPs (quantization parameter).
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- A Fast Video Transcoder from Wyner-Ziv to AVS3
Experimental results demonstrate that the proposed transcoder can significantly reduce the encoding complexity of AVS, and meanwhile provide close compression performance compared with that can be achieved by performing mode decision and a full-scale motion search.
- Template based illumination compensation algorithm for multiview video coding3
A template based illumination compensation method is presented, and a template models selection strategy is devised to improve the illumination compensation performance and experimental results show that the proposed algorithm can improve the coding efficiency significantly.
- Fovea based image quality assessment3
Experimental results indicate that the consistency and relevance between FSSIM and mean opinion score (MOS) are both better than SSIM and PSNR clearly.
- Error-resistance and Low-complexity Integer Inverse Discrete Cosine Transform3
A low-complexity multiplication-free integer inverse discrete cosine transform based on data flow structure of improved AAN’s fast IDCT is proposed for error drifting resistance of decoder and shows that it reduces the error drifting of decoders efficiently.
- 3
- Effective algorithms for fast transcoding of AVS to H.264/AVC in the spatial domain3
A simple and effective method by reusing the mode and motion vectors to achieve high-efficient and fast transcoding and a fast intra transcoding algorithm based on the distribution of the DCT coefficients is proposed to speed up the transcoding process.
- 3
- 3
- 3
- Three-dimensional subband scalable video coding embedded with H.264/AVC codec3
A new Base Layer coding scheme is presented which introduces the rate-distortion optimization mode decision into hierarchical-fashion B-picture coding with open-loop structure and improves the coding performance and visual quality at both low and high bit-rate points.
- Architectures of incorporating MPEG-4 AVC into three-dimensional wavelet video coding3
This paper presents the architectures about how to efficiently incorporate base layer codec MPEG-4 AVC into 3D wavelet video coding and also compatibility with existing video compression standards.
- 2
- Task-Agnostic Learning to Accomplish New Tasks2
A task-agnostic learning method that can learn fragmented knowledge only from task-agnostic data to accomplish new tasks and outperforms the state-of-the-art offline RL methods and IL methods by more than 20%.
- 2
- Mesh Denoising Using Filtering Coefficients Jointly Aware of Noise and Geometry2
A novel Filtering Coefficient Learner for mesh denoising is developed, which delicately generates coefficients to filter face normals based on two types of geometric features, namely the category feature and face-wise features.
- DV-Hop localization based on Distance Estimation using Multinode and Hop Loss in WSNs2
A DV-Hop localization based on the distance estimation using multinode (DEMN) and the hop loss in WSNs is proposed to address the two issues of location awareness and how to select a suitable solution from multiple solutions obtained by the Euclidean distance loss.
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 3D silhouette tracking with occlusion inference2
A 3D silhouette tracking framework to resolve occlusions and recover the appearances in 3D space, which enhances tracking effectiveness and the experiments under the public LAB and SCULPTURE datasets validate the feasibility and effectiveness.
- Side information enhancement via texture and motion activity analysis in distributed video coding2
This paper proposes a simple and effective DVC scheme based on artifact detection and removal, which re-code them in intra mode and replace the co-located ones at the decoder side so that the quality of SI is enhanced.
- 2
- 2
- A JND Guided Foveation Video Coding2
A novel just noticeable distortion (JND) guided foveation video coding method, by which the foveated region can be adaptively selected according to the video content, is presented.
- A 3D auto-regressive model for bidirectional prediction2
To derive accurate AR coefficients, this paper proposes a framework that performs simultaneous coefficient estimation and image interpolation and confirms that the proposed method has superior performance for bi-directional prediction.
- 2
- An Improved Motion Vector Prediction Scheme for Video Coding2
The experimental results show that the improved scheme achieves better coding efficiency than the original median predictor, and the point obtained by the proposed MVP scheme is closer to the global minimum point, the following fast motion estimation (FME) computation complexity is reduced.
- Adaptive Search Range Scaling for B Pictures Coding2
A frame-level adaptive search range scaling strategy for B pictures coding for H.264/AVC from the hardware-oriented viewpoint that can not only reduce approximate 60% search area of B pictures, but also keep almost the same coding performance as the reference software.
- 2
- 2
- High Efficient Context-Based Variable Length Coding with Parallel Orientation2
A new well-designed context-based VLC entropy coder for transform coefficients that exploits coefficient block’s inner context information to obtain high coding efficiency, and at the same time context models for successive coding elements are designed to be dependent-free so that the coder is more apt to be parallel.
- Approximating Inference on Complex Motion Models Using Multi-model Particle Filter2
This paper proposes the idea of approximating the complex motion model using a set of simple motion models to deal with the tracking problems cumbered by complex motions, and provides a practical way to do inference on the set ofsimple motion models instead of original complexMotion model in the particle filter.
- Design of a wavelet slave processor for audio and video decompression2
The intention of this paper is to present an architecture for a WT slave processor, an architectural design for an integer Wavelet Slave Processor (WSP) for decompression and to show the effectiveness of wavelet transform.
- VLSI design of a programmable DCT engine for digital cameras2
It is proposed in here that DCT followed by Embedded Zerotree Coding (EZC) of DCT coefficients can be competitive to wavelet compression scheme.
- 1
- Region-Level Context-Aware Multimodal Understanding1
This work proposes Region-level Context-aware Visual Instruction Tuning (RCVIT), which incorporates object information into the model input and enables the model to utilize bounding box coordinates to effectively associate objects'visual content with their textual information.
- 1
- Multiscale and multidirection depth map super resolution with semantic inference1
Experimental results demonstrate that the proposed multiscale and multidirection depth map super resolution framework with semantic inference has a significant improvement than the state‐of‐the‐art algorithms both visually and quantitatively.
- 1
- 1
- 1
- 1
- ODD: An Algorithm of Online Directional Dictionary Learning for Sparse Representation1
Experimental results show that the reconstruction performance of the proposed approach exceeds other competitive dictionary learning based image sparse representation methods, validating the superiority of the approach.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- Up-sampling oriented frame rate reduction1
Experimental results conducted on various sequences demonstrate that the proposed frame rate reduction is able to significantly improve the quality of up-sampled frames compared with other down-sampling methods.
- 1
- 1
- Directional frame interpolation for MPEG compressed video1
The experimental results demonstrate that the proposed directional frame interpolation for MPEG compressed video achieves better performance than the traditional linear methods such as Bicubic and Bilinear and the edge-directed methodssuch as LAZA and NEDI, while keeping low computational complexity which meets the requirement of practical applications.
- 1
- 1
- 1
- An Image Data Hiding Method Using Pixel-Based JND Model1
A spatial data hiding using pixel-based JND (Just-Noticeable Distortion) model to modify the difference image between host image and predictive image to hide the data and shows that the stego-image is visually indistinguishable from the original cover-image and has better quality for Stego image.
- 1
- A fast intra 4×4 mode decision algorithm for H.264/AVC down rate transcoding1
A fast intra 4×4 mode decision algorithm is proposed to reduce the intra transcoding complexity by using the surrounding modes in the high bitrate and the modes of the neighboring blocks in the current bitrate to form the candidate modes.
- Compressed image restoration based on edge enhancement field of experts1
A degradation model, represent by additive Gaussian noise model, is proposed to simulate JPEG compression process, while the original image is modeled as a high order Markov random field (MRF) based on the fields of experts framework to restore the high frequency (HF) components.
- 1
- 1
- 1
- 1
- Rate distortion cost modeling of skip mode and early skip mode selection for H.264/MPEG-4 AVC1
The proposed linear rate-distortion (RD) cost model is derived theoretically based on the quantization scheme of H.264, and the simulation results verify that the proposed RD cost model can estimate the RD cost of skip mode accurately.
- Improvements of multiple FGS layers coding for low-delay applications in SVC1
A more efficient multiple FGS layers coding structure is presented, which can provide higher coding performance within wide bitrate range and stronger error resilience, and through selecting different-quality enhancement layer references generated with cycle-based reconstruction mechanism, more flexible video quality can be supported.
- 1
- 1
- 1
- Illumination Invariant Feature Selection for Face Recognition1
A novel hybrid illumination invariant feature selection scheme for face recognition, which is a combination of geometrical feature extraction and linear subspace projection, and the NHE+DFLD yields the best performance.
- A study on the motion vector prediction schemes for AVS1
Two MVP schemes for a new coding standard, Audio and Video Standard (AVS), are proposed, suitable for different video sequences with different motion characteristics, respectively, and the experimental results show that the bit rate savings are achieved with these schemes, compared with the median predictor implemented in AVS.
- LLEC: An Image Coder with Low-Complexity and Low-Memory Requirement1
The experimental results show that the compression efficiency of DCT- and DWT-based LLEC outperforms baseline JPEG and EZW at the given bit rates, respectively.
- –
- –
- –
- –
- –
- Bidirectional Feature-Aligned Motion Transformation for Efficient Dynamic Point Cloud Compression–
A Bidirectional Feature-aligned Motion Transformation (Bi-FMT) framework that implicitly models motion in the feature space, and a Random Access (RA) reference strategy that treats the bidirectionally aligned features as conditional context, enabling frame-level parallel compression and eliminating the sequential encoding.
- –
- –
- –
- –
- PVINet: Point-Voxel Interlaced Network for Point Cloud Compression–
A point-voxel interlaced network (PVINet) is proposed, which captures global structural features and local contextual features in parallel and performs interactions at each scale to enhance feature perception efficiency.
- –
- –
- A New Fast Algorithm for Sample Adaptive Offset–
A fast SAO algorithm in HEVC encoder is proposed, which explores the correlation of SAO type among neighboring CTUs, and then utilizes this spatial information to reduce the complexity ofSAO.
- –
- –
- –
- –
- –
- Image Restoration via Multi-prior Collaboration–
A big reference image set is adopted to provide the references and predictions of different popular prior models and accordingly further guide the subsequent multi-prior collaboration, which improves the restoration performance significantly.
- –
- –
- Quality assessment of stereoscopic images based on the significance of perceptual vision–
The experimental results confirm that, in comparison with traditional methods, the raised objective assessment method sufficiently considers the coordination of various psychological and physiological factors in the task of image quality assessment, it is more relevant to the subjective image quality Assessment of human.
- –
- –
- –
- Corrections to “A Spatio-Temporal Auto Regressive Model for Frame Rate Up-Conversion” [Sep 09 1289-1301–
In the above titled paper (ibid., vol. 19, no. 9, pp. 1289-1301, Sep. 09), the column under 3-DRS in Table II is incorrect due to the author's table editing error.
- –
- –
- –
- –
- The design,motion analysis and dynamic simulation of the planetary gear wall-climbing robot–
The three-dimensional modeling,virtually and dynamic simulation of the robot which based on the three- dimensional modeling software such as Solid Edge and UG are demonstrated respectively and elaborately.
- –
- Smooth extraction of SVC fine-granular SNR scalable videos with a virtual-GOP-based rate-distortion modeling–
This paper introduces the R-D analysis of SVC FGS coding and a practical non-search algorithm for smooth quality reconstruction and presents virtual GOP concept and a virtual-GOP-based packet scheduling algorithm is proposed to acquire the optimal packet scheduling sequence in a virtual GOP.
- –
- –
- –
- –
- –
- A Real-Time Video Deinterlacing Scheme for MPEG-2 to AVS Transcoding–
Experimental results show that the presented scheme is more insensitive to incorrect motion vectors than conventional algorithms, and targeting at higher coding efficiency and lower complexity than existing standards for high definition video coding.
- Study on new fast intetf rame coding mode decision based on rate-distortion function cost–
A kind of new algorithm for deciding the coding mode of a macroblock more fast based on the rate-distortion theory is put forward that can saving 20%-30% coding times than the classical most best coding mode decision at the cost of an ignorable influence on the quality of video coding.
- Morphological Representation of DCT Data for Image Coding–
It is pointed out that the block-based DCT by proper reorganization and representation of its coefficients can have the similar characteristics to wavelet transform, such as energy compaction, crosssubband similarity, decay of magnitude across subband, etc.
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.