Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks189 from public data
- Large-scale visual sentiment ontology and detectors using adjective noun pairs862
This work presents a method built upon psychological theories and web mining to automatically construct a large-scale Visual Sentiment Ontology (VSO) consisting of more than 3,000 Adjective Noun Pairs (ANP) and proposes SentiBank, a novel visual concept detector library that can be used to detect the presence of 1,200 ANPs in an image.
- Executing your Commands via Motion Diffusion in Latent Space766
The proposed Motion Latent-based Diffusion model (MLD) could produce vivid motion sequences conforming to the given conditional inputs and substantially reduce the computational overhead in both the training and inference stages.
- An epidermal sEMG tattoo-like patch as a new human–machine interface for patients with loss of voice145
The design of an imperceptible, flexible epidermal sEMG tattoo-like patch with the thickness of less than 10 μm and peeling strength of larger than 1 N cm−1 that exhibits large adhesiveness to complex biological surfaces and is thus capable of s EMG recording for silent speech recognition is demonstrated.
- Cascade EF-GAN: Progressive Facial Expression Editing With Local Focuses119
The introduction of the local focus enables the Cascade EF-GAN to better preserve identity-related features and details around eyes, noses and mouths, which further helps reduce artifacts and blurs within the generated facial images.
- 113
- End-to-End 3D Dense Captioning with Vote2Cap-DETR112
Without bells and whistles, extensive experiments on two commonly used datasets, ScanRefer and Nr3D, demonstrate that the proposed Vote2Cap-DETR surpasses current state-of-the-arts by 11.13% and 7.11% in CIDEr@0.5IoU, respectively.
- 111
- Internet visual media processing: a survey with graphics and vision applications89
Recent research as regards processing of large collections of images and video, including work on analysis, manipulation, and synthesis is surveyed, and possible future directions in this emerging research area are suggested.
- Word Embedding Composition for Data Imbalances in Sentiment and Emotion Classification88
This paper presents an oversampling method based on word embedding compositionality which produces meaningful balanced training data and achieves improved results for both sentiment and emotion classification.
- Landmark recognition with compact BoW histogram and ensemble ELM87
A landmark recognition framework is proposed by employing a novel discriminative feature selection method and the improved extreme learning machine (ELM) algorithm to generate a set of preliminary codewords for landmark images.
- 83
- 77
- BerDiff: Conditional Bernoulli Diffusion Model for Medical Image Segmentation74
The proposed BerDiff uses the Bernoulli noise as the diffusion kernel to enhance the capacity of the diffusion model for binary segmentation tasks, resulting in more accurate segmentation masks and suggests diffusion models could serve as a strong backbone for medical image segmentation.
- Curriculum-Style Local-to-Global Adaptation for Cross-Domain Remote Sensing Image Segmentation74
Experimental results demonstrate that the proposed curriculum-style local-to-global cross-domain adaptation framework can significantly boost the domain adaptability of segmentation networks for VHR RSIs.
- M$^3$Lung-Sys: A Deep Learning System for Multi-Class Lung Pneumonia Screening From CT Imaging71
The quantitative results with plenty of metrics indicate the superiority of the proposed model on both slice- and patient-level classification tasks, and the generated lesion location maps make the system interpretable and more valuable to clinicians.
- Towards a comprehensive computational model foraesthetic assessment of videos69
A novel aesthetic model emphasizing psycho-visual statistics extracted from multiple levels in contrast to earlier approaches that rely only on descriptors suited for image recognition or based on photographic principles that demonstrates strong correlation with human prediction on 1,000 broadcast quality videos released by NHK as an aesthetic evaluation dataset.
- 64
- 63
- ShapeGPT: 3D Shape Generation With a Unified Multi-Modal Language Model62
This article presents ShapeGPT, a shape-included multi-modal framework to leverage strong pre-trained language models to address multiple shape-relevant tasks, and demonstrates that ShapeGPT achieves comparable performance across shape-relevant tasks, including text-to-shape, shape-to-text, shape completion, and shape editing.
- 61
- 60
- A Large-Scale Outdoor Multi-modal Dataset and Benchmark for Novel View Synthesis and Implicit Scene Reconstruction58
A large-scale outdoor multi-modal dataset, OMMO dataset, containing complex objects and scenes with calibrated images, point clouds and prompt annotations is proposed, establishing a new benchmark for several outdoor NeRF-based tasks, such as novel view synthesis, diverse 3D representation, and multi-modal NeRF.
- Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning55
This paper proposes Vote2Cap-DETR, a simple-yet-effective transformer framework that decouples the decoding process of caption generation and object localization through parallel decoding, and proposes an advanced version, Vote2Cap-DETR++, which decouples the queries into localization and caption queries to capture task-specific features.
- Uni3D: A Unified Baseline for Multi-Dataset 3D Object Detection55
A Uni3D is presented which leverages a simple data-level correction operation and a designed semantic-level coupling-and-recoupling module to alleviate the unavoidable data- level and taxonomy-level differences, respectively.
- 55
- BiLO-CPDP54
This paper proposes a tool, dubbed BiLO-CPDP, which is the first of its kind to formulate the automated CPDP model discovery from the perspective of bi-level programming, and champions better prediction performance than all other 21 existing C PDP techniques on 70% of the projects, while being overwhelmingly superior to Auto-Sklearn and its single-level optimization variant on all cases.
- 54
- 53
- 52
- Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classification52
Extensive experiments demonstrate that HelixFormer can effectively enhance the cross-image object semantic relation matching for recognizing fine-grained objects, achieving much better performance over most state-of-the-art methods under 1-shot and 5-shot scenarios.
- Fine-grained facial expression analysis using dimensional emotion model50
This paper proposes to train deep convolutional neural networks (CNNs) to analyze facial expressions explainable in a dimensional emotion model and improves the method by a bilinear pooling which encodes second-order statistics of features.
- 45
- Performance-Aware Approximation of Global Channel Pruning for Multitask CNNs44
Experiments on several multitask datasets show that the proposed PAGCP can reduce the FLOPs and parameters by over 60% with minor performance drop, and achieves 1.3x acceleration on both cloud and mobile platforms.
- Exploring Multi-Timestep Multi-Stage Diffusion Features for Hyperspectral Image Classification41
A novel diffusion-based feature learning framework that explores multi-timestep multi-stage diffusion features for HSI classification for the first time, called MTMSD, which outperforms state-of-the-art methods for HSI classification, especially on the challenging Houston 2018 dataset.
- Bi3D: Bi-Domain Active Learning for Cross-Domain 3D Object Detection41
This work proposes a Bi-domain active learning approach, namely Bi3D, to solve the cross-domain 3D object detection task, and develops a domainness-aware source sampling strategy, which identifies target-domain-like samples from the source domain to avoid the model being interfered by irrelevant source data.
- Object-aware Long-short-range Spatial Alignment for Few-Shot Fine-Grained Image Classification41
This work proposes an object-aware long-short-range spatial alignment approach, which is composed of a foreground object feature enhancement (FOE) module, a long-range semantic correspondence (LSC) module and a short-rangeatial manipulation (SSM) module that is developed to weaken background disturbance and encourage higher foreground object response.
- 37
- What Makes for Effective Few-shot Point Cloud Classification?34
A novel plug-and-play component called Cross-Instance Adaptation (CIA) module is proposed, to address the high intra-class variances and subtle inter-class differences issues, which can be easily inserted into current baselines with significant performance improvement.
- 33
- 32
- 32
- 31
- Attention Reallocation: Towards Zero-cost and Controllable Hallucination Mitigation of MLLMs29
AttnReal recycles excessive attention from output tokens and reallocates it to visual tokens, which reduces MLLM’s reliance on language priors and ensures the decoding process depends more on the visual inputs.
- A Closer Look at Few-Shot 3D Point Cloud Classification29
This work performs systematic and extensive investigations of directly applying recent 2D FSL works to 3D point cloud related backbone networks and proposes a new network, Point-cloud Correlation Interaction (PCIA), with three novel plug-and-play components called Salient-Part Fusion (SPF), Self-Channel Interaction Plus (SCI), and Cross-Instance Fusion Plus (CIF+) module to improve the feature distinction.
- Joint Distribution Alignment via Adversarial Learning for Domain Adaptive Object Detection29
An end-to-end joint adversarial adaptation framework for object detection is proposed, which aligns both marginal and conditional distributions between domains without introducing any extra hyper-parameter.
- Point Cloud Instance Segmentation With Semi-Supervised Bounding-Box Mining28
This paper introduces the first semi-supervised point cloud instance segmentation framework (SPIB) using both labeled and unlabelled bounding boxes as supervision and introduces a novel occupancy ratio guided refinement module to refine the instance masks.
- Densely Semantic Enhancement for Domain Adaptive Region-Free Detectors28
The proposed adversarial module, namely, densely semantic enhancement module (DSEM), is proposed to strengthen the cross-domain matching of instance-level features for region-free detectors and outperforms existing domain adaptive region-based detectors under various domain shift settings.
- 28
- Generalized Global Ranking-Aware Neural Architecture Ranker for Efficient Image Classifier Search25
The proposed Neural Architecture Ranker (NAR), a predictor which concentrates on the global quality tier of specific architecture, achieves better performance than the state-of-the-art methods on two widely used datasets for NAS research.
- UV-Induced Chromatism of Polydiacetylenic Assemblies25
Highly ordered lamellar polydiacetylene nanocomposites are synthesized by assembling polydacetylene and azobenzene through a ready solution process that induces a conformational change of polydACetylene with a color change from blue to red.
- 24
- 24
- Partial Fine-Tuning: A Successor to Full Fine-Tuning for Vision Transformers23
A novel fine-tuned angle metric is proposed to guide the selection of appropriate layers for partial fine-tuning, making it flexible to be adapted to various scenarios for more practicable partial fine-tuning.
- 23
- The durability of flexible eddy current array (FECA) sensors in harsh service environments23
FECA sensors can survive in harsh service environments of aircrafts, which provides important support for the engineering applications of FECA sensors.
- 22
- 22
- Rethinking Cross-Domain Pedestrian Detection: A Background-Focused Distribution Alignment Framework for Instance-Free One-Stage Detectors21
This paper proposes a novel framework, namely, background-focused distribution alignment (BFDA), to train domain adaptive one-stage pedestrian detectors that first decouples the background features from the whole image feature maps and then aligns them via a novel long-short-range discriminator.
- BridgeNet: Comprehensive and Effective Feature Interactions via Bridge Feature for Multi-Task Dense Predictions20
This work proposes a novel BridgeNet framework, which extracts comprehensive and discriminative intermediate Bridge Features, and conducts interactions based on them, and is the first work considering the completeness and quality of feature participants in cross-task interactions.
- 20
- 19
- DreamFrame: Enhancing Video Understanding via Automatically Generated QA and Style-Consistent Keyframes17
This work proposes a three-stage framework named DreamFrame for automatically generating style-consistent keyframes and corresponding question-answer pairs to support LVLM instruction tuning, and constructs a new LVLM named DreamFrame-7B, which significantly surpasses the previous similar-sized LVLMs across different benchmarks.
- 17
- ReSimAD: Zero-Shot 3D Domain Transfer for Autonomous Driving with Source Reconstruction and Target Simulation17
Results demonstrate that the proposed Reconstruction-Simulation-Perception (ReSimAD) scheme is beneficial to boost the domain generalization ability, even promising for 3D pre-training.
- Comp-GAN17
A novel end-to-end Compositional Generative Adversarial Network that is able to synthesize new face images with specified poses and desired facial expressions and which can dynamically change the expression and pose of faces according to the input images while keeping the identity information.
- 16
- Optimizing Chinese Character Displays Improves Recognition and Reading Performance of Simulated Irregular Phosphene Maps15
The performance of CC recognition and paragraph reading when using an irregular phosphene array can be improved through optimizing the display method.
- 15
- Automatic Extraction of Skeleton and Center of Area Feature15
An approach to the automatic extraction of skeleton and center based on the constraint Delaunay triangulation is presented and the algorithm is developed in detail and its properties are analyzed by experiment.
- 14
- Experts Weights Averaging: A New General Training Scheme for Vision Transformers14
A new general training strategy for ViTs that decouple the training and inference phases of ViTs, and can significantly improve the effectiveness of naive MoE in various 2D visual small datasets and 3D visual tasks.
- 14
- 13
- Rethinking Saliency Map: A Context-Aware Perturbation Method to Explain EEG-Based Deep Learning Model12
A new context-aware perturbation method that not only extends the scope to the instance level but can capture the representative context information when estimating the saliency map and points out another role of context information in explaining the EEG-based model.
- 12
- Chimera: Improving Generalist Model with Domain-Specific Experts11
Chimera, a scalable and low-cost multi-modal pipeline designed to boost the ability of existing LMMs with domain-specific experts with a novel Generalist-Specialist Collaboration Masking mechanism, results in a versatile model that excels across the chart, table, math, and document domains.
- 11
- 11
- 10
- Extreme Learning Machine on High Dimensional and Large Data Applications10
This paper presents a meta-modelling system that automates the very labor-intensive and therefore time-heavy and expensive process of integrating IOT and information fusion technology into the fabric of modern society.
- Recursive implementation of constrained LMS L-filters for image restoration10
Simulations conducted show the advantage of the recursive L-filter over its nonrecursive counterpart in suppressing image noise.
- 9
- 9
- Boosting Residual Networks with Group Knowledge9
A group knowledge based training framework for boosting the performance of residual networks by implicitly dividing all subnets into hierarchical groups by subnet-in-subnet sampling, aggregate the knowledge of different subnets in each group during training, and exploit upper-level group knowledge to supervise lower-level subnet group.
- 9
- Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering9
This paper proposes a learning framework that trains models to predict geometry-preserving depth without requiring extra data or annotations, and renders novel views of the reconstructed scenes and design loss functions to promote depth estimation consistency across different views.
- 9
- JMNet: A joint matting network for automatic human matting9
A novel end-to-end deep learning framework, the JMNet, to automatically generate alpha mattes for human images by introducing a pose estimation module, which can provide both global structural guidance and a local attention focus for the matting task.
- Implantable Imaging System for Visual Prosthesis9
An implantable microcamera was developed and evaluated in vivo for intraocular imaging system for the visual prosthesis and short-term results showed the novel approach is promising.
- 8
- 8
- Spectral-spatial adaptive and well-balanced flow-based anisotropic diffusion for multispectral image denoising8
An effective denoising algorithm is presented by integrating the spectral-spatial adaptive mechanism into a well-balanced flow (WBF) based anisotropic diffusion model, in which an adjustable weighted function is introduced to perform the appropriate levels of smoothing and enhancing according to different feature scales.
- EXIF-white balance recognition for image forensic analysis8
The proposed evidence can detect cascade manipulated images which are subject to copy-and-paste followed by different white balance post-processing operations, high compression or heavy downsampling in both theoretical and realistic scenarios.
- DSF2-NAS: Dual-Stage Feature Fusion via Network Architecture Search for Classification of Multimodal Remote Sensing Images7
A dual-stage feature fusion framework based on NAS, termed DSF2-NAS, is proposed, aiming to better integrate multimodal features with complex spatial and channel information, and achieves state-of-the-art performance across multiple classification metrics.
- Revisiting face forgery detection towards generalization7
This first comprehensive overview and in-depth analysis of the generalizable face forgery detection methods is presented, categorizing the target of generalizable face forgery detection into the robustness on novel and unknown forged images, and robustness on damaged low-quality images.
- Efficient Architecture Search via Bi-Level Data Pruning7
This work introduces a progressive bi-level data pruning strategy that utilizes supernet prediction dynamics as the metric to gradually prune unsuitable samples for DARTS during the search, and proposes a novel Bi-level Data Pruning (BDP) paradigm that targets the weights and architecture levels of DARTS to enhance efficiency from a data perspective.
- 7
- Digital Analysis of Smart Registration Methods for Magnetic Resonance Images in Public Healthcare7
This study compares the performance of three publicly available registration techniques in brain magnetic resonance imaging (MRI) analysis based on some key features widely used in previous MRI studies for classification and detection tasks.
- Adaptive dictionary learning based on local configuration pattern for face recognition7
An algorithm of adaptive dictionary learning according to the inputting testing image, which ensures not only that the information included in face image is not lost but also that the atoms are more similar to the testing image in structure, which greatly increases the recognition accuracy.
- 7
- Crowd Security Detection based on Entropy Model.7
A physical entropy model is provided to measure the crowd security level and by recognizing the entropy mutation, it is possible to automatically detect the abnormal crowd behavior and to set the warning alarm.
- Pioneering 4-Bit FP Quantization for Diffusion Models: Mixup-Sign Quantization and Timestep-Aware Fine-Tuning6
The mixup-sign floating-point quantization (MSFP) framework is proposed, first introducing unsigned FP quantization in model quantization, along with timestep-aware LoRA and denoising-factor loss alignment (DFA) which ensure precise and stable fine-tuning.
- Point Cloud Instance Segmentation with Inaccurate Bounding-Box Annotations6
A novel self-distillation architecture is presented to boost the generalization ability while leveraging the cheap but noisy bounding-box annotations, and employs consistency regularization to distill self-knowledge from data perturbation and historical predictions.
- DECap: Towards Generalized Explicit Caption Editing via Diffusion Mechanism6
This work reformulates the ECE task as a denoising process under the diffusion mechanism, and introduces innovative edit-based noising andDenoising processes that can help to eliminate the need for meticulous paired data selection and improve the inference speed.
- SpVOS: Efficient Video Object Segmentation With Triple Sparse Convolution6
A novel triple sparse convolution is developed to reduce the computation costs of the overall VOS framework, and achieves superior performance over other state-of-the-art sparse methods, and even maintains comparable performance on mainstream VOS datasets.
- Coarse-to-Fine Gaze Redirection with Numerical and Pictorial Guidance6
A novel gaze redirection framework which exploits both a numerical and a pictorial direction guidance, jointly with a coarse-to-fine learning strategy and outperforms the state-of-the-art approaches in terms of both image quality and redirection precision.
- 6
- 6
- PM-INR: Prior-Rich Multi-Modal Implicit Large-Scale Scene Neural Representation5
This work explores using multi-modal priors to assist individual points to obtain more global semantic information and proposes a priorrich multi-modal implicit neural representation network, Pm-INR, for the outdoor unbounded large-scale scene.
- A regularized orthogonal activated inverse-learning neural network for regression and classification with outliers5
Both regression and classification experiments show that W-ROAIL neural network has strong ability to suppress the influence of outliers and improves the robustness of the ℓ2-ROAIL neural network by replacing the original two-norm in loss function with Welsch function.
- 5
- 5
- 5
- Orientation space code and multi-feature two-phase sparse representation for palmprint recognition5
A novel orientation-space code scheme to represent the orientation space feature of palmprint is proposed and a novel multi-feature two-phase sparse representation (MTPSR) scheme for feature matching is designed.
- An improved rotation forest algorithm based on heterogeneous classifiers ensemble for classifying gene expression profile5
Experimental results on nine benchmark gene expression profile datasets show the improved rotation forest algorithm based on heterogeneous classifiers ensemble is better than traditional rotation forest, bagging and boosting, and improves not only classification accuracy, but also has high stability and time efficiency.
- 5
- Operating performance assessment of industrial process based on MIC-graph convolutional networks with local slow feature analysis4
A maximum information coefficient-based graph convolutional networks (MIC-GCN) is proposed for operational performance assessment, which aims to effectively capture the intricate interactions of latent spatial structures embedded in temporal process data.
- Lightweight Model Pre-Training via Language Guided Knowledge Distillation4
This paper introduces language guidance to the distillation process and proposes a new method named Language-Guided Distillation (LGD) system, which uses category names of the target downstream task to help refine the knowledge transferred between the teacher and student.
- Instance-aware Model Ensemble With Distillation For Unsupervised Domain Adaptation4
A novel framework, namely Instance aware Model Ensemble With Distillation, IMED, which fuses multiple UDA component models adaptively according to different instances and distills these components into a small model is proposed.
- 4
- A multi-level feature integration network for image inpainting4
This work proposes a multi-level feature integration (MFI) network for image inpainting, and uses PatchGAN to support the refinement generator network to produce more discriminative detail and demonstrates the effectiveness of this network for producing visually pleasing results with semantically ordered textures.
- 4
- 4
- 3
- Meta-TTT: A Meta-learning Minimax Framework For Test-Time Training3
A meta-learning minimax framework for test-time training on batch normalization (BN) layers, ensuring that the SSL task aligns with the primary task while addressing minibatch overfitting, and proposes a stochastic domain synthesizing method to improve model generalization and robustness to domain shifts.
- Rethinking Pseudo-Label-Based Unsupervised Person Re-ID with Hierarchical Prototype-based Graph3
This work proposes a novel hierarchical prototype-based graph network (HPG-Net) for unsupervised person Re-ID that outperforms state-of-the-art (SOTA) works and achieves promising performance on an occluded dataset.
- VQ-NeRF: Vector Quantization Enhances Implicit Neural Representations3
This work proposes VQ-NeRF, an effective and efficient pipeline for enhancing implicit neural representations via vector quantization, and designs an innovative multi-scale NeRF sampling scheme that concurrently optimizes the NeRF model at both compressed and original scales to enhance the network's ability to preserve fine details.
- 3
- BURSTS: A bottom-up approach for robust spotting of texts in scenes3
In the proposed technique, character candidates are first detected using the proposed character detector, which leverages on the strengths of an Extremal Region detector and an Aggregate Channel Feature detector for high character detection recall.
- 3
- A Cloud Computing Security Model Based on Noninterference3
This work proposes noninterference for cloud architecture in which concurrent access and sequential access coexist, and proposes a model that ensures the information flow between security domains can flow in accordance with established rules.
- 3
- 3
- $$\Delta $$-DiT: Accelerating Diffusion Transformers without Training via Denoising Property Alignment2
A denoising property alignment method that adaptively skips computations for different blocks at various timesteps while preserving performance is introduced, highlighting its effectiveness in resource-constrained scenarios.
- 2
- 2
- 2
- An improved low-complexity DenseUnet for high-accuracy iris segmentation network2
An improved low complexity DenseUnet is proposed to this paper based on U-net for acquiring a high-accuracy iris segmentation network and provides the possibility for the deployment of portable mobile devices.
- 2
- 2
- On Cloud Computing Theory and Its Technique2
Cloud computing enables computing capacity to be carried out as a commodity flow, just like the authors' daily life's natural gas, electricity and water, convenient, and of low-cost.
- Perceptual blocking distortion measure for digital video2
A perceptual blocking distortion metric for block-based transform coded digital video is proposed, based on a spatio-temporal multichannel vision model to calculate the Just Noticeable Distortion map.
- A knowledge-driven self-supervised learning method for enhancing EEG-based emotion recognition1
This work proposes a novel knowledge-driven self-supervised learning framework for EEG emotion recognition that incorporates domain knowledge to approximate the extraction of statistical feature differential entropy (DE), aiming to preserve emotion-related and generalizable information.
- 1
- 1
- 1
- Deep cross-view autoencoder network for multi-view learning1
A deep cross-view autoencoder network (DCVAE) that extracts the features of different views and establishes the correlation between views in one step to simultaneously handle view-specific, view-correlation, and consistency in a joint manner is proposed.
- 1
- Spcr: semi-supervised point cloud instance segmentation with perturbation consistency regularization1
- FACIA: A Fully Automatic Change Impact Analysis Method for Large Scale Requirements1
A fully automatic change impact analysis (FACIA) method to overcome the aforementioned shortcomings of existing CIA techniques and show that compared with the method of expert depended, this approach can get a reliable sorted list for CIA more quickly with lower cost.
- Improved group management protocol of RFID password method1
This article introduces the group management of RFID passwords method, come up with by YUICHI KOBAYASHI and other researchers, which aimed to reduce the risk of privacy disclosure.
- 1
- Context-aware vocabulary tree for mobile landmark recognition1
An effective mobile landmark recognition approach which exploits both context (direction and location) and content information for vocabulary tree learning and image recognition is proposed.
- 1
- 1
- 1
- 1
- A Study on the Application of Three-Dimensional Scanning Data Analysis Method Based on Convolutional Neural Network in Machining Inspection–
The improved Faster R-CNN processing detection method is designed by combining the multi-scale feature extraction structure, which improves the efficiency of machining detection by dimensionality reduction of the feature map of the previous layer, then feature extraction, and stitching the features extracted from different scale convolution kernels together.
- –
- –
- –
- –
- –
- –
- –
- Low illumination image enhancement based on attention mechanism and global illumination estimation–
According to the experimental results, this method may effectively improve image brightness, contrast, and color in subjective visual effects while also enhancing objective evaluation indicators like PSNR, SSIM, and MSE when compared to some conventional methods.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Study on Optimization Technologies of Visual Test System for Mountainous Expressway–
This dissertation researches on the application of optimization technologies in mountainous expressway virtual model to improve the operation speed of visual test system for mountainousexpressway Driver-Vehicle-Road system.
- –
- –
- Research in Complex Motion Tracking on Segmentation–
Experimental results shown that this flexible segmental method can track different objects and irregular motion well and this algorithm demonstrated its robustness.
- Physio-parameter Detection and Type Test of Multi-parameter Monitor–
Expounds the definitions and measurement methods of feature parameters,i.e.heart rate,blood pressure,blood oxygen saturation degree, breath, body temperature, etc to emphasize the importance of detecting the safety of electrocardio monitor and the cautions of safety detection.
- –
- Password Authentication Scheme Based on Sunzi Theorem and Euler Function–
The scheme with its advantages such as high feasibility, security and low storage cost overcomes the defects in other authentications such as the password authentication scheme based on the Lagarange polynomial.
- Password Authentication Scheme in Cryptography–
In this dissertation, two new schemes which are based on the polynomial password authentication and meaningful in theory and practical for the changeable network of nowadays are represented.
- The Application of Multi-slice Spiral CT Angiography in Pulmonary Lesions–
MSCT can clearly display the vessels feeding pulmonary lesions in pulmonary lesions as seen in 68 cases with massive hemoptysis caused by lung tumor or other reasons underwent 16-slice spiral CT scan.
- –
- –
- –
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 2026-10-12. 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.