Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks107 from public data
- The Eighth Visual Object Tracking VOT2020 Challenge Results350
A significant novelty is introduction of a new VOT short-term tracking evaluation methodology, and introduction of segmentation ground truth in the VOT-ST2020 challenge – bounding boxes will no longer be used in theVDT challenges.
- Correlation-Aware Deep Tracking200
This work proposes a novel target-dependent feature network inspired by the self-/cross-attention scheme that deeply embeds cross-image feature correlation in multiple layers of the feature network and is able to suppress non-target features, resulting in instance-varying feature extraction.
- 130
- The Ninth Visual Object Tracking VOT2021 Challenge Results127
The Visual Object Tracking challenge VOT2021 is the ninth annual tracker benchmarking activity organized by the VOT initiative; results of 71 trackers are presented; many are state-of-the-art trackers published at major computer vision conferences or in journals in recent years.
- Statistical behavior analysis and precision optimization for the laser stripe center detector based on Steger's algorithm89
In this paper, a statistical behavior analysis for the laser stripe center extractor based on Steger method has been carried out and relationships between center extraction precision, image quality and stripe characteristics have been examined analytically.
- Learning Tracking Representations via Dual-Branch Fully Transformer Networks76
A Siamese-like Dual-branch network based on solely Transformers for tracking, which outperforms the state-of-the-art methods on the GOT-10k and VOT2020 benchmarks and achieves real-time inference speed (about 40 fps) on one GPU.
- Deep Stock Representation Learning: From Candlestick Charts to Investment Decisions51
This work applies Convolutional AutoEncoder to learn a stock representation, based on which a novel portfolio construction strategy is proposed, using the deeply learned representation and modularity optimisation to cluster stocks and identify diverse sectors.
- A New Signal Processing Method Based on Notch Filtering and Wavelet Denoising in Wire Rope Inspection50
A combined signal processing method based on notch filtering and wavelet denoising to process detected wire rope signals is proposed, which can not only distinguish steel wire rope defect signal and strand signal effectively but also with high detection accuracy, even for the inner defect.
- Automatic velocity picking from semblances with a new deep-learning regression strategy: Comparison with a classification approach49
A tutorial overview of two state-of-the-art ML implementations of classification and regression neural networks for the extraction of apparent rms velocity trajectories from semblance data.
- 35
- 32
- 31
- 29
- 27
- Automatic evaluation of facial nerve paralysis by dual-path LSTM with deep differentiated network24
The key idea behind DP-LSTM-DDN is that the diagnosis results are sensitive to the facial asymmetry and the patterns of facial muscular movements when the patients were doing the diagnostic facial actions, and a deep differentiated network is designed to analyze the difference between two sides of patients’ faces.
- 23
- Human body and posture recognition system based on an improved thinning algorithm23
Experimental results demonstrate that the human body and posture estimation algorithm have a robust and real-time performance, and is useful for the discrimination of human postures.
- Representation learning from noisy user-tagged data for sentiment classification22
A novel Weakly-supervised Anti-noise Contrastive Learning framework for sentiment classification, and name it as WACL, which can learn rich contrastive sentiment patterns in the case of label noise and is applicable to a variety of deep encoders.
- 21
- A Two-Step Method for Remote Sensing Images Registration Based on Local and Global Constraints21
The key idea is to remove the mismatches in the initial correspondence set and obtain a stable correspondence through a two-step strategy that is more robust and accurate than state-of-the-art methods.
- 20
- 18
- Attention-Based Spatial and Spectral Network with PCA-Guided Self-Supervised Feature Extraction for Change Detection in Hyperspectral Images18
A novel attention-based spatial and spectral network with PCA-guided self-supervised feature extraction mechanism to detect changes in hyperspectral images and results show the effectiveness and advancement of the proposed method.
- P2P: Part-to-Part Motion Cues Guide a Strong Tracking Framework for LiDAR Point Clouds17
This paper proposes to perform part-to-part motion modeling for consecutive point clouds and introduces a novel tracking framework, termed P2P, which fuses each corresponding part information between consecutive point clouds, effectively exploring detailed information changes and thus modeling accurate target-related motion cues.
- 17
- An Adaptive Surrogate-Assisted Endmember Extraction Framework Based on Intelligent Optimization Algorithms for Hyperspectral Remote Sensing Images17
An adaptive surrogate-assisted endmember extraction (ASAEE) framework based on intelligent optimization algorithms is proposed for hyperspectral remote sensing images in this paper, which shows the effectiveness and the excellent performance of the proposed ASAEE framework.
- Knowledge diffusion of dynamical network in terms of interaction frequency17
The simulation results show that, comparing with the Null model defined by the random selection mechanism and the traditional knowledge diffusion (TKD) model driven by knowledge distance, the knowledge would spread more fast based on SKD driven by interaction frequency.
- 16
- GPR uncertainty modelling and analysis of object depth based on constrained least squares16
The sources of uncertainty affecting an object’s depth measurement with respect to host material, instrumentation, data collection method and signal processing are discussed and a centimetre-order of uncertainty can be achieved in the survey results for depth estimation of objects at several metres deep with a 95% confidence level at ± 2 standard deviations.
- 15
- GA-Net: A geographical attention neural network for the segmentation of body torso tissue composition15
A body composition tissue segmentation method that can automatically delineate those key tissues, including subcutaneous adipose tissue, skeleton, skeletal muscle tissue, and visceral adipose tissue, on positron emission tomography/computed tomography scans of the body torso is proposed.
- 15
- Oral mucosal disease recognition based on dynamic self‐attention and feature discriminant loss14
Convolutional neural networks can effectively capture the visual features of the oral mucosal disease lesions, and the distinguishedVisual features of different oral lesions can be extracted better using dynamic self-attention and feature discrimination loss function, which is conducive to the auxiliary diagnosis of Oral mucosal diseases.
- 13
- Spatial-temporal dynamic semantic graph neural network13
Spatial-temporal dynamic semantic graph neural network is proposed, a dynamic aggregation method is proposed that learns the weighting ratio corresponding to each feature through training and the injection-stacked structure is designed to solve the over-smoothing problem.
- 13
- An importance sampling-based smoothing approach for quasi-Monte Carlo simulation of discrete barrier options13
A so-called sequential importance sampling (SIS) method to remove multiple discontinuity structures sequentially for pricing discrete barrier options is developed, and it is shown that the effective dimension is greatly reduced by the combined method.
- 11
- VRM: Knowledge Distillation via Virtual Relation Matching10
This paper revive relational KD by identifying and tackling several key issues in relation-based methods, including their susceptibility to overfitting and spurious responses, and transfers novelly constructed affinity graphs that compactly encapsulate a wealth of beneficial inter-sample, inter-class, and inter-view correlations.
- 10
- Evolutionary Multiobjective Optimization with Endmember Priori Strategy for Large-Scale Hyperspectral Sparse Unmixing10
An evolutionary multiobjective hyperspectral sparse unmixing algorithm with endmember priori strategy (EMSU-EP) with experiments on two benchmark large-scale simulated data to demonstrate the effectiveness of the proposed algorithm.
- Lesion Segmentation Framework Based on Convolutional Neural Networks with Dual Attention Mechanism10
This paper proposed an end-to-end medical lesion segmentation framework based on convolutional neural networks with a dual attention mechanism, which integrates both fully and weakly supervised segmentation.
- 10
- Mamba-Adaptor: State Space Model Adaptor for Visual Recognition9
This work investigates a simple yet powerful vision task adapter for Mamba models, which consists of two functional modules: Adaptor-T and Adapator-S, and explores three usages of Mamba-Adaptor: A general visual backbone for various vision tasks; A booster module to raise the performance of pretrained backbones; A highly efficient fine-tuning module that adapts the base model for transfer learning tasks.
- 9
- Hierarchical Representations with Discriminative Meta-filters in Dual Path Network for Tracking8
A novel dual path network with discriminative meta-filters and hierachical representations with superior performance compared with other state-of-the-arts methods is proposed.
- 7
- 7
- Spatial-temporal correlated graph neural networks based on neighborhood feature selection for traffic data prediction7
A novel spatial-temporal corelated graph neural network (STCGNN) of data forecasting that can extract the full-scale characteristics of intricate spatial- Temporal graph and can generate spatial-Temporal adjacent correlated matrix based on whole characteristics of time series.
- 5
- Discriminative Segmentation Tracking Using Dual Memory Banks5
This work presents a novel discriminative segmentation tracking architecture equipped with dual memory banks, i.e., appearance memory bank and spatial memory bank, which outperforms the leading segmentation tracker D3S on two video object segmentation benchmarks DAVIS16 and DAVIS17.
- Automatic Degree Evaluation of Facial Nerve Paralysis Based on Triple-stream Long Short Term Memory5
Triple-stream Long Short Term Memory (LSTM) is presented to evaluate the severity degree of facial paralysis automatically and the final fused features could express the facial features for different degrees of facial nerve paralysis more effectively.
- 5
- 4
- 4
- 4
- Spatial-Temporal Semantic Neural Network for Time Series Forecasting4
STSeNN is proposed, which combines graph neural network and TCN to dynamically capture the spatial correlation, temporal correlation and semantic correlation of data to predict traffic flow time series data.
- 4
- 3
- 3
- Unstructured Road Region Detection and Road Classification Algorithm Based on Machine Vision3
The results show that the designed unstructured road classification algorithm can accurately identify the changes of road categories, with an average accuracy of 94.57% on asphalt road, brick road, dirt road, and gravel road.
- Fuzzy Active Contour Model With Markov Random Field for Change Detection3
The Markov random field (MRF) theory is incorporated into the fuzzy active contour model to detect the changes of multitemporal SAR images and is able to accurately segment the difference image and has better performance in comparison with other change detection techniques.
- Evolutionary Multiobjective Site Selection of Xi’an Medical Emergency Material Warehouse Based on Multiple Memetic Directions3
This study aims to select suitable sites of Xi’an medical emergency material warehouse by solving the problem of site selection models as a multiobjective optimization problem.
- 3
- 3
- Computer simulation of investment efficiency function model based on GMM method and artificial intelligence3
An investment efficiency model based on the GMM method and machine learning algorithm is constructed, and the characteristics of multi-scale Gaussian convolution are used to establish the MGCGMM model corresponding to theGMM model.
- 3
- 3
- 3
- 3
- 3
- Stability and Hopf Bifurcation of a Time-Delayed SVIR Epidemic Model with Saturated Incidence Rates and Virus Mutation2
A time-delayed SVIR epidemic model incorporating saturated incidence rates and virus mutation incorporating saturated incidence rates and virus mutation is proposed and the effect of changes in saturation coefficients on disease transmission dynamics is investigated.
- Semi-Supervised Gastrointestinal Stromal Tumor Detection via Self-Training2
A semi-supervised gastrointestinal stromal tumor (GIST) detection method based on self-training using the new selection criterion to guarantee the quality of pseudo-labels and adding the pseudo-labeled data to the training set together with the labeled data after linear mixing is proposed.
- 2
- Cnnformer: Transformer-Based Semantic Information Enhancement Framework for Behavior Recognition2
Cnnformer is transformer-based semantic information enhancement model for behavior recognition that combines the convolution module and the attention module into the encoder module to simultaneously learn both local and global features, so as to enhance visual representation.
- An EEG abnormality detection algorithm based on graphic attention network2
The proposed series of EEG automatic analysis and anomaly detection algorithms based on GATs-LSTM shows great results on the benchmark datasets and a big potential for clinics as a support system with medical experts monitoring the patients.
- Complex Dynamic Analysis, Circuit Design and Simplified Predefined Time Synchronization for a Jerk Absolute Memristor Chaotic System2
In this parper, a 4D absolute memristor Jerk chaotic system is proposed, and a simplified predefined time synchronization scheme can not only reduce the controller inputs but also predefine the synchronization time.
- Enhanced three‐dimensional U‐Net with graph‐based refining for segmentation of gastrointestinal stromal tumours2
A GIST segmentation algorithm is proposed based on a convolutional neural network to fuse multi‐scale features and achieves better performance than that of the traditional U‐Net.
- Driver Attribute Filling for Genes in Interaction Network via Modularity Subspace-Based Concept Learning from Small Samples2
The model can overcome the curse of dimensionality due to small samples via dimension reduction in the task of attribute concept learning and explore the features of genes through modularity subspace beyond the network neighbours and shows a promising prospect in the application of interaction network analysis of tumorigenesis.
- The Application of Undergraduates' Deep Learning Strategy on Network2
By interviewing undergraduates with different professional backgrounds, this study will conduct deep observation from the perspective of the individual, to understand how undergraduates invoke learning strategies during network learning.
- 2
- 2
- 1
- Integration of single-cell and bulk RNA data to identify key cell types and biomarkers in viral myocarditis: An integrated bioinformatics analysis1
T cells are identified as key immune players in VMC, with CCL3 proposed as a novel biomarker for the condition and functional genomics analyses further substantiated their cardinal involvement in cardiotropic viral pathogenesis.
- Evolutionary Competition Multitasking Optimization with Online Resource Allocation for Endmemeber Extraction of Hyperspectral Images1
An evolutionary competition multitasking optimization method (CMTEE) is proposed to achieve endmember extraction and demonstrates the effectiveness of the proposed evolutionary competition multitasking optimization method for endmember extraction.
- 1
- QMC Sampling from Empirical Datasets1
It is found that when applying the proposed QMC sampling methods to datasets coming from a known distribution, they give similar performance as the standard QMC method directly sampling from this known distribution.
- Degree Evaluation of Facial Nerve Paralysis by Combining LBP and Gabor Features1
This work proposes a method of assessing the degree of facial paralysis considering static facial asymmetry and dynamic transformation factors, and uses a combination of static and dynamic quantification to generate facial palsy grading models to assess the extent of facial palsies.
- 1
- 1
- –
- –
- Concolic Testing of JavaScript using Sparkplug–
Evaluation on 160 Node.js libraries reveals comparable coverage and bug detection in significantly less time than the in-situ method, enhancing tracing with V8 Sparkplug baseline compiler and remill libraries for assembly to LLVM IR conversion.
- –
- –
- –
- –
- –
- –
- –
- –
- A Method of Experimental Design for GNSS-Dot Net under Jamming Attack–
A new attack detection algorithm that based on an improved angle of arrival (AOA) positioning mechanism to determine the point of disruption and interference correction is proposed and the attack detection and correction is very efficient, and interference location under ideal conditions is higher efficiency.
- –
- Mass-target image matching algorithm based on self-constructed multi-window–
An algorithm of mass-target image matching for vision measurement in mass chip production was put forward to carry out multi-window self-construction and results confirm that the assignment of recognizing mass chips is achieved by the algorithm.
- DIGITAL IMAGE DISORDER BASE ON A TWO-DEMENSIONS CHAOS MAP–
Because chaos map's specialty is first-rate randomicity, it is used in digital image disorder experiments of random space, and its security and complexity of arithmetic are analysed.
- –
- [A knowledge-based method for 3D segmentation and display of human brain].–
The 3D knowledge mobel is built using frame as the main knowledge expression method and the main structures in the brain are segmented and displayed by means of the "inelligent ray-tracing".
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 2026-10-15. 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.