Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks148 from public data
- Nanofiber membrane supported lung-on-a-chip microdevice for anti-cancer drug testing240
A lung-on-a-chip with a poly(lactic-co-glycolic acid) electrospinning nanofiber membrane as the chip substrate and cell scaffold is developed and found that A549 cells could lead to endothelial cell apoptosis or death, and then the occurrence of tumor invasion.
- CounTR: Transformer-based Generalised Visual Counting151
This paper introduces a novel transformer-based architecture for generalised visual object counting, termed as Counting Transformer (CounTR), which explicitly capture the similarity between image patches or with given"exemplars" with the attention mechanism.
- 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.
- Multi-Scale Ship Detection Algorithm Based on YOLOv7 for Complex Scene SAR Images126
This paper suggests an SAS-FPN module that combines atrous spatial pyramid pooling and shuffle attention, allowing the model to focus on important information and ignore irrelevant information, reduce the feature loss of small ships, and simultaneously fuse the feature maps of ship targets on various SAR image scales, thereby improving detection accuracy and the model’s capacity to detect objects at several scales.
- Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentation73
A group ranking-based Out-of-Candidate Rectification (OCR) mechanism in a plug-and-play fashion that can achieve remarkable performance gains on both Pascal VOC and MS COCO datasets with negligible extra training overhead, which jus-tifies the effectiveness and generality of OCR.
- Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection67
A Ambiguity-Resistant Semi-supervised Learning (ARSL) for one-stage detectors is proposed that effectively mitigates the ambiguities and achieves state-of-the-art SSOD performance on MS COCO and PASCAL VOC.
- 50
- On-Line Pattern Matching on Similar Texts44
An attempt to close this gap via proposing two efficient algorithms for pattern matching on a set of similar texts, which requires time linear in the size of the texts' representation, for short patterns.
- 43
- 40
- Linear Span Network for Object Skeleton Detection40
A Linear Span Network (LSN) is proposed which introduces Linear Span Units (LSUs) to minimizes the reconstruction error and utilizes subspace linear span besides the feature linear span to increase the independence of convolutional features and the efficiency of feature integration, which enhances the capability of fitting complex ground-truth.
- Discretization-aware architecture search37
Discretization-aware architecture search is presented, with the core idea being adding a loss term to push the super-network towards the configuration of desired topology, so that the accuracy loss brought by discretization is largely alleviate.
- 35
- 30
- An efficient multi-scale channel attention network for person re-identification28
This work designed a novel cross-channel attention module (CCAM) in EMCA and placed it after different layers in the backbone and showed that the performance of the EMCA is consistently significantly superior to the existing state-of-the-art methods.
- 27
- 25
- 25
- 25
- 24
- Unsupervised underwater shipwreck detection in side-scan sonar images based on domain-adaptive techniques20
A domain collaborative bridging detector (DCBD) including intra-domain consistency constraint (IDCC) and domain collaborative bridging (DCB), is proposed, which addresses the conflict between feature transferability and discriminability in domain-adaptive object detection.
- UMOTMA: Underwater multiple object tracking with memory aggregation20
Experiments on the UMOT datasets and the underwater fish school datasets show that UMOTMA generally outperforms existing models and can maintain the stability of the target trajectory while ensuring high-quality detection.
- 18
- 18
- Error Concealment for Whole Frame Loss in HEVC18
By analysis of the texture features of video, motion vector extrapolation based on variable size coding blocks is proposed in this paper to recovery the lost frame fast and effectively.
- 17
- 16
- 15
- Identification of molecular characteristics in polycystic ovary syndrome using single-cell and transcriptome analysis14
This study, by analyzing multiple datasets, has revealed the complex molecular network of PCOS, offering new insights into understanding its pathophysiological basis, and weighted gene co-expression network analysis revealed 7 co-expression modules, with the bisque4 module showing the highest positive correlation with PCOS.
- 14
- LaPE: Layer-adaptive Position Embedding for Vision Transformers with Independent Layer Normalization14
- The Identification of Ship Trajectories Using Multi-Attribute Compression and Similarity Metrics14
A ship trajectory classification method based on multi-attribute trajectory similarity metrics which utilizes the following steps and can accurately cluster the ship trajectory groups and extract traffic distributions in key waters.
- Microfluidic Fabrication of Gelatin Acrylamide Microgels through Visible Light Photopolymerization for Cell Encapsulation14
GelA has potential for constructing scaffolds for bioapplications and can be an excellent substitute for GelMA, which was found to exhibit fast photopolymerization kinetics, better gelation, steady viscosity at elevated temperatures, and satisfying biocompatibility when compared to GelMA.
- MAP-Gen: An Automated 3D-Box Annotation Flow with Multimodal Attention Point Generator14
This work proposes a novel autolabeler, called multimodal attention point generator (MAP-Gen), that generates high-quality 3D labels from weak 2D boxes that leverages dense image information to tackle the sparsity issue of 3D point clouds, thus improving label quality.
- Efficient Genetic Modification of Cynomolgus Monkey Embryonic Stem Cells with Lentiviral Vectors14
It is demonstrated that the self-inactivating HIV-1-based lentiviral vectors constructed by MultiSite gateway technology are efficient tools for the transduction of cynomolgus monkey (Macaca fasicularis) ES (cmES) cells.
- 13
- Camera-LiDAR Cross-Modality Fusion Water Segmentation for Unmanned Surface Vehicles12
A novel camera-LiDAR cross-modality fusion water segmentation method, which combines the data characteristics of the 2D image and 3D LiDAR point cloud in water segmentsation for the first time and can significantly improve image-only-based methods.
- AD-YOLOv5s based UAV detection for low altitude security11
This work presents a novel approach, named AD-YOLOv5s, to achieve low altitude small UAV detection with high precision and high real-time performance, and proposes the method of lightweight design of model to improve the detection speed.
- 11
- 10
- 10
- 9
- 9
- 9
- 9
- 9
- 8
- 8
- 8
- 8
- 8
- 8
- 8
- Diverse receptive field network with context aggregation for fast object detection8
This work presents a context-exploited method that integrates features in different receptive fields to obtain contextual representation and proposes a one-stage diverse receptive field network (DRFNet), which achieves a good trade-off between speed and accuracy.
- 7
- 6
- A Cartilage Matrix Protein Regulates Collagen Synthesis in Mantle of Magallana gigas (Crassostrea gigas) under Ocean Acidification6
Results suggested that MgCMP1 was involved in regulating the expression of MgCollagen I and Mgcollagen X in the MF of the mantle in response to ocean acidification (OA).
- 6
- Quantum genetic algorithm for adaptive image multi-thresholding segmentation6
The proposed algorithm introduces a parallel quantum genetic algorithm PQGA for histogram-based image segmentation for adaptive multilevel thresholding segmentation problems by comparing with other methods for several test images.
- 5
- 5
- 5
- 5
- Multiscale attention-based detection of tiny targets in aerial beach images5
The feature pyramid network model based on multiscale attention is proposed to address the problem of tiny target detection in aerial beach images with large field-of-view, which forms the basis for the tiny target recognition and counting.
- 5
- Continuous Reservoir Simulation Model Updating and Forecasting Using a Markov Chain Monte Carlo Method5
This thesis suggests a way to quantify uncertainty for high dimensional problems by using the MCMC sampling process under the Bayesian frame, and reports a new approach in the use of the continuous MCMC method for automatic history matching.
- 5
- 4
- 4
- Instance Brownian Bridge as Texts for Open-vocabulary Video Instance Segmentation4
This work builds a frozen video segmentor to generate frame-level instance queries, and design Temporal Instance Resampler (TIR) to generate queries with temporal context from frame queries to link frame-level instance representations as a Brownian Bridge to model instance dynamics and align bridge-level instance representation to class texts.
- 4
- 4
- 4
- 3
- 3
- Changes in the Structure, Function, and Fat Content of the Heart in Patients with Obesity After Bariatric Surgery—A Prospective Magnetic Resonance Imaging Study3
After surgery, the cardiac structure and function of obese patients significantly improved, the PATV and M-PDFF decreased, and there was a correlation between the structure and function of the heart and several clinical and laboratory indicators.
- 3
- 3
- 3
- 3
- 3
- Optimized non-reciprocating legged gait for an eccentric paddle mechanism3
This work found that the locomotion performance of the mechanism can be further improved by keeping the supporting paddle vertical for a longer time of the supporting phase, and vertical parameter which denotes the time rate of vertical state to supporting phase is proposed for gait planning.
- 2
- 2
- LEDet: localization estimation detector with data augmentation for ship detection based on unmanned surface vehicle2
A one-stage localization estimation detector (LEDet) with ship-customized data augmentation that integrates the localization quality estimation into the classification branch as a soft label localization score and is applied to expand ship datasets without manual annotation.
- Detection on Satellite Navigation Deception Signals Based on Multi Platforms Cooperation2
A conical constraint condition of two platforms is established by using the advantage of multi platforms networking cooperation and the time difference measurement of the received signals, and the difference between the actual matrix and the reference one is contrasted to detect navigation deception signals.
- Sea surface object tracking for USV with spatio-temporal context fusion2
This paper proposed an object tracking algorithm with spatio-temporal context fusion that combines the image space context information of the multi-scale detection of deep network and the correlated filter tracking video time context information and is a real-time, accurate and robust object tracking.
- 2
- 2
- AviaryMOT: Aviary Attention-based adaptive multi-object tracking of cranes and storks in wetlands1
A novel multi-target tracking algorithm, AviaryMOT, is proposed, which utilizes a fusion technique that combines shallow and deep features to enhance tracking accuracy and effectiveness, and outperforms the state-of-art models.
- 1
- Infrared and Visible Image Fusion Based on Implicit Neural Representations1
Experimental results indicate that INRFuse outperforms existing methods in both subjective visual quality and objective evaluation metrics, producing fused images with clear structures, natural details, and rich information without the necessity for a training dataset.
- 1
- 1
- 1
- 1
- 1
- 1
- Vessel trajectory compression algorithm based on MapReduce1
The experimental results show that the MapReduce-based vessel trajectory compression algorithm can reduce the impact caused by data skew and significantly improve the compression efficiency of vessel trajectory data.
- 1
- 1
- Face tampering detection based on spatiotemporal attention residual network1
A face tampering detection method with spatiotemporal attention residual network designed to reduce the misuse of face data due to malicious dissemination, which can effectively detect whether the face data is tampered, and its detection accuracy is better than other methods.
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- LDMD with Temporally Adaptive Segmentation–
A localized DMD (LDMD) framework is proposed that improves prediction performance by integrating DMD's strong linear forecasting capabilities with time-domain segmentation techniques, and significantly enhances long-term predictive accuracy while preserving high computational efficiency.
- –
- –
- –
- –
- A real-time temperature prediction method based on CNN-LSTM with MODE in steelmaking process–
A Convolutional neural networks and long short-term memory networks model based on multi-objective differential evolution algorithm for the real-time prediction problem in the steelmaking process and outperform other artificial intelligence methods in multi-task prediction is proposed.
- –
- –
- Light field stitching using light field feature points–
Experimental results show that using LF feature points can effectively stitch 4D LFs, and preserve the spatial and angular consistency of the stitched LF compared with directly using the image stitching corresponding SAIs based on 2D feature points.
- Diverse Feature-Level Guidance Adjustments for Unsupervised Domain Adaptative Object Detection–
Diverse Feature-level Guidance Adjustments (DFGAs) are proposed for two-stage object detection frameworks, including Pixel-wise Multi-scale Alignment (PMA) and Adaptative Threshold Confidence Adjustment (ATCA), which adapts features within diverse hierarchical levels to capture sufficient contextual information.
- –
- –
- –
- –
- –
- –
- Adaptive mining algorithm of ship typical trajectory based on improved spectral clustering–
An improved spectral clustering algorithm for adaptive mining of ship typical trajectories and shows that typical trajectory of the ship is consistent with the facts, and the best parameters can be adaptively and accurately selected through the Calinski-Harabasz index.
- –
- –
- –
- –
- Attention mutual teaching network for unsupervised domain adaptation person re-identification–
An attention mutual teaching (AMT) network for unsupervised domain adaptation person ReID is proposed, which improves the performance of a model through iterative clustering and retraining and teaches two attention modules to teach each other to reduce clustering noise.
- –
- Soft labeling with quasi-Gaussian structure for training samples of deep classification trackers–
A soft labeling with quasi-Gaussian structure instead of the binary labeling, which distinguishes the samples belonging to different classes and the same class simultaneously is proposed, which achieves better classification and location performance.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- An Algorithm to Realize the Real-time Interpolation of Bezier Curves Based on DSP–
A method of uniform cutting Bezier curve is presented, so that the smooth running of the motor, effectively solve the frequent acceleration and deceleration, and avoid stepping motor slow speed response, and the problem of low frequency oscillation.
- –
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.