Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks106 from public data
- Source-Free Domain Adaptation for Semantic Segmentation340
A source-free domain adaptation framework for semantic segmentation, namely SFDA, in which only a well-trained source model and an unlabeled target domain dataset are available for adaptation, which enables to recover and preserve the source domain knowledge from the source model via knowledge transfer during model adaptation.
- Multi-Scale Adaptive Graph Neural Network for Multivariate Time Series Forecasting243
A multi-scale adaptive graph neural network (MAGNN) is introduced to jointly model intra-variable dependencies and inter- variable dependencies, and a scale-wise fusion module is developed to effectively promote the collaboration across different time scales, and automatically capture the importance of contributed temporal patterns.
- 226
- 200
- Automated insect identification through concatenated histograms of local appearance features: feature vector generation and region detection for deformable objects145
A computer vision approach to automated rapid-throughput taxonomic identification of stonefly larvae by evaluating this classification methodology on a task of discriminating among four stonefly taxa, two of which, Calineuria and Doroneuria, are difficult even for experts to discriminate.
- Unsupervised Person Image Generation With Semantic Parsing Transformation128
This paper proposes a new pathway to decompose the hard mapping into two more accessible subtasks, namely, semantic parsing transformation and appearance generation, and proposes a semantic generative network to transform between semantic parsing maps, in order to simplify the non-rigid deformation learning.
- Box-Aware Feature Enhancement for Single Object Tracking on Point Clouds125
This work proposes the BoxCloud, an informative and robust representation, to depict an object using the point-to-box relation, and designs an efficient box-aware feature fusion module, which leverages the aforementioned BoxCloud for reliable feature matching and embedding.
- Semi-DETR: Semi-Supervised Object Detection with Detection Transformers87
This work proposes a Stage-wise Hybrid Matching strategy that combines the one-to-many assignment and one- to-one assignment strategies to improve the training efficiency of the first stage and thus provide high-quality pseudo labels for the training of the second stage.
- Optimized prostate biopsy via a statistical atlas of cancer spatial distribution80
A statistical predictive model was developed to optimize the needle biopsy sites, by maximizing the probability of detecting cancer, in a statistical atlas of spatial distribution of prostate cancer from a large patient cohort.
- 75
- Analyzing the robotic behavior in a smart city with deep enforcement and imitation learning using IoRT58
This research focuses on developing a robotic behavior control using the Internet of Robotic Things (IoRT) using deep learning for a Smart City and uses two main paradigms: Deep Reinforcement Learning (DRL) and Imitation Learning (IL).
- 54
- G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitation50
This paper proposes a novel semantic-guided feature imitation technique, which automatically performs soft matching between feature pairs across all pyramid levels to provide the optimal guidance to the student and introduces contrastive distillation to effectively capture the information encoded in the relationship between different feature regions.
- A fractional diffusion-wave equation with non-local regularization for image denoising47
A novel fractional diffusion-wave equation with non-local regularization for noise removal using the fractional time derivative interpolates between the heat diffusion equation and the wave equation, which leads to a mixed behavior of diffusion and wave propagation and thus it can preserve edges in a highly oscillatory region.
- JITL based MWGPR soft sensor for multi-mode process with dual-updating strategy40
A multi-mode moving-window Gaussian process regression (MWGPR) based approach for ARX modeling is proposed to effectively capture process nonlinearity or switching dynamics.
- 33
- 33
- Robust Feature Matching Method for SAR and Optical Images by Using Gaussian-Gamma-Shaped Bi-Windows-Based Descriptor and Geometric Constraint32
The experimental results demonstrate that the proposed method provides significant improvements in the number of correct matches and matching precision compared with the state-of-the-art SIFT-like methods.
- 32
- Light field super-resolution using complementary-view feature attention19
A residual complementary-view spatial and channel attention module (RCSCAM) is designed to effectively interact with complementary information between complementary views and has a more advanced reconstruction performance that displays faithful details with higher SR accuracy than state-of-the-art methods.
- The generative adversarial networks and its application in machine vision19
The basic principles and existing problems of GAN are described, then several improved GAN models, including Info, DC-GAN, f-gan, Cat-GAN and others are introduced.
- I2R-NUS-MSRA at TAC 2011: Entity Linking.18
The joint participation of I2R-NUS team and MSRA team in entity linking task for Knowledge Base Population at Text Analysis Conference 2011 is reported.
- Visualization deep learning model for automatic arrhythmias classification17
The proposed 1D Resnet-GRU method can effectively select and integrate ECG features to achieve the goal of end-to-end arrhythmia classification by using 12-lead ECG signals, which can serve a promising and useful way for automatic arrhythmias classification, and can provide an explainable deep leaning model for clinical diagnosis.
- Application of Feature Engineering for Phishing Detection12
A novel anti-phishing framework that employs feature engineering including feature selection and feature extraction based on genetic algorithm (GA) to divide features into critical features and non-critical features and considers utilizing their projection in the process of classification, which is dification from literatures.
- 12
- Improving Relation Extraction with Relational Paraphrase Sentences11
This work proposes a novel model to learn the information of diverse relation expressions via enriching diverse expressions by relational paraphrase sentences via a joint learning framework and shows that this approach is effective to improve the performance on relation extraction, even compared with a strong baseline.
- Minimum sensitivity based robust beamforming with eigenspace decomposition10
An enhanced eigenspace-based beamformer (ESB) derived using the minimum sensitivity criterion is proposed with significantly improved robustness against steering vector errors.
- DFT-extractor10
This study demonstrates a novel system called DFT-Extractor, which automatically constructs domain-specific faceted taxonomies from Wikipedia in three steps: it crawls domain terms from Wikipedia by using a modified topical crawler, and exploits a classification model to extract hyponym relations with the use of motif-based features.
- 9
- 8
- 8
- 7
- 7
- 6
- 6
- 6
- 5
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- Light Field Image Super-Resolution via Global-View Information Adaption and Angular Attention Fusion1
- 1
- ISTA-Inspired Network for Image Super-Resolution1
Experimental results show the proposed ISTA-inspired restoration network (ISTAR) achieves competitive or better performances than other optimization-inspired works with fewer parameters and lower computation complexity.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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 2026-10-16. 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.