Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Pong Chi YuenSuggested from co-authorship
- Ping LiSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works83 from public data
- The Visual Object Tracking VOT2016 Challenge Results776
The Visual Object Tracking challenge VOT2016 goes beyond its predecessors by introducing a new semi-automatic ground truth bounding box annotation methodology and extending the evaluation system with the no-reset experiment.
- DilateFormer: Multi-Scale Dilated Transformer for Visual Recognition396
This work analyzes the patch interaction of global attention in ViTs and proposes Multi-Scale Dilated Attention (MSDA) to model local and sparse patch interaction within the sliding window, indicating the redundancy of global dependency modeling in shallow layers of ViTs.
- 217
- Dynamic Label Graph Matching for Unsupervised Video Re-identification195
A dynamic graph matching (DGM) method is proposed that iteratively updates the image graph and the label estimation process by learning a better feature space with intermediate estimated labels and is robust to noisy initial training data.
- 156
- 145
- DATA-GRU: Dual-Attention Time-Aware Gated Recurrent Unit for Irregular Multivariate Time Series142
A novel end-to-end Dual-Attention Time-Aware Gated Recurrent Unit (DATA-GRU) is proposed for IMTS to predict the mortality risk of patients and can significantly outperform state-of-the-art methods and provide meaningful clinical interpretation.
- 117
- Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning115
Self-supervised learning has shown great potentials in improving the video representation ability of deep neural networks by getting supervision from the data itself, but some of the current methods tend to cheat from the background, so this work proposes to remove the background impact by adding the background.
- 99
- Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis83
To generate more realistic texture details, a hybrid- granularity attention module is proposed to encode multi-scale fine-grained appearance features as bias terms to augment the coarse-grained prompt.
- Artificial intelligence in prediction of non‐alcoholic fatty liver disease and fibrosis71
The principles of applying AI on electronic health records, liver biopsy, and liver images are discussed and a few common AI approaches include logistic regression, decision tree, random forest, and XGBoost for data at a single time stamp.
- 62
- Machine learning model to predict recurrent ulcer bleeding in patients with history of idiopathic gastroduodenal ulcer bleeding60
Patients with a history of Helicobacter pylori–negative idiopathic bleeding ulcers have an increased risk of recurring ulcer complications.
- Semi-supervised Region Metric Learning for Person Re-identification56
A novel semi-supervised region metric learning method to improve person re-identification performance under imbalanced unlabeled data is proposed, which proposes to estimate positive neighbors by label propagation with cross person score distribution alignment.
- 52
- Learning domain-shared group-sparse representation for unsupervised domain adaptation47
A new criterion of domain-shared group sparsity that is an equivalent condition for conditional distribution alignment is proposed and developed, together with marginal distribution alignment, to develop a domain- Shared group-sparse dictionary learning model to learn domain- shared representations with aligned joint distributions.
- 40
- Invariant subspace learning for time series data based on dynamic time warping distance33
A novel subspace learning algorithm based on dynamic time warping (DTW) distance which is an elastic distance defined in a DTW space is developed which outperforms traditional subspacelearning algorithms and temporal transform-invariance based methods and obtains competitive results with the state-of-the-art algorithms, such as BOSS algorithm.
- 29
- Query Based Adaptive Re-ranking for Person Re-identification26
Experimental results show that the proposed query based adaptive re-ranking method can improve the ranking performance and outperforms other adaptive methods.
- 26
- Reduced Analytic Dependency Modeling: Robust Fusion for Visual Recognition25
A new framework to model dependency based on probabilistic properties of posteriors without any assumption on the data distribution is developed, and the Reduced Analytic Dependency Model (RADM) is proposed based on the convergent property of analytic function.
- Adversarial open set domain adaptation via progressive selection of transferable target samples22
A novel method namely Thresholded Domain Adversarial Network (ThDAN), which progressively selects transferable target samples for distribution alignment and outperforms state-of-the-art domain adaptation and open set recognition approaches on benchmarks.
- UA-CRNN: Uncertainty-Aware Convolutional Recurrent Neural Network for Mortality Risk Prediction22
A novel Uncertainty-Aware Convolutional Recurrent Neural Network (UA-CRNN) is proposed, which incorporates the uncertainty information in the generated data to improve the mortality risk prediction performance and significantly outperforms state-of-the-art methods in both short-term and long-term mortality risk predictions.
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.