Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
View as a treeStudents and postdocs3
- Meng LingyanFrom a thesis record ↗
- Zhou YichenFrom a thesis record ↗
- Connie Kou Khor LiFrom a thesis record ↗
Works28 from public data
- Rafiki81
Rafiki provides distributed hyper-parameter tuning for the training service, and online ensemble modeling for the inference service which trades off between latency and accuracy.
- Mugs: A Multi-Granular Self-Supervised Learning Framework73
This work proposes an effective MUlti-Granular Self-supervised learning (Mugs) framework to explicitly learn multi-granular visual features and surpasses SoTAs on other tasks, e.g. transfer learning, detection and segmentation.
- 30
- Multiple circular-harmonic-function correlation filter providing specified response to in-plane rotation23
A new method to combine multiple circular harmonics into a single filter that can provide the desired correlation response to in-plane rotation while minimizing the correlation-plane energy is presented.
- Pedestrian registration in static images with unconstrained background18
Experimental results show that the proposed method register pedestrian contours in complex backgrounds effectively, and is robust to image clutter.
- 14
- 14
- A compact network learning model for distribution regression11
This work designs a compact network representation that encodes and propagates functions in single nodes for the distribution regression task, and achieves higher prediction accuracies while using fewer parameters than traditional neural networks.
- 11
- Local Statistics for Generative Image Detection8
It is shown that the effectiveness of Bayer pattern and local statistics in distinguishing digital camera images from DM-generated images and that this approach is also robust to various perturbations such as image resizing and JPEG compression.
- 8
- 7
- 6
- 5
- The Localized Consistency Principle for Image Matching under Non-uniform Illumination Variation and Affine Distortion5
The idea is to do image matching through establishing an imaging function that describes the functional relationship relating intensity values between two images that is robust to illumination variation and affine distortion.
- Theoretical and experimental analysis on the generalizability of distribution regression network4
The theoretical properties ofDRN can be used to provide some explanation on the ability of DRN to achieve better generalization performance than conventional neural networks.
- Deep Co-Training for Cross-Modality Medical Image Segmentation3
This paper presents a novel method to tackle cross-modality medical image segmentation as semi-supervised multi-modal learning with image translation, which learns better feature representations and is more robust to source annotation scarcity.
- Distribution Regression Network.3
The Distribution Regression Network is introduced, which performs regression from input probability distributions to output probability distributions and generalizes the conventional multilayer perceptron (MLP).
- 3
- 2
- Predicting time-varying distributions with limited training data1
A new recurrent architecture for DRN is proposed, named recurrent distribution regression network (RDRN), and in experiments involving prediction on sequences of distributions, RDRN and DRN outperform neural network models, with RDRn achieving similar or better accuracies than DRN.
- An Efficient Network for Predicting Time-Varying Distributions.1
Compared to neural networks and DRN, RDRN achieves the best prediction performance while keeping the network compact, and the combination of compact distribution representation and shared weights architecture across time steps makes the time dependencies in a distribution sequence suitable.
- 1
- Real-time Mosaic for Multi-Camera Videoconferencing1
The main application for this system is videoconferencing for distance learning but it can be used for any high resolution broadcasting.
- –
- –
- –
- MACE-type correlation filter with controlled in-plane rotation response–
This work presents a method that combines three useful objectives: using multiple circular harmonics, controlling the correlation response to in-plane rotation and minimizing the correlation plane energy in order to achieve sharp correlation peaks.
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 2026-10-10. 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. You will be asked to sign in.