Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks51 from public data
- GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models474
GLM-4.5 is presented, an open-source Mixture-of-Experts (MoE) large language model with 355B total parameters and 32B activated parameters, featuring a hybrid reasoning method that supports both thinking and direct response modes that ranks 3rd overall among all evaluated models and 2nd on agentic benchmarks.
- MS-TCN++: Multi-Stage Temporal Convolutional Network for Action Segmentation350
A multi-stage architecture for the temporal action segmentation task that overcomes the limitations of the previous approaches and achieves state-of-the-art results on three datasets: 50Salads, Georgia Tech Egocentric Activities (GTEA), and the Breakfast dataset.
- Moving Object Segmentation in 3D LiDAR Data: A Learning-Based Approach Exploiting Sequential Data258
A novel approach is proposed that pushes the current state of the art in LiDAR-only moving object segmentation forward to provide relevant information for autonomous robots and other vehicles and compares to several other state-of-the-art methods showing superior segmentation quality in urban environments.
- MiniSeg: An Extremely Minimum Network for Efficient COVID-19 Segmentation166
MiniSeg, a lightweight deep learning model for efficient COVID-19 segmentation, has several significant strengths: i) it only has 83K parameters and is thus not easy to overfit; ii) it has high computational efficiency and is therefore convenient for practical deployment; and iii) it can be fast retrained by other users using their private CO VID-19 data for further improving performance.
- Multi-Scale Interaction for Real-Time LiDAR Data Segmentation on an Embedded Platform105
The proposed Multi-scale Interaction Network (MINet) uses multiple paths with different scales and balances the computational resources between the scales and outperforms point-based, image- based, and projection-based methods in terms of accuracy, number of parameters, and runtime.
- Pose Refinement Graph Convolutional Network for Skeleton-Based Action Recognition59
The network first refines the poses before they are further processed to recognize the action, which provides a much better trade-off between accuracy, memory footprint and processing time, which makes it suitable for robotics applications.
- DEL: Deep Embedding Learning for Efficient Image Segmentation53
A novel method called DEL (deep embedding learning) which can efficiently transform superpixels into image segmentation which can achieve comparable segments when compared with MCG but is much faster than it, i.e. 11.4fps vs. 0.07fps.
- 46
- 45
- TFNet: Exploiting Temporal Cues for Fast and Accurate LiDAR Semantic Segmentation41
TFNet is presented, a range-image-based LiDAR semantic segmentation method that utilizes temporal information to address the "many-to-one" problem and designs a max-voting-based post-processing technique to correct false predictions, particularly those caused by the "many-to-one" issue.
- CubemapSLAM: A Piecewise-Pinhole Monocular Fisheye SLAM System32
This work proposes a novel SLAM system with the cubemap model that utilizes the full FoV without introducing distortion from the fisheye lens, which greatly benefits the feature matching pipeline.
- Joint salient object detection and existence prediction29
This paper proposes a supervised learning approach for jointly addressing the salient object detection and existence prediction problems and adopts the structural SVM framework, which forms the two problems jointly in a single integrated objective function.
- 28
- 26
- A Visual Analysis Approach for Understanding Durability Test Data of Automotive Products26
A migration-adapted clustering algorithm that utilizes a segmentation strategy and a group of matching-updating operations to achieve an efficient and accurate clustering analysis of the data for starting mode identification and abnormal test detection and the results demonstrate the effectiveness of the approach and its possible inspiration for the durability test data analysis of other similar industrial products.
- Subjective and objective quality assessment of gastrointestinal endoscopy images: From manual operation to artificial intelligence18
A new artificial intelligence (AI)-based gastroscope image quality evaluator (GIQE) that leverages the newly proposed semi-full combination subspace to learn multiple kinds of human visual system (HVS) inspired features for providing objective quality scores.
- A multidimensional feature fusion network based on MGSE and TAAC for video-based human action recognition17
A multidimensional feature fusion network, called P-MTSC3D, a parallel network based on context modeling and temporal adaptive attention module, which has better overall performance than the state-of-the-art networks.
- 17
- Refinedbox: Refining for fewer and high-quality object proposals17
A computationally lightweight neural network is designed to reduce the number of proposals in object proposal generation, and can achieve state-of-the-art performance with a few proposals compared with some well-known proposal generation methods.
- Dual Pyramid Generative Adversarial Networks for Semantic Image Synthesis14
A Dual Pyramid Generative Adversarial Network (DP-GAN) is proposed that learns the conditioning of spatially-adaptive normalization blocks at all scales jointly, such that scale information is bi-directionally used, and it unifies supervision at different scales.
- Denoising of Joint Tracking Data by Kinect Sensors Using Clustered Gaussian Process Regression12
A joint standardization method is proposed, which translates the raw joint positions of different people into a standard coordinate, where the distance between each pair of adjacent joints is kept at a reference distance, and shows that the denoised Kinect measurements are more accurate than several benchmark methods.
- 11
- Exploring frame segmentation networks for temporal action localization11
A Frame Segmentation Network (FSN) is proposed that places a temporal CNN on top of the 2D spatial CNNs and can make dense predictions at frame-level for a video clip using both spatial and temporal context information.
- Automatic task scheduling optimization and collision-free path planning for multi-areas problem10
The results show that the presented approach could find a feasible collision-free task visit tour in various complex multi-tasks planning as well as demonstrate the proposed feasibility multi-task planning algorithm.
- 9
- 8
- Foresight Social-aware Reinforcement Learning for Robot Navigation7
A novel Foresight Social-aware Reinforcement Learning (FSRL) framework for mobile robots to achieve collision-free navigation that considers the current human-robot interaction to avoid an immediate collision, but also estimates upcoming social interactions to still keep distance in the future.
- The Methods and Experiments of Shape Measurement for Off-Axis Conic Aspheric Surface7
Three shape measurement methods of null test including auto-collimation, single computer-generated hologram (CGH), and hybrid compensation are presented in detail in this research and the correctness and effectiveness of these three measurement methods were confirmed.
- Multi-View Industrial Anomaly Detection with Epipolar Constrained Cross-View Fusion6
An epipolar guided multi-view anomaly detection framework that outperforms existing methods on the state-of-the-art multi-view anomaly detection dataset and proposes a pretraining strategy inspired by memory bank-based anomaly detection.
- 6
- Multi-scale gated network for efficient image super-resolution5
A novel lightweight multi-scale gated network (MSGN) is proposed by exploring the variant of the Transformer which is built upon its general structure and achieves the best performance among the state-of-the-art efficient image SR models while utilizing the least number of parameters and FLOPs.
- 5
- Projected-point-based Segmentation: A New Paradigm for LiDAR Point Cloud Segmentation4
This work proposes a new paradigm, namely projected-point-based methods, to transform point- based methods to a suitable form for LiDAR point cloud segmentation by utilizing the characteristics of LiDar point clouds.
- 2
- 1
- 1
- 1
- The role of construction of healthcare consortium on the allocation of human resources for primary care resources and its equity in China: A quantitative study1
The inequality of HR for PHC in China is low, however, the inequality between regions has not been eliminated and a long-term view is needed to monitor the impact of CHC on the allocation of HR for PHC and its equity in China.
- 1
- 1
- 1
- 1
- 1
- –
- –
- The role of Construction of Healthcare Consortium on the allocation of human resources for primary care resources and its equity in China–
The inequality of human resources for primary health care in China is low, however, the inequality between regions has not been eliminated and a long-term view is still needed to monitor the impact of CHC on the allocation of HR for PHC and its equity.
- –
- –
- –
- –
- –
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.