Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks44 from public data
- 3D-Aided Deep Pose-Invariant Face Recognition83
A 3D-Aided Deep Pose-Invariant Face Recognition Model (3D-PIM), which automatically recovers realistic frontal faces from arbitrary poses through a 3D face model in a novel way, and demonstrates superiority of the proposed model over state-of-the-arts.
- 64
- 51
- 45
- 44
- 40
- RECAP: Towards Precise Radiology Report Generation via Dynamic Disease Progression Reasoning39
RECAP is proposed, which generates precise and accurate radiology reports via dynamic disease progression reasoning via dynamic progression reasoning, and combines the historical records, spatiotemporal information, and radiographs for report generation.
- 28
- 24
- 22
- Keyword-Aware Relative Spatio-Temporal Graph Networks for Video Question Answering19
A Keyword-aware Relative Spatio-Temporal graph network for VideoQA that employs an attention mechanism to assign high weights to keywords during question encoding and integrates the relative relation modeling to better capture the spatio-temporal dynamics among object nodes.
- 18
- Improved Particle Filter Algorithm for Multi-Target Detection and Tracking17
Experimental result shows that the proposed particle filter algorithm for multi-target detection and tracking can effectively improve the detection probability, and it has a lower root mean square error (RMSE) and a stronger adaptability to multi-target situation.
- 16
- 10
- MCPA: multi-scale cross perceptron attention network for 2D medical image segmentation9
This work proposes a 2D medical image segmentation model called multi-scale cross perceptron attention network (MCPA), and introduces a progressive dual-branch structure (PDBS) to address the semantic segmentation of the image involving finer tissue structures.
- 9
- 9
- KubFBS: A fine‐grained and balance‐aware scheduling system for deep learning tasks based on kubernetes8
A fine‐grained and balance‐aware scheduling model (FBSM) which considers the resource consumption characteristic of the DL task and is proposed to construct a scheduling system called KubFBS, which accelerates the execution of DL tasks while improving the load balancing capability of the cluster.
- 8
- SkatingVerse: A large‐scale benchmark for comprehensive evaluation on human action understanding7
SkatingVerse significantly helps the training and evaluation of HAU methods, the performance of existing HAU methods has much room to improve, and SkatingVerse helps to reduce such gaps, and unifying relevant tasks in HAU through a uniform dataset can facilitate more practical applications.
- 7
- 7
- 7
- PEVA-Net: Prompt-enhanced view aggregation network for zero/few-shot multi-view 3D shape recognition6
- An efficient sequential design of clinical trials6
The proposed design is robust to a wide range of priors, and achieves the specified power with a saving of sample size compared to existing adaptive designs.
- Self-Teaching Strategy for Learning to Recognize Novel Objects in Collaborative Robots5
A self-teaching strategy for a cobot to learn to recognize novel objects efficiently and effectively is proposed, like human-to-human teaching, where the user just provides a few examples of a novel object captured by an RGB-D camera.
- A Novel Spatial Clustering with Obstacles Constraints Based on Particle Swarm Optimization and K-Medoids4
A novel spatial clustering method based on PSO and K-Medoids, called PKSCOC, which aims to cluster spatial data with obstacles constraints is proposed, which performs better than the IKSCOC algorithm in terms of quantization error.
- Medical Dialogue Generation via Intuitive-then-Analytical Differential Diagnosis2
This work proposes a medical dialogue generation framework with the Intuitive-then-Analytic Differential Diagnosis (IADDx), which starts with a differential diagnosis via retrieval-based intuitive association and subsequently refines it through a graph-enhanced analytic procedure.
- 2
- Techniques and Methods of Spatial Data Fusion2
This article discusses vector data fusion from of data model fusion, semantic information fusion and coordinates unification, reviews the main methods of raster data fusion and discusses the key technologies of vector and rasterData fusion.
- Towards an Evidence-Based and Context-Aware Elderly Caring System Using Persuasive Engagement2
An evidencebased caring system which can inconspicuously and automatically monitor the health status of the elderly by continuously analyzing their real-life long-term living patterns deduced from activity recognition is proposed.
- Genetic Algorithm Based on Chaos Optimization2
A hybrid genetic algorithm is proposed based on chaos optimization that has global searching ability and fast convergence rate and the simulation results prove that the algorithm can give satisfied results to function optimization problems.
- EDB-YOLO: An enhanced multi-scale feature fusion model for steel surface defect detection1
The improved real-time detection model, EDB-YOLO, based on YOLO11 is proposed, which achieves an optimal trade-off between detection accuracy, computational cost, and efficiency, making it highly suitable for steel surface defect detection.
- A Study on Differentiable Logic and LLMs for EPIC-KITCHENS-100 Unsupervised Domain Adaptation Challenge for Action Recognition 20231
The innovative application of a differentiable logic loss in the training to leverage the co-occurrence relations between verb and noun, as well as the pre-trained Large Language Models to generate the logic rules for the adaptation to unseen action labels achieves the first place in terms of top-1 action recognition accuracy.
- 1
- A Method for 3D Building Individualization Integrating SAMPolyBuild and Multiple Spatial-Geometric Features–
A novel framework integrating SAMPolyBuild’s zero-shot capability with spatial-geometric feature refinement achieves high-precision 3D building individualization without pre-training, and provides a lightweight, efficient solution for large-scale urban modeling.
- –
- –
- –
- –
- –
- –
- Backtracking IC Placement Algorithm–
A new algorithm for integrated circuit (IC) layout placement is introduced that allows uphill movements but in a more restrictive manner; thus, the search for an optima is more directed.
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 2026-10-12. 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.