Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks42 from public data
- Phase-Shifting Coder: Predicting Accurate Orientation in Oriented Object Detection184
A novel differentiable angle coder named phase-shifting coder is proposed to accurately predict the orientation of objects, along with a dual-frequency version (PSCD) to provide a unified framework for various periodic fuzzy problems caused by rotational symmetry in oriented object detection.
- Survey of access control models and technologies for cloud computing88
This paper surveys access control models and policies in different application scenarios, especially for cloud computing, by following the development of the internet as the main line and by examining different network environments and user requirements.
- STAR: A First-Ever Dataset and a Large-Scale Benchmark for Scene Graph Generation in Large-Size Satellite Imagery86
This paper constructs a large-scale dataset for SGG in large-size VHR SAI with image sizes ranging from 512 × 768 to 27 860 × 31 096 pixels, named STAR, encompassing over 210K objects and over 400K triplets.
- PointOBB: Learning Oriented Object Detection via Single Point Supervision64
PointOBB is proposed, the first single Point-based OBB generation method, for oriented object detection, and achieves promising performance, and significantly outperforms potential point-supervised baselines.
- 36
- Improved 1D-CNNs for behavior recognition using wearable sensor network36
A human behavior recognition method based on improved One-Dimensional Convolutional Neural Networks (1D-CNNs) and a sample autonomous learning method, which aims to find the optimal sample training set and avoid over-fitting problems in traditional CNNs are proposed.
- Point2RBox-v2: Rethinking Point-supervised Oriented Object Detection with Spatial Layout Among Instances27
The Point2RBox-v2 is the first approach to explore the spatial layout among instances for learning point-supervised OOD from point annotations and is expected to give a competitive performance especially in densely packed scenes.
- 26
- Wholly-WOOD: Wholly Leveraging Diversified-Quality Labels for Weakly-Supervised Oriented Object Detection22
Wholly-WOOD is developed, a weakly-supervised OOD framework, capable of wholly leveraging various labeling forms (Points, HBoxes, RBoxes, and their combination) in a unified fashion, and achieves performance very close to that of the RBox-trained counterpart on remote sensing and other areas.
- PointOBB-v3: Expanding Performance Boundaries of Single Point-Supervised Oriented Object Detection20
This paper proposes PointOBB-v3, a stronger single point-supervised OOD framework that generates pseudo rotated boxes without additional priors and incorporates support for the end-to-end paradigm and introduces an Instance-Aware Weighting strategy to focus on high-quality predictions.
- Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing19
Theoretically, it is proved that DRS guarantees a tight ${\ell_2}$ certified robustness radius for the original input and revealed that DRS attains a superior upper bound on the ${\ell_2}$ robustness radius, which decreases proportionally at a rate of $(1/\sqrt m + 1/\sqrt n )$ with $m+n=d).
- 19
- High-quality defocusing phase-shifting profilometry on dynamic objects16
An efficient motion-compensated defocusing phase-shifting profilometry, which accurately estimates the motion-induced shifts regarding each pixel, both on the image plane and the phase map, to reduce the artifacts occurring in the dynamic scenes, is proposed.
- Few-data guided learning upon end-to-end point cloud network for 3D face recognition14
An end-to-end deep learning network entitled Sur3dNet-Face for point-cloud-based 3D face recognition is proposed, which uses PointNet, which is a successful point cloud classification solution but performs unexpectedly in face recognition, as the backbone.
- 13
- 13
- Temporal Unlearnable Examples: Preventing Personal Video Data from Unauthorized Exploitation by Object Tracking11
A novel generative framework for generating Temporal Unlearnable Examples (TUEs) is proposed that achieves state-of-the-art performance in video dataprivacy protection, with strong transferability across VOT models, datasets, and temporal matching tasks.
- Theoretical Insights in Model Inversion Robustness and Conditional Entropy Maximization for Collaborative Inference Systems10
This work theoretically proves that the conditional entropy of inputs given intermediate features provides a guaranteed lower bound on the reconstruction mean square error (MSE) under any MIA, and derives a differentiable and solvable measure for bounding this conditional entropy based on the Gaussian mixture estimation and proposes a conditional entropy maximization (CEM) algorithm to enhance the inversion robustness.
- 10
- 9
- 9
- VGPCNet: viewport group point clouds network for 3D shape recognition8
A Viewport Group Point Cloud Network for 3D Shape Recognition (VGPCNet) in which features are grouped according to viewports instead of local neighbor points to model the long-range global context and a novel attention-based feature aggregation module is proposed.
- YOLOv3_Slim for Face Mask Recognition8
Y OLOv3_Slim is more accurate than YOLOv4 in face mask recognition based on the data set and ECA module is added to the network.
- 8
- 8
- A new method for identity authentication using mobile terminals8
This paper proposes a technique in which IMEI (International Mobile Equipment Identity) is used to apply the backstage hidden automatic identification authentication mode for the user, which has good user experience and can enhance the practicability of identity authentication.
- 4
- Defocused projection model for phase-shifting profilometry with a large depth range4
A new defocus-induced error related to the shape of the measured object is pinpointed and a novel defocused projection model is established to cope with such a error to improve the accuracy of defocusing phase-shifting profilometry.
- 3
- 2
- Face recognition on 3D point clouds2
A novel 3D face recognition network (FPCNet) is proposed using modified PointNet++ and a 3D augmentation technique to enhance the learned features more discriminative and synthesize more identity-variance and expression- Variance 3D faces from limited data.
- An Improved GAFSA Based on Chaos Search and Modified Simplex Method2
This paper combines the dynamically adjusting parameters, the chaos search (CS), and the modified simplex method (MS) with GAFSA, and the CS_MS_GAFSA is proposed which improves in optimizing accuracy and convergence speed.
- An Automatic Landmark Localization Method for 2D and 3D Face2
An automatically and accurately facial landmark localization algorithm based on Active Shape Model (ASM) and Gabor Wavelets Transformation (GWT) which can be applied to both 2D and 3D facial data is proposed.
- 1
- 1
- 1
- –
- –
- Research on the Difficulty Points Marking System of Online Learning Process–
This work model the learning behavior of online learners based on facial expression information and mouse track data, and proposes a method for marking learner’s difficulties in online learning process based on machine learning.
- –
- –
- On the Computational Study of Artificial Fish Swarm Algorithm and its Improvement–
The computational results on 34 Benchmark functions show that MS_GAFSA does improve in optimizing accuracy and convergence speed, and combined with GAFSA and Modified Simplex, the algorithm can improve the convergence speed and precision of optimization.
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 2026-10-11. 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.