Author name cluster

Hong Qin

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

15 papers

1 author row

EAAI Journal 2026 Journal Article

Autoencoder: An efficient inverse design method for gallium nitride high electron mobility transistor structures

Yan Pang
Meilan Hao
Shu Wei
Lina Yu
Jufeng Han
Min Wu
Hong Qin
Weijun Li

Autoencoders are artificial neural networks widely used for feature extraction and data reconstruction, and can also be leveraged for device and material structure design. In gallium nitride (GaN) high electron mobility transistor (HEMT) inverse design, the mapping from target radio-frequency (RF) metrics to geometric parameters is often non-unique, meaning that multiple distinct structures can achieve similar performance. This one-to-many nature makes deterministic inverse regression unstable. Motivated by this challenge, this paper presents an autoencoder-based inverse design approach for GaN HEMT structures that learns the relationship between device geometry and two key RF metrics: cut-off frequency ( f T ) and maximum oscillation frequency ( f max ). The proposed method enables efficient generation of candidate GaN HEMT designs that match specified RF targets, using technology computer-aided design (TCAD) simulations to generate and label the training data. The model predicts four structural parameters, including gate–source spacing, gate length, gate field-plate length, and passivation-layer thickness. Experimental results show that the proposed framework can reliably generate structures consistent with the target specifications. The average relative error is 2. 64% for f T and 2. 67% for f max. Compared with direct inverse regression baselines, the autoencoder-based framework exhibits more stable training behavior and alleviates slow convergence or training failures caused by the non-uniqueness of the inverse mapping. In our implementation, the method can generate a candidate structure for a given RF target within a few milliseconds (ms), substantially reducing computational cost and providing an effective route to accelerate GaN HEMT device design.

Details DOI

JAAMAS Journal 2026 Journal Article

Behavioral Self-Organization in Lifelike Synthetic Agents

Jiming Liu
Hong Qin

Abstract Modern computer graphics technology has enjoyed rapid development in recent years, attracting researchers and practitioners to explore a wide spectrum of applications ranging from computer-aided graphical design to artificial life and virtual reality. This paper is concerned with the animation-based entertainment use of computer graphics, i. e. , to create digitally synthetic agents that can self-animate themselves, adapt to their virtual environments, and learn new behaviors to attain some specific goals. Here we propose a synthetic agent computational architecture called inter-threaded motif-based behavioral self-organization architecture, in which one motif acquires a conditioned association from the presently sensed state of the environment to the requirement of a desired motion as well as a plausible behavioral pattern to enable such a motion, whereas another computes the optimal parameters for the identified behavior in fulfilling the motion requirement. This architecture will enable animated behaviors to be automatically programmed based on the concurrent self-organization of individual motifs as well as their crisscrossing interactions.

Details DOI

AAAI Conference 2026 Conference Paper

Implicit Neural Representation with Multi-Scale Sine Activation

Jufeng Han
Shu Wei
Min Wu
Lina Yu
Weijun Li
Linjun Sun
Hong Qin
Yan Pang

Implicit Neural Representations (INRs) have become a powerful paradigm for modeling continuous signals in computer vision, graphics, and scientific computing. However, multilayer perceptrons (MLPs) generally suffer from severe spectral bias, which limits their ability to accurately model high-frequency details and multi-scale structures. To address this challenge, we propose a novel Multi-Scale Sine Activation (MSA), which explicitly introduces multi-scale frequency responses by incorporating multiple sets of sine activations with logarithmically spaced frequencies in parallel at each layer. MSA is further combined with an amplitude modulation mechanism to ensure numerical stability and robust optimization across different frequency channels. We conduct extensive experiments on a series of challenging tasks, including 1D multi-scale function fitting, image representation, video representation, 3D shape representation, and PDEs solving. Experimental results show that MSA outperforms existing state-of-the-art methods in terms of reconstruction accuracy, detail preservation, and training stability.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Details Enhancement in Unsigned Distance Field Learning for High-fidelity 3D Surface Reconstruction

Cheng Xu
Fei Hou
Wencheng Wang
Hong Qin
Zhebin Zhang
Ying He

While Signed Distance Fields (SDF) are well-established for modeling watertight surfaces, Unsigned Distance Fields (UDF) broaden the scope to include open surfaces and models with complex inner structures. Despite their flexibility, UDFs encounter significant challenges in high-fidelity 3D reconstruction, such as non-differentiability at the zero level set, difficulty in achieving the exact zero value, numerous local minima, vanishing gradients, and oscillating gradient directions near the zero level set. To address these challenges, we propose Details Enhanced UDF (DEUDF) learning that integrates normal alignment and the SIREN network for capturing fine geometric details, adaptively weighted Eikonal constraints to address vanishing gradients near the target surface, unconditioned MLP-based UDF representation to relax non-negativity constraints, and DCUDF for extracting the local minimal average distance surface. These strategies collectively stabilize the learning process from unoriented point clouds and enhance the accuracy of UDFs. Our computational results demonstrate that DEUDF outperforms existing UDF learning methods in both accuracy and the quality of reconstructed surfaces.

PDF Details DOI

TMLR Journal 2025 Journal Article

LBMamba: Locally Bi-directional Mamba

Jingwei Zhang
Xi Han
Hong Qin
Mahdi S. Hosseini
Dimitris Samaras

Mamba, a State Space Model (SSM) that accelerates training by recasting recurrence as a parallel selective scan, has recently emerged as a linearly-scaling, efficient alternative to self-attention. Because of its unidirectional nature, each state in Mamba only has information of its previous states and is blind to states after. Current Mamba-based computer-vision methods typically overcome this limitation by augmenting Mamba's global forward scan with a global backward scan, forming a bi-directional scan that restores a full receptive field. However, this operation doubles the computational load, eroding much of the efficiency advantage that originally Mamba have. To eliminate this extra scans, we introduce LBMamba, a locally bi-directional SSM block that embeds a lightweight locally backward scan inside the forward selective scan and executes it entirely in per-thread registers. Building on LBMamba, we present LBVim, a scalable vision backbone that alternates scan directions every two layers to recover a global receptive field without extra backward sweeps. We validate the versatility of our approach on both natural images and whole slide images (WSIs). We show that our LBVim constantly offers a superior performance–throughput trade-off. That is under the same throughput, LBVim achieves 0.8% to 1.6% higher top-1 accuracy on the ImageNet-1K classification dataset, 0.6% to 2.7% higher mIoU on the ADE20K semantic segmentation dataset, 0.9% higher AP$^b$ and 1.1% higher AP$^m$ on the COCO detection dataset. Our method serves as a general-purpose enhancement, boosting the accuracy of four SOTA Mamba models, namely VMamba, LocalVim, PlainMamba and Adventurer, by 0.5% to 3.4%. We also integrate LBMamba into the SOTA pathology multiple instance learning (MIL) approach, MambaMIL, which uses single directional scan. Experiments on 3 public WSI classification datasets show that our method achieves a relative improvement of up to 3.06% better AUC, 3.39% better F1, 1.67% better accuracy. Our code is available at https://github.com/cvlab-stonybrook/LBMamba.

PDF Details

NeurIPS Conference 2025 Conference Paper

MIND: Material Interface Generation from UDFs for Non-Manifold Surface Reconstruction

Xuhui Chen
Fei Hou
Wencheng Wang
Hong Qin
Ying He

Unsigned distance fields (UDFs) are widely used in 3D deep learning due to their ability to represent shapes with arbitrary topology. While prior work has largely focused on learning UDFs from point clouds or multi-view images, extracting meshes from UDFs remains challenging, as the learned fields rarely attain exact zero distances. A common workaround is to reconstruct signed distance fields (SDFs) locally from UDFs to enable surface extraction via Marching Cubes. However, this often introduces topological artifacts such as holes or spurious components. Moreover, local SDFs are inherently incapable of representing non-manifold geometry, leading to complete failure in such cases. To address this gap, we propose MIND ($\mathrm{\underline{M}aterial}$ $\mathrm{\underline{I}nterface}$ $\mathrm{from}$ $\mathrm{\underline{N}on}$-$\mathrm{manifold}$ $\mathrm{\underline{D}istance}$ $\mathrm{fields}$), a novel algorithm for generating material interfaces directly from UDFs, enabling non-manifold mesh extraction from a global perspective. The core of our method lies in deriving a meaningful spatial partitioning from the UDF, where the target surface emerges as the interface between distinct regions. We begin by computing a two-signed local field to distinguish the two sides of manifold patches, and then extend this to a multi-labeled global field capable of separating all sides of a non-manifold structure. By combining this multi-labeled field with the input UDF, we construct material interfaces that support non-manifold mesh extraction via a multi-labeled Marching Cubes algorithm. Extensive experiments on UDFs generated from diverse data sources, including point cloud reconstruction, multi-view reconstruction, and medial axis transforms, demonstrate that our approach robustly handles complex non-manifold surfaces and significantly outperforms existing methods. The source code is available at https: //github. com/jjjkkyz/MIND.

PDF Details

NeurIPS Conference 2024 Conference Paper

From Transparent to Opaque: Rethinking Neural Implicit Surfaces with $\alpha$-NeuS

Haoran Zhang
Junkai Deng
Xuhui Chen
Fei Hou
Wencheng Wang
Hong Qin
Chen Qian
Ying He

Traditional 3D shape reconstruction techniques from multi-view images, such as structure from motion and multi-view stereo, face challenges in reconstructing transparent objects. Recent advances in neural radiance fields and its variants primarily address opaque or transparent objects, encountering difficulties to reconstruct both transparent and opaque objects simultaneously. This paper introduces $\alpha$-NeuS$\textemdash$an extension of NeuS$\textemdash$that proves NeuS is unbiased for materials from fully transparent to fully opaque. We find that transparent and opaque surfaces align with the non-negative local minima and the zero iso-surface, respectively, in the learned distance field of NeuS. Traditional iso-surfacing extraction algorithms, such as marching cubes, which rely on fixed iso-values, are ill-suited for such data. We develop a method to extract the transparent and opaque surface simultaneously based on DCUDF. To validate our approach, we construct a benchmark that includes both real-world and synthetic scenes, demonstrating its practical utility and effectiveness. Our data and code are publicly available at https: //github. com/728388808/alpha-NeuS.

PDF Details DOI

JBHI Journal 2022 Journal Article

Automatic Dental Plaque Segmentation Based on Local-to-Global Features Fused Self-Attention Network

Shuai Li
Yuting Guo
Zhennan Pang
Wenfeng Song
Aimin Hao
Bin Xia
Hong Qin

The accurate detection of dental plaque at an early stage will definitely prevent periodontal diseases and dental caries. However, it remains difficult for the current dental examination to accurately recognize dental plaque without using medical dyeing reagent due to the low contrast between dental plaque and healthy teeth. To combat this problem, this paper proposes a novel network enhanced by a self-attention module for intelligent dental plaque segmentation. The key motivation is to directly utilize oral endoscope images (bypassing the need for dyeing reagent) and get accurate pixel-level dental plaque segmentation results. The algorithm needs to conduct self-attention at the super-pixel level and fuse the super-pixels’ local-to-global features. Our newly-designed network architecture will afford the simultaneous fusion of multiple-scale complementary information guided by the powerful deep learning paradigm. The critical fused information includes the statistical distribution of the plaques color, the heat kernel signature (HKS) based local-to-global structure relationship, and the circle-LBP based local texture pattern in the nearby regions centering around the plaque area. To further refine the fuzed multiple-scale features, we devise an attention module based on CNN, which could focalize the regions of interest in plaque more easily, especially for many challenging cases. Extensive experiments and comprehensive evaluations confirm that, for a small-scale training dataset, our method could outperform the state-of-the-art methods. Meanwhile, the user studies verify the claim that our method is more accurate than conventional dental practice conducted by experienced dentists.

Details DOI

NeurIPS Conference 2021 Conference Paper

Knowledge-inspired 3D Scene Graph Prediction in Point Cloud

Shoulong Zhang
Shuai Li
Aimin Hao
Hong Qin

Prior knowledge integration helps identify semantic entities and their relationships in a graphical representation, however, its meaningful abstraction and intervention remain elusive. This paper advocates a knowledge-inspired 3D scene graph prediction method solely based on point clouds. At the mathematical modeling level, we formulate the task as two sub-problems: knowledge learning and scene graph prediction with learned prior knowledge. Unlike conventional methods that learn knowledge embedding and regular patterns from encoded visual information, we propose to suppress the misunderstandings caused by appearance similarities and other perceptual confusion. At the network design level, we devise a graph auto-encoder to automatically extract class-dependent representations and topological patterns from the one-hot class labels and their intrinsic graphical structures, so that the prior knowledge can avoid perceptual errors and noises. We further devise a scene graph prediction model to predict credible relationship triplets by incorporating the related prototype knowledge with perceptual information. Comprehensive experiments confirm that, our method can successfully learn representative knowledge embedding, and the obtained prior knowledge can effectively enhance the accuracy of relationship predictions. Our thorough evaluations indicate the new method can achieve the state-of-the-art performance compared with other scene graph prediction methods.

PDF Details

AAAI Conference 2021 Conference Paper

Point Cloud Semantic Scene Completion from RGB-D Images

Shoulong Zhang
Shuai Li
Aimin Hao
Hong Qin

In this paper, we devise a novel semantic completion network, called point cloud semantic scene completion network (PCSSC-Net), for indoor scenes solely based on point clouds. Existing point cloud completion networks still suffer from their inability of fully recovering complex structures and contents from global geometric descriptions neglecting semantic hints. To extract and infer comprehensive information from partial input, we design a patch-based contextual encoder to hierarchically learn point-level, patch-level, and scene-level geometric and contextual semantic information with a divideand-conquer strategy. Consider that the scene semantics afford a high-level clue of constituting geometry for an indoor scene environment, we articulate a semantics-guided completion decoder where semantics could help cluster isolated points in the latent space and infer complicated scene geometry. Given the fact that real-world scans tend to be incomplete as ground truth, we choose to synthesize scene dataset with RGB-D images and annotate complete point clouds as ground truth for the supervised training purpose. Extensive experiments validate that our new method achieves the stateof-the-art performance, in contrast with the current methods applied to our dataset.

PDF Details

JBHI Journal 2021 Journal Article

Structure Correction for Robust Volume Segmentation in Presence of Tumors

Pranjal Sahu
Yiyuan Zhao
Parmeet Bhatia
Luca Bogoni
Anna Jerebko
Hong Qin

CNN based lung segmentation models in absence of diverse training dataset fail to segment lung volumes in presence of severe pathologies such as large masses, scars, and tumors. To rectify this problem, we propose a multi-stage algorithm for lung volume segmentation from CT scans. The algorithm uses a 3D CNN in the first stage to obtain a coarse segmentation of the left and right lungs. In the second stage, shape correction is performed on the segmentation mask using a 3D structure correction CNN. A novel data augmentation strategy is adopted to train a 3D CNN which helps in incorporating global shape prior. Finally, the shape corrected segmentation mask is up-sampled and refined using a parallel flood-fill operation. The proposed multi-stage algorithm is robust in the presence of large nodules/tumors and does not require labeled segmentation masks for entire pathological lung volume for training. Through extensive experiments conducted on publicly available datasets such as NSCLC, LUNA, and LOLA11 we demonstrate that the proposed approach improves the recall of large juxtapleural tumor voxels by at least 15% over state-of-the-art models without sacrificing segmentation accuracy in case of normal lungs. The proposed method also meets the requirement of CAD software by performing segmentation within 5 seconds which is significantly faster than present methods.

Details DOI

JBHI Journal 2019 Journal Article

A Lightweight Multi-Section CNN for Lung Nodule Classification and Malignancy Estimation

Pranjal Sahu
Dantong Yu
Mallesham Dasari
Fei Hou
Hong Qin

The size and shape of a nodule are the essential indicators of malignancy in lung cancer diagnosis. However, effectively capturing the nodule's structural information from CT scans in a computer-aided system is a challenging task. Unlike previous models that proposed computationally intensive deep ensemble models or three-dimensional CNN models, we propose a lightweight, multiple view sampling based multi-section CNN architecture. The model obtains a nodule's cross sections from multiple view angles and encodes the nodule's volumetric information into a compact representation by aggregating information from its different cross sections via a view pooling layer. The compact feature is subsequently used for the task of nodule classification. The method does not require the nodule's spatial annotation and works directly on the cross sections generated from volume enclosing the nodule. We evaluated the proposed method on lung image database consortium (LIDC) and image database resource initiative (IDRI) dataset. It achieved the state-of-the-art performance with a mean 93. 18% classification accuracy. The architecture could also be used to select the representative cross sections determining the nodule's malignancy that facilitates in the interpretation of results. Because of being lightweight, the model could be ported to mobile devices, which brings the power of artificial intelligence (AI) driven application directly into the practitioner's hand.

Details DOI

JBHI Journal 2019 Journal Article

Multitask Cascade Convolution Neural Networks for Automatic Thyroid Nodule Detection and Recognition

Wenfeng Song
Shuai Li
Ji Liu
Hong Qin
Bo Zhang
Shuyang Zhang
Aimin Hao

Thyroid ultrasonography is a widely used clinical technique for nodule diagnosis in thyroid regions. However, it remains difficult to detect and recognize the nodules due to low contrast, high noise, and diverse appearance of nodules. In today's clinical practice, senior doctors could pinpoint nodules by analyzing global context features, local geometry structure, and intensity changes, which would require rich clinical experience accumulated from hundreds and thousands of nodule case studies. To alleviate doctors’ tremendous labor in the diagnosis procedure, we advocate a machine learning approach to the detection and recognition tasks in this paper. In particular, we develop a multitask cascade convolution neural network (MC-CNN) framework to exploit the context information of thyroid nodules. It may be noted that our framework is built upon a large number of clinically confirmed thyroid ultrasound images with accurate and detailed ground truth labels. Other key advantages of our framework result from a multitask cascade architecture, two stages of carefully designed deep convolution networks in order to detect and recognize thyroid nodules in a pyramidal fashion, and capturing various intrinsic features in a global-to-local way. Within our framework, the potential regions of interest after initial detection are further fed to the spatial pyramid augmented CNNs to embed multiscale discriminative information for fine-grained thyroid recognition. Experimental results on 4309 clinical ultrasound images have indicated that our MC-CNN is accurate and effective for both thyroid nodules detection and recognition. For the correct diagnosis rate of malignant and benign thyroid nodules, its mean Average Precision (mAP) performance can achieve up to $\text{98. 2}\%$ accuracy, which outperforms the common CNNs by $\text{5}\%$ on average. In addition, we conduct rigorous user studies to confirm that our MC-CNN outperforms experienced doctors, yet only consuming roughly $\text{2}\%$ ( $1/48$ ) of doctors’ examination time on average. Therefore, the accuracy and efficiency of our new method exhibit its great potential in clinical applications.

Details DOI

JBHI Journal 2016 Journal Article

Robust Optimization-Based Coronary Artery Labeling From X-Ray Angiograms

Xinglong Liu
Fei Hou
Hong Qin
Aimin Hao

In this paper, we present an efficient robust labeling method for coronary arteries from X-ray angiograms based on energy optimization. The fundamental goal of this research is to facilitate the analysis and diagnosis of interventional surgery in the most efficient way, and such effort could also improve the performance during doctor training, and surgery simulation and planning. Compared to the prior state-of-the-art, our method is much more robust to resist noises and is tolerant to even incomplete data because of the “ built-in ” nature of global optimization. We start with a fully parallelized algorithm based on Hessian matrix to extract the tubular structure from the X-ray angiograms as vessel candidates. Then, instead of using the candidates directly, we use the grow cut (Vezhnevets and V. Konouchine, Growcut: Interactive multi-label N-D image segmentation by cellular automata, in Proc. of Graphicon, 2005, pp. 150–156.) method, which is similar to graph cut (Boykov et al. , Fast approximate energy minimization via graph cuts, IEEE Trans. Pattern Anal. Mach. Intell. , vol. 23, no. 11, pp. 1222–1239, Nov. 2001.)but with better performance to extract the precise vessel structure from the images. Next, we use the fast marching method with second derivatives and cross neighbors to extract the accurate skeleton segments. After that, we propose an efficient method based on iterative closest point (Z. Zhang, Iterative point matching for registration of free-form curves and surfaces, Int J. Comput. Vis. , vol. 13, no. 2, pp. 119–152, 1994.) to organize the skeleton segments by treating the continuity and similarity as extra constraints. Finally, we formulate the vessel labeling problem as an energy optimization problem and solve it using belief propagation. We also demonstrate several typical applications including flow velocity estimation, heart beat estimation, and vessel diameter estimation to show its practical uses in clinical diagnosis and treatment. Our experiments exhibit the correctness and robustness, as well as the high performance of our algorithm. We envision that our system would be of high utility for diagnosis and therapy to treat vessel-related diseases in a clinical setting in the near future.

Details DOI

AAAI Conference 2016 Conference Paper

Structure Aware L1 Graph for Data Clustering

Shuchu Han
Hong Qin

In graph-oriented machine learning research, L1 graph is an ef- ﬁcient way to represent the connections of input data samples. Its construction algorithm is based on a numerical optimization motivated by Compressive Sensing theory. As a result, It is a nonparametric method which is highly demanded. However, the information of data such as geometry structure and density distribution are ignored. In this paper, we propose a Structure Aware (SA) L1 graph to improve the data clustering performance by capturing the manifold structure of input data. We use a local dictionary for each datum while calculating its sparse coefﬁcients. SA-L1 graph not only preserves the locality of data but also captures the geometry structure of data. The experimental results show that our new algorithm has better clustering performance than L1 graph.

PDF Details