Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks84 from public data
- 209
- 90
- SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding89
SeeGround is introduced, a zero-shot 3DVG framework leveraging 2D Vision-Language Models (VLMs) trained on large-scale 2D data that outperforms existing zero-shot methods by large margins and exceeds weakly supervised methods and rival some fully supervised ones.
- 77
- Multiple local 3D CNNs for region-based prediction in smart cities69
A novel region-based information extraction mechanism and an end-to-end multiple spatial-temporal dependency learning structure are designed for local regions and the superior performance of the proposed method over the exisiting state-of-the-art methods is demonstrated.
- 37
- 35
- Robust information clustering incorporating spatial information for breast mass detection in digitized mammograms31
A robust information clustering (RIC) algorithm incorporating spatial information for breast mass detection in digitized mammograms based on the raw region of interest extracted from global mammogram by two steps of adaptive thresholding is investigated.
- Lignin degradation potential and draft genome sequence of Trametes trogii S030127
A nearly complete genome for T. trogii S0301 is presented, which will help elucidate the biosynthetic pathways of the lignin-degrading enzyme, advancing the discovery, characterization, and modification of novel enzymes from this genus.
- Learn to Optimize Denoising Scores for 3D Generation: A Unified and Improved Diffusion Prior on NeRF and 3D Gaussian Splatting22
A novel, unified framework that iteratively optimizes both the 3D model and the diffusion prior, which markedly surpasses existing techniques, establishing new state-of-the-art in the realm of text-to-3D generation.
- DGSLN: Differentiable graph structure learning neural network for robust graph representations22
This work proposes a novel differentiable graph structure learning neural network (DGSLN), which learns suitable graph structures for GNNs and develops a hybrid loss function to ensure the quality of learned graphs.
- Lipidomic Profiling of Lung Pleural Effusion Identifies Unique Metabotype for EGFR Mutants in Non-Small Cell Lung Cancer22
Novel lipid candidate markers in the non-cellular fraction of PE that holds potential to aid the diagnosis of benign, EGFR mutation positive and negative NSCLC are revealed.
- 21
- 21
- Learning Intra-View and Cross-View Geometric Knowledge for Stereo Matching18
This work proposes a novel Intra-view and Cross-view Geometric knowledge learning Network (ICGNet), specifically crafted to assimilate both intra-view and cross-view geo-metric knowledge.
- Semi-Supervised Self-Taught Deep Learning for Finger Bones Segmentation18
This study focuses on segmenting finger bones within a newly introduced semi-supervised self-taught deep learning framework which consists of a student network and a stand-alone teacher module.
- A New Cluster Validity for Data Clustering15
The results of comparative study show that the proposed VB index has high ability in producing a good cluster number estimate and in addition, it provides a new approach for cluster validity from the view of statistical learning theory.
- Deep learning based CETSA feature prediction cross multiple cell lines with latent space representation13
This study aims to predict CETSA features in various cell lines by introducing a computational framework called CycleDNN based on deep neural network technology, and confirms the validity of the predicted MS-CETSA data from the proposed CycleDNN through validation in protein–protein interaction prediction.
- 13
- 13
- 13
- 12
- How Do Images Align and Complement LiDAR? Towards a Harmonized Multi-modal 3D Panoptic Segmentation11
This work proposes Image-Assists-LiDAR (IAL), a novel multi-modal 3D panoptic segmentation framework that achieves state-of-the-art performance compared to previous multi-modal 3D panoptic segmentation methods on two widely used benchmarks.
- An information-theoretic fuzzy C-spherical shells clustering algorithm11
The proposed information fuzzy C-spherical shells (IFCSS) algorithm tackles the intertwined robust fuzzy clustering problems of outlier detection, prototype initialization and cluster validity in a unified framework of information clustering.
- 10
- Graph Neural Networks for Protein-Protein Interactions -- A Short Survey9
This paper reviews various graph-based methodologies, and discusses their applications in PPI prediction, and classifies these approaches into two primary groups based on their model structures.
- 8
- 8
- 8
- Kernel online learning algorithm with state feedbacks7
This paper presents a novel recurrent kernel algorithm for online learning that introduces a propagation scheme to recycle the kernel state information and an adaptive training method is proposed to tune the kernel weight and recurrent weight simultaneously followed by detailed analysis of the weight convergence.
- 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.
- On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning6
An effective and realistic attack method is proposed that better produces poisoned samples without access to benign samples, and an effective in-distribution attack objective is derived, and two TTA-aware attack objectives are designed.
- 6
- 6
- 6
- A Modified Deterministic Annealing Algorithm for Robust Image Segmentation6
A modified deterministic annealing algorithm, which is called DA-RS, for robust image segmentation, which possesses enhancing robustness and segmentation ability due to the injection of a robust non-Euclidean distance measure, obtained through a nonlinear mapping by using Gaussian radial basis function (GRBF).
- 5
- Adaptive B-Snake model using shape and appearance information for object segmentation5
It turns out that the proposed adaptive B‐Spline model can attain more accurate object segmentation and is compared with the traditional Snake and ASM models.
- 4
- Training Binary Neural Networks via Gaussian Variational Inference and Low-Rank Semidefinite Programming4
This paper proposes an optimization framework for BNN training based on Gaussian variational inference that allows us to go beyond latent weights to formulate and solve low-rank semidefinite programming (SDP) relaxations that explicitly model and learn pairwise correlations between weights during training, resulting in improved accuracy.
- DM3D: Distortion-Minimized Weight Pruning for Lossless 3D Object Detection4
This paper proposes a novel post-training weight pruning scheme for 3D object detection that is orthogonal to all existing point cloud sparsifying methods, and introduces a lightweight scheme to efficiently acquire Hessian information, and subsequently perform dynamic programming to solve the layer-wise sparsity.
- Zero-Shot 3D Visual Grounding from Vision-Language Models3
SeeGround is presented, a zero-shot 3DVG framework that leverages 2D Vision-Language Models (VLMs) to bypass the need for 3D-specific training and achieves substantial improvements over existing zero-shot baselines, demonstrating strong generalization under challenging conditions.
- Exploring Human-in-the-Loop Test-Time Adaptation by Synergizing Active Learning and Model Selection3
This work first select samples for human annotation and then use the labeled data to select optimal hyper-parameters (model selection) and can always prevent choosing the worst hyper-parameters on all off-the-shelf TTA methods.
- The Survey of CNN-based Cancer Diagnosis System3
This thesis summarizes the structure and image processing methods of miniature robot from the perspectives of miniature diagnostic robot, CSF (CNN-SVM-FCN and expert systems, and analyzes the advantages and disadvantages of each method, and elaborates their respective implementation processes and system framework.
- 2
- 2
- 2
- 2
- Robust Data Clustering in Mercer Kernel-Induced Feature Space2
A robust pruning method, the maximization of the mutual information against the constrained input data points, is performed to phase out noise and outliers in the robust kernel-based deterministic annealing algorithm for data clustering in mercer kernel-induced feature space.
- 2
- Clustering Spherical Shells by a Mini-Max Information Algorithm2
A novel cluster validity criteria is estimated to determine an optimal cluster number of spherical shells for a given set of data and the effectiveness of MMI algorithm for clustering spherical shells is demonstrated by experimental results.
- A Simple and Efficient Baseline for Video Action Recognition1
A simple and very efficient 3D convolutional neural network for video action recognition that beats the previous state-of-the-art accuracy achieved with 2-stream methods by more than 5% using only RGB input.
- MPTN: A video-based multi-point tracking network for atrioventricular junction detection and tracking in cardiovascular magnetic resonance imaging1
This work provides an initial framework for cardiac motion tracking and function evaluation, which may support future advances in diagnosis of heart diseases and may support future advances in diagnosis of heart diseases.
- 1
- Utilizing the Mean Teacher with Supcontrast Loss for Wafer Pattern Recognition1
This work introduces an innovative approach that integrates the Mean Teacher framework with the supervised contrastive learning loss for enhanced wafer map pattern recognition and addresses data imbalance in the wafer dataset by employing SMOTE and under-sampling techniques.
- Improving Adversarial Robustness for 3D Point Cloud Recognition at Test-Time through Purified Self-Training1
The proposed test-time purified self-training strategy is complementary to purification based method in handling continually changing adversarial attacks on the testing data stream and Adaptive thresholding and feature distribution alignment are introduced to improve the robustness of self-training.
- 1
- 1
- 1
- 1
- 1
- Mammographic Mass Detection by Robust Learning Algorithms1
A number of methods were proposed for the detection of spiculated masses because of their high likelihood of malignancy, and Gaussian smoothing and subsampling operations as preprocessing steps in mass detection.
- A novel pruning approach for robust data clustering1
A novel pruning method is proposed to phase out noisy points for robust data clustering, and this approach identifies and prunes the noisy points based on the maximization of mutual information against input data distributions such that the resulting clusters are least affected by noise and outliers.
- Image Segmentation by Deterministic Annealing Algorithm with Adaptive Spatial Constraints1
An adaptive spatially-constrained deterministic annealing (ASDA) algorithm, which takes into account the spatial continuity constraints by using a dissimilarity index that allows spatial interactions between image pixels, for image segmentation.
- 1
- –
- –
- –
- OccLE: Label-Efficient 3D Semantic Occupancy Prediction–
OccLE is proposed, a Label-Efficient 3D Semantic Occupancy Prediction that takes images and LiDAR as inputs and maintains high performance with limited voxel annotations and achieves competitive performance with only 10\% of voxel annotations on the SemanticKITTI and Occ3D-nuScenes datasets.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar; position from the scholar’s ORCID record, 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.