Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- H. K. HuangSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works305 from public data
- 3,432
- 2,188
- Beyond Triplet Loss: A Deep Quadruplet Network for Person Re-identification1,231
A quadruplet deep network using a margin-based online hard negative mining is proposed based on the quadruplet loss for the person ReID, which can lead to the model output with a larger inter- class variation and a smaller intra-class variation compared to the triplet loss.
- The 2005 PASCAL Visual Object Classes Challenge742
This chapter provides details of the datasets, algorithms used by the teams, evaluation criteria, and results achieved in the PASCAL Visual Object Classes Challenge.
- TEA: Temporal Excitation and Aggregation for Action Recognition575
This paper proposes a Temporal Excitation and Aggregation block, including a motion excitation module and a multiple temporal aggregation module, specifically designed to capture both short- and long-range temporal evolution, and achieves impressive results at low FLOPs on several action recognition benchmarks.
- 558
- Local Features and Kernels for Classication of Texture and Object Categories: A Comprehensive Study531
A large-scale evaluation of an approach that represents images as distributions as distributions of features extracted from a sparse set of keypoint locations and learns a Support Vector Machine classier with kernels based on two effective measures for comparing distributions, the Earth Mover’s Distance and the 2 distance.
- Brief review of invariant texture analysis methods524
This paper considers invariant texture analysis, and approaches whose performances are not affected by translation, rotation, affine, and perspective transform are addressed.
- Standardized Assessment of Automatic Segmentation of White Matter Hyperintensities and Results of the WMH Segmentation Challenge333
There is a cluster of four methods that rank significantly better than the other methods, with one clear winner, and the inter-scanner robustness ranking shows that not all the methods generalize to unseen scanners.
- Video Understanding With Large Language Models: A Survey332
The emergent capabilities of Vid-LLMs are surprisingly advanced, particularly their ability for open-ended multi-granularity (abstract, temporal, and spatiotemporal) reasoning combined with common-sense knowledge, suggesting a promising path for future video understanding.
- 285
- Dataset Issues in Object Recognition261
Current datasets are lacking in several respects, and this paper discusses some of the lessons learned from existing efforts, as well as innovative ways to obtain very large and diverse annotated datasets.
- Fully convolutional network ensembles for white matter hyperintensities segmentation in MR images219
The effectiveness and generalization capability of the proposed system show its potential for real‐world clinical practice and are the highest achieved in the challenge, suggesting the proposed method is the state‐of‐the‐art.
- Not Just Privacy208
A noisy training method is proposed to enhance the cloud-side network robustness to perturbed data and can not only preserve privacy but also improve the inference performance.
- A Multi-Task Deep Network for Person Re-Identification198
This paper proposes a multi-task deep network (MTDnet) that makes use of their own advantages and jointly optimize the two tasks simultaneously for person ReID, and is the first to integrate both tasks in one network to solve the person re-identification problem.
- 180
- Discriminative Learning of Latent Features for Zero-Shot Recognition173
This work proposes an end-to-end network that is capable of automatically discovering discriminative regions by a zoom network and learning discrim inative semantic representations in an augmented space introduced for both user-defined and latent attributes.
- 152
- Local Features and Kernels for Classification of Texture and Object Categories: An In-Depth Study142
This paper presents a large-scale evaluation of an approach that represents images as distributions of features extracted from a sparse set of keypoint locations and learns a Support Vector Machine classifier with kernels based on two effective measures for comparing distributions, the Earth Mover's Distance and the chi-square distance.
- Tumor segmentation from magnetic resonance imaging by learning via one-class support vector machine142
A novel and user-friendly tumor segmentation method is proposed by exploring one-class support vector machine (SVM), which has the ability of learning the nonlinear distribution of the tumor data without using any prior knowledge.
- 141
- Human action segmentation and recognition via motion and shape analysis132
An automated video analysis system which addresses segmentation and detection of human actions in an indoor environment, such as a gym, and applies a novel approach for human action recognition by describing human actions using motion and shape features.
- 125
- Boundary-Aware Fully Convolutional Network for Brain Tumor Segmentation112
A novel, multi-task, fully convolutional network (FCN) architecture for automatic segmentation of brain tumor achieves improved segmentation performance by incorporating boundary information directly into the loss function.
- Feature Selection and Performance Evaluation of Support Vector Machine (SVM)-Based Classifier for Differentiating Benign and Malignant Pulmonary Nodules by Computed Tomography104
A method to find and select texture features of solitary pulmonary nodules (SPNs) detected by computed tomography (CT) and evaluate the performance of support vector machine (SVM)-based classifiers in differentiating benign from malignant SPNs.
- Few-Shot Intent Detection via Contrastive Pre-Training and Fine-Tuning103
This work conducts self-supervised contrastive pre-training on collected intent datasets and performs few-shot intent detection together with supervised contrastive learning, which explicitly pulls utterances from the same intent closer and pushes utterances across different intents farther.
- DiamondGAN: Unified Multi-modal Generative Adversarial Networks for MRI Sequences Synthesis102
This work proposes a novel, scalable and multi-modal approach called DiamondGAN, capable of performing exible non-aligned cross-modality synthesis and data infill, when given multiple modalities or any of their arbitrary subsets, learning structured information in an end-to-end fashion.
- Deep Bilinear Learning for RGB-D Action Recognition100
A new action feature called modality-temporal cube is presented in a tensor structure for characterizing RGB-D actions from a comprehensive perspective and the proposed method outperforms the state-of-the-art approaches.
- Discriminative Nearest Neighbor Few-Shot Intent Detection by Transferring Natural Language Inference99
This paper proposes to boost the discriminative ability by transferring a natural language inference (NLI) model, and achieves more stable and accurate in-domain and OOS detection accuracy than RoBERTa-based classifiers and embedding-based nearest neighbor approaches.
- An automated pattern recognition system for classifying indirect immunofluorescence images of HEp-2 cells and specimens87
The proposed systems for classifying immunofluorescence images of HEp-2 cells came first in the I3A contest associated with ICPR 2014, suggesting that the methods are state-of-the-art.
- 85
- Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning82
This paper proposes a Sparse Local Patch Transformer (SLPT) for learning the inherent relation between facial landmarks, which generates the representation of each single landmark from a local patch and aggregates them by an adaptive inherent relation based on the attention mechanism.
- 82
- Action categorization with modified hidden conditional random field82
Effective silhouette-based action features are extracted using motion moments and spectrum of chain code in a modified HCRF to have a guaranteed global optimum in the modelling of the temporal action dependencies after the HMM pathing stage.
- 80
- 78
- True Random Number Generators Using Electrical Noise76
This review discusses the different methods to harvest electrical noise in TRNGs, including the early amplify noise based on amplifier, phase jitter based on oscillator, the effect of electrical noise on the metastable behavior and amplify noisebased on chaos circuits.
- Feature Alignment and Uniformity for Test Time Adaptation74
This work addresses TTA as a feature revision problem due to the domain gap between source domains and target domains, and proposes a memorized spatial local clustering strategy to align the representations among the neighborhood samples for the upcoming batch.
- 70
- 70
- AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning58
This paper introduces \textbf{AgentOhana} as a comprehensive solution to address challenges faced by autonomous agents powered by large language models, and presents \textbf{xLAM-v0.1}, a large action model tailored for AI agents, which demonstrates exceptional performance across various benchmarks.
- Texture analysis- and support vector machine-assisted diffusional kurtosis imaging may allow in vivo gliomas grading and IDH-mutation status prediction: a preliminary study58
Findings demonstrate the superiority of DKI enhanced by texture analysis and SVM, compared to conventional imaging, for gliomas staging and prediction of IDH mutational status.
- 56
- Detect Faces Efficiently: A Survey and Evaluations54
A comprehensive comparison of several successful deep learning-based face detectors is conducted to uncover their efficiency using two metrics: FLOPs and latency and can guide to choose appropriate face detectors for different applications and also to develop more efficient and accurate detectors.
- 54
- 51
- Abnormality Detection in Chest X-Ray Images Using Uncertainty Prediction Autoencoders50
A new abnormality detection approach based on an autoencoder which outputs not only the reconstructed normal version of the input image but also a pixel-wise uncertainty prediction, which provides a natural measurement for abnormality Detection in images.
- 49
- 49
- 49
- Action categorization by structural probabilistic latent semantic analysis48
This work proposes a new approach structural pLSA (SpLSA) to model explicitly word orders by introducing latent variables, and develops an action categorization approach that learns action representations as the distribution of latent topics in an unsupervised way.
- 47
- Relevance feedback for real-world human action retrieval47
A video retrieval system that can be used to perform a content-based query on a large database of videos very efficiently and it is shown that by using ABRS-SVM, a technique for incorporating Relevance feedback on the search results, it is possible to quickly achieve useful results even when dealing with very complex human action queries, such as in Hollywood movies.
- Fully photonics-based physical random bit generator46
A fully photonics-based approach for ultrafast physical random bit generation that exploits a compact nonlinear loop mirror to sample the chaotic optical waveform in an all-optical domain and then generate random bit streams through further comparison with a threshold level is proposed.
- Real-time online photonic random number generation45
A real-time scheme for ultrafast random number extraction from a broadband photonic entropy source that eliminates the electronic jitter bottleneck confronted by currently available physical RN generators, and has no need for threshold tuning and post-processing is presented.
- 44
- 43
- Are Pre-trained Transformers Robust in Intent Classification? A Missing Ingredient in Evaluation of Out-of-Scope Intent Detection41
This work points out the importance of in-domain out-of-scope detection in few-shot intent recognition tasks and illustrates the vulnerability of pre-trained Transformer-based models against samples that are in- domain but out- of-scope (ID-OOS).
- High Dimensional Classification with Bayesian Neural Networks and Dirichlet Diffusion Trees41
The authors' winning entry in the NIPS 2003 challenge was a hybrid, in which the predictions for the five data sets were made using different methods of classification, or, for the Madelon data set, by averaging the predictions produced using two methods.
- 40
- Sign-Agnostic Implicit Learning of Surface Self-Similarities for Shape Modeling and Reconstruction from Raw Point Clouds40
With a global post-optimization of local sign flipping, SAIL-S3 is able to directly model raw, un-oriented point clouds and reconstruct high-quality object surfaces and Experiments show its superiority over existing methods.
- Mixed Supervised Object Detection with Robust Objectness Transfer40
This paper proposes a more reasonable and robust objectness transfer approach for MSD, which outperforms the existing MSD methods, and achieves state-of-the-art results on the challenging ILSVRC2013 detection dataset and the PASCAL VOC datasets.
- Efficient Video Stitching Based on Fast Structure Deformation40
Experimental results show that the proposed efficient and effective wide-view video stitching method outperforms the existing ones compared in terms of overall stitching quality and computational efficiency.
- Automatic Segmentation of Ground-Glass Opacities in Lung CT Images by Using Markov Random Field-Based Algorithms40
A new approach is presented which automatically segments GGO in lung computed tomography (CT) images using algorithms derived from Markov random field theory, and the acceptability and usefulness of AMAP-based GGO segmentation for assisting radiologists in detecting G GO in high-resolution CT diagnostic procedures are demonstrated.
- ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations39
This work proposes ReferDINO, a strong RVOS model that inherits region-level vision-language alignment from foundational visual grounding models, and is further endowed with pixellevel dense perception and cross-modal spatiotemporal reasoning.
- Age classification using Radon transform and entropy based scaling SVM39
This paper introduces entropy estimation to the scaling support vector machine classifier to enhance the quality of feature selection and demonstrates that the proposed algorithm leads to better recognition accuracy than the state of the art.
- Class attention to regions of lesion for imbalanced medical image recognition37
A simple yet effective framework, named CARE, to handle data imbalance issues by embedding attention into the training process of CNNs and helps CNNs attend to lesion regions of rare diseases, therefore helping CNNs to learn their characteristics more effectively.
- Deep kNN for Medical Image Classification36
An end-to-end learning strategy to unify the kNN classification and the feature extraction procedure and shows that the proposed deep kNN outperforms both kNN and other strong classifiers.
- 35
- External validation of ADO, DOSE, COTE and CODEX at predicting death in primary care patients with COPD using standard and machine learning approaches34
Performance of ADO and DOSE improved when combined with COTE comorbidities suggesting better models may be generated with additional data facilitated using novel approaches.
- Cross Contrasting Feature Perturbation for Domain Generalization33
Comprehensive experiments show that the proposed CCFP framework outperforms the previous state-of-the-art, and quantitative analyses illustrate that the approach can alleviate the domain shift problem in out-of-distribution (OOD) scenarios.
- 32
- 31
- 30
- Deep Learning-Based Security Verification for a Random Number Generator Using White Chaos30
Results show that the DL-based predictive model is expected to provide an efficient supplement for evaluating the security and quality of RNGs and demonstrates that the NRNG has the strong resistance against the predictive model.
- Imbalance-Aware Self-supervised Learning for 3D Radiomic Representations29
This work demonstrates how to learn image representations in a self-supervised fashion using a 3D Siamese network and deals with data imbalance by exploiting two unsupervised strategies: a) sample re-weighting, and b) balancing the composition of training batches.
- CARE: Class Attention to Regions of Lesion for Classification on Imbalanced Data29
Comprehensive experiments showed that paying attention to lesion regions of rare diseases during learning not only improved the classification performance on rare diseases, but also on the mean class accuracy.
- When SAM Meets Sonar Images25
The experimental results reveal a substantial enhancement in the performance of the fine-tuned SAM, increasing from 0.24 to 0.75 in mIoU, which underscores the promising potential of SAM for sonar image segmentation applications.
- 25
- 25
- 24
- Enriching Non-Autoregressive Transformer with Syntactic and Semantic Structures for Neural Machine Translation24
This paper proposes to incorporate the explicit syntactic and semantic structure of languages into a non-autoregressive Transformer, for the task of neural machine translation, and considers the intermediate latent alignment within target sentences to better learn the long-term token dependencies.
- Adversarial Convolutional Networks with Weak Domain-Transfer for Multi-sequence Cardiac MR Images Segmentation24
This work proposes an end-to-end segmentation framework based on convolutional neural network (CNN) and adversarial learning that outperforms baseline deep-learning methods on the public dataset released by the challenge organizer in MICCAI 2019.
- Web-based electronic patient records for collaborative medical applications24
A new approach to create and manage image-based EPR from actual patient records is given, and a novel method to use Web technology and DICOM standard to build an open architecture for collaborative medical applications is presented.
- Structural- and DTI- MRI enable automated prediction of IDH Mutation Status in CNS WHO Grade 2–4 glioma patients: a deep Radiomics Approach23
Investigating the diagnostic value of combined diffusion tensor imaging (DTI) and structural MRI enhanced by a deep radiomics approach based on convolutional neural networks (CNNs) and support vector machine (SVM) to determine the IDH mutation status in Central Nervous System World Health Organization grade 2–4 gliomas found imaging features derived from DTI-based FA and MD maps combined with structural MRI have superior diagnostic value.
- 23
- Multi-task Fully Convolutional Network for Brain Tumour Segmentation23
A novel, multi-task fully convolutional network (FCN) architecture is proposed for automatic segmentation of brain tumour that builds on the hierarchical relationship between tumour substructures with branch and leaf losses imposed and optimised simultaneously.
- 22
- Neurosurgical robots in China: State of the art and future prospect22
Several key skills in neurosurgical robots, such as medical imaging systems, automatic manipulator, lesion localization techniques, multimodal image fusion technology, registration method, and vascular imaging technology are focused on.
- Rethinking Alignment and Uniformity in Unsupervised Semantic Segmentation22
Experimental results on multiple semantic segmentation benchmarks show that the proposed Semantic Attention Network (SAN) framework specializes in catching semantic representations, which outperforms all the unpretrained and even several pretrained methods.
- 22
- WorldGenBench: A World-Knowledge-Integrated Benchmark for Reasoning-Driven Text-to-Image Generation20
A benchmark designed to systematically evaluate T2I models' world knowledge grounding and implicit inferential capabilities, covering both the humanities and nature domains is introduced, and a structured metric that measures how well generated images satisfy key semantic expectations is proposed.
- 20
- Deep Class-Specific Affinity-Guided Convolutional Network for Multimodal Unpaired Image Segmentation20
This paper designs class-specific affinity matrices to encode the knowledge of hierarchical feature reasoning, together with the shared convolutional layers to ensure the cross-modality generalization, and proposes an affinity-guided fully Convolutional network for multimodal image segmentation.
- Multimodal Egocentric Analysis of Focused Interactions20
An evaluation protocol is described, including framewise, extended framewis, and event-based measures, and empirical evidence that the fusion of visual face track scores with audio voice activity scores provides an effective combination is provided.
- Multiple Instance Cancer Detection by Boosting Regularised Trees20
A novel multiple instance learning algorithm for cancer detection in histopathology images that compared favourably with competing methods in experiments on breast cancer tissue microarray images and optical tomographic images of colorectal polyps.
- Earth observation satellite data receiving, processing system and data sharing20
The China Remote Sensing Satellite Ground Station plays an important role in land, ocean, and atmospheric resource investigation and environmental monitoring and has the capacity to receive data from 15 international and domestic Earth observation satellites.
- Bimodal biometric verification based on face and lips20
A novel approach to person verification by fusing face and lip features by considering two simple fusion strategies: data fusion before training and score fusion after training, working with two different face databases.
- Affine invariant classification and retrieval of texture images20
The algorithm discussed in this paper exploits the spectral signatures of texture images and based on spectral representation of affine transform, anisotropic scale invariant signatures of orientation spectrum distributions are extracted.
- MobileAIBench: Benchmarking LLMs and LMMs for On-Device Use Cases19
This work introduces MobileAIBench, a comprehensive benchmarking framework for evaluating mobile-optimized LLMs and LMMs, and provides insights into the performance and feasibility of deploying LLMs and LMMs on mobile platforms.
- Strip-MLP: Efficient Token Interaction for Vision MLP19
Strip-MLP significantly improves the performance of MLP-based models on small datasets and obtains comparable or even better results on ImageNet.
- Limited One-time Sampling Irregularity Map (LOTS-IM) for Automatic Unsupervised Assessment of White Matter Hyperintensities and Multiple Sclerosis Lesions in Structural Brain Magnetic Resonance Images19
LOTS-IM outperformed unsupervised method LST-LGA on WMH segmentation, both in performance and processing speed, thanks to the limited one-time sampling scheme and its implementation on GPU.
- 19
- 18
- 18
- Counterfeit Anomaly Using Generative Adversarial Network for Anomaly Detection18
This paper proposes a novel framework called adGAN for anomaly detection using GAN, which uses the fake data generated from GAN as an abnormal class, and then learns a boundary between normal data and simulated abnormal data, and is able to output the anomaly scores directly similar as one-class SVM (OCSVM), without any reconstruction process.
- 17
- 16
- 16
- A feature-matching method for side-scan sonar images based on nonlinear scale space16
A novel feature-matching method for side-scan sonar images that uses nonlinear diffusion filtering to build a nonlinear scale space and the modified feature descriptor reduces the dimensionality of the feature vector so that the computational expense is reduced.
- 16
- 15
- Generalisable Cardiac Structure Segmentation via Attentional and Stacked Image Adaptation14
It is shown that the domain shifts in heterogeneous cardiac imaging datasets can be drastically reduced by two aspects: 1) good-quality synthetic data by learning the underlying target domain distribution, and 2) stacked classical image processing techniques for data augmentation.
- Discriminating dysplasia: Optical tomographic texture analysis of colorectal polyps14
This paper investigates the ability of image analysis based on 3-D texture features to discriminate diagnostic levels of dysplastic change from such images, specifically, low-grade dysplasia, high-grade Dysplasia and invasive cancer.
- Using a Discrete Hidden Markov Model Kernel for lip-based biometric identification14
A novel and effective lip-based biometric identification approach with the Discrete Hidden Markov Model Kernel (DHMMK) is developed, and the performance of linear and RBF SVM is comparable under the frame work of DHMMK.
- People detection in low-resolution video with non-stationary background14
A framework for robust people detection in low resolution image sequences of highly cluttered dynamic scenes with non-stationary background is presented and it is shown that the model is more robust with better detection rate compared to the model of Viola et al.
- Areas of GeneralizedH-Polygons14
The main purpose of the paper is to give a Pick-type formula applicable to arbitrary H-polygons, that is, the set of vertices of a tiling of the plane by regular hexagons of unit area.
- Reduction of SEM charging artefacts in native cryogenic biological samples13
The use of interleaved scanning is demonstrated to reduce charging artefacts, allowing the observation of biological features that otherwise would be masked or perturbed and an alternative scanning method is proposed that could also be widely applicable to imaging any non-conductive.
- 13
- 13
- 13
- 13
- Gender classification via lips: static and dynamic features13
It is shown for the first time that important gender-specific information can be obtained from the way in which a person moves their lips during speech, and that the lip dynamics during speech provide greater gender discriminative information than simply lip appearance.
- 13
- Aggregation of Disentanglement: Reconsidering Domain Variations in Domain Generalization12
A novel paradigm called Domain Disentanglement Network (DDN) is proposed to disentangle the domain expert features from the source domain images and aggregate the sourcedomain expert features for representing the target test domain.
- TransVLAD: Focusing on Locally Aggregated Descriptors for Few-Shot Learning12
This paper is the first to prove self-supervised learning like masked autoencoders (MAE) can deal with the overfitting of transformers in few-shot image classification, and proposes two methods to mitigate few-shot biases, supervision bias and simple-characteristic bias.
- 12
- 11
- Modeling and representing events in multimedia11
An overview of the Joint Workshop on Modeling and Representing Events (JMRE) is presented, which is concerned with the understanding of events from multimedia, and with using events in order to better organize and consume multimedia.
- 10
- 9
- 9
- 9
- Content-based image retrieval in picture archiving and communication systems9
A CBIR system that is integrated with PACS and RIS, by using a user-supplied query image to retrieve similar images fromPACS and get corresponding reports from RIS, and employs ACR index for radiological diagnosis to reduce the search space and to provide meaningful results.
- 8
- 8
- 8
- 8
- EigenBody: Analysis of body shape for gender from noisy images8
The paper confirms that intuitive thoughts about what properties of the human body are important for gender classification, can be effectively represented in a small number of key components and that eigenpeople reproduced using just these key components can be visually classified by gender to a large extent.
- 8
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- Cross-DINO: Cross the Deep MLP and Transformer for Small Object Detection5
Extensive experimental results on COCO, WiderPerson, VisDrone, AI-TOD, and SODA-D datasets demonstrate that Cross-DINO efficiently improves the performance of DETR-like models on SOD.
- 5
- Open-Det: An Efficient Learning Framework for Open-Ended Detection5
Open-Det accelerates model training in both the bounding box and object name generation process by reconstructing the Object Detector and the Object Name Generator, and proposes a Vision-Language Aligner with V-to-L and L-to-V alignment mechanisms, enabling accurate object name generation for the LLM.
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- ToolLibGen: Scalable Automatic Tool Creation and Aggregation for LLM Reasoning4
Experimental results demonstrate that the proposed systematic approach to automatically refactor an unstructured collection of tools into a structured tool library significantly improves tool retrieval accuracy and overall reasoning performance across multiple reasoning tasks.
- 4
- Unsupervised Part Discovery via Dual Representation Alignment4
The proposed method achieves competitive performance and robustness due to its part-specific attention and can further serve as a series of reliable detectors in the testing phase, predicting pixel masks for part discovery.
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 3
- Adaptively Integrated Knowledge Distillation and Prediction Uncertainty for Continual Learning3
Two novel ways to adaptively balance model stability and plasticity are proposed, to adaptively integrate multiple levels of old knowledge and transfer it to each block level in the new model and to connect model prediction uncertainty and knowledge distillation for continual learning.
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- Learning from Partially Annotated OPT Images by Contextual Relevance Ranking3
A novel learning framework to reduce the requirement of manual annotations while achieving competitive classification performance is presented and the results show that the proposed method can robustly infer patterns from partially annotated images with low computational cost.
- 3
- 3
- 3
- 3
- 2
- 2
- GeoGNN: Quantifying and Mitigating Semantic Drift in Text-Attributed Graphs2
This work introduces a local PCA--based metric that measures the degree of semantic drift and provides the first quantitative framework to analyze how different aggregation mechanisms affect manifold structure, proposing Geodesic Aggregation, a manifold--aware mechanism that aggregates neighbor information along geodesics via log--exp mappings on the unit sphere.
- Personalized Multi-task Training for Recommender System2
This paper introduces a novel approach named PMTRec, the first personalized multi-task learning algorithm to obtain comprehensive user/item embeddings from various information sources, and demonstrates its effectiveness in achieving enhanced recommendation accuracy by leveraging multiple tasks simultaneously.
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- Data Separation of L1-minimization for Real-time Motion Detection2
A data separation algorithm with computationally efficient strategies to achieve real-time performance of sparse model based motion detection using the traditional pursuit algorithms as a pre-process step that converts the iterative optimization into linear addition and multiplication operations.
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- DS-Det: Single-Query Paradigm and Attention Disentangled Learning for Flexible Object Detection1
DS-Det is proposed, a more efficient detector capable of detecting a flexible number of objects in images and reformulate and introduce a new unified Single-Query paradigm for decoder modeling, transforming the fixed-query into flexible.
- Unravelling combustion chemistry of 2-pentene in pyrolysis, oxidation, and laminar flame propagation1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- Angle consistency for registration between catadioptric omni‐images and orthorectified aerial images1
- 1
- 1
- Poisson Kalman Particle Filtering for Tracking Centrosomes in Low-Light 3-D Confocal Image Sequences1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Learning Brain Tumor Representation in 3D High-Resolution MR Images via Interpretable State Space Models–
A novel state-space-model (SSM)-based masked autoencoder which scales ViT-like models to handle high-resolution data effectively while also enhancing the interpretability of learned representations and a latent-to-spatial mapping technique that enables direct visualization of how latent features correspond to specific regions in the input volumes in the context of SSM.
- –
- –
- –
- Semi-supervised Semantic Segmentation via Boosting Uncertainty on Unlabeled Data–
This work theoretically analyze and experimentally prove that appropriately boosting uncertainty on unlabeled data can help minimize the distribution gap, which benefits the generalization of the model.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Fusion of Motion and Appearance for Robust People Detection in Cluttered Scenes–
This work introduces a spatial pyramid Gaussian Mixture approach to model variations of long-term human motion information, which is computed via an improved background modeling using spatial motion constrains and people appearance is modeled by histograms of oriented gradients.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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 2026-10-16. 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.