Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks101 from public data
- 428
- Unsupervised Person Re-Identification by Soft Multilabel Learning421
The reference agent learning to represent each reference person by a reference agent in a joint embedding is introduced and the unified deep model outperforms the state-of-the-art unsupervised RE-ID methods by clear margins.
- Dynamic Refinement Network for Oriented and Densely Packed Object Detection410
A dynamic refinement network that consists of two novel components, i.e., a feature selection module (FSM) and a dynamic refinement head (DRH) that enables neurons to adjust receptive fields in accordance with the shapes and orientations of target objects, which empowers the model to refine the prediction dynamically in an object-aware manner.
- Asymmetric Co-Teaching for Unsupervised Cross-Domain Person Re-Identification172
An asymmetric co-teaching framework, which resists noisy labels by cooperating two models to select data with possibly clean labels for each other, which can consistently benefit most clustering based methods, and boost the state-of-the-art adaptation accuracy.
- Toward an Expert Level of Lung Cancer Detection and Classification Using a Deep Convolutional Neural Network166
The three-dimensional convolutional neural network described in this article demonstrated both high sensitivity and high specificity in classifying pulmonary nodules regardless of diameters as well as superiority compared with manual assessment.
- Transformer-based Dual Relation Graph for Multi-label Image Recognition120
This paper proposes a novel Transformer-based Dual Relation learning framework, constructing complementary relationships by exploring two aspects of correlation, i.e., structural relation graph and semantic relation graph, which aims to capture long-range correlations from object context by developing a cross-scale transformer-based architecture.
- Viewpoint-Aware Loss with Angular Regularization for Person Re-Identification106
This work proposes a novel approach to viewpoint-aware adaptive label smoothing regularization (VALSR) that assigns the adaptive soft label to feature representation and demonstrates that it outperforms the state-of-the-art supervised Re-ID methods.
- 103
- Application of Gradient Boosting Machine Learning Algorithms to Predict Uniaxial Compressive Strength of Soft Sedimentary Rocks at Thar Coalfield99
The XGBoost algorithm was shown to be the most accurate algorithm among all the investigated four algorithms for UCS prediction of soft sedimentary rocks of the Block-IX at Thar Coalfield, Pakistan.
- 95
- Enhancing Unsupervised Video Representation Learning by Decoupling the Scene and the Motion73
This work proposes to decouple the scene and the motion (DSM) with two simple operations, so that the model attention towards the motion information is better paid and the impact of the scene is weakened while the temporal sensitivity of the network is further enhanced.
- Adversarial Attribute-Image Person Re-identification65
This work conducted extensive experiments on three attribute datasets and demonstrated that the regularized adversarial modelling is so far the most effective method for the attribute-image cross-modality person Re-ID problem.
- Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians63
A novel deep network termed Pedestrian-Interference Suppression Network (PISNet) is presented, which leverages a Query-Guided Attention Block (QGAB) to enhance the feature of the target in the gallery, under the guidance of the query.
- Semi-Supervised Adversarial Monocular Depth Estimation61
This paper proposes a semi-supervised adversarial learning framework that only utilizes a small number of image-depth pairs in conjunction with a large number of easily-available monocular images to achieve high performance.
- 57
- 3D convolutional neural network for differentiating pre-invasive lesions from invasive adenocarcinomas appearing as ground-glass nodules with diameters ≤3 cm using HRCT57
An automatic classification framework based on a 3D convolutional neural network to distinguish different types of lung cancer using computed tomography (CT) data is developed and is a promising tool for the diagnosis and treatment choice decision.
- Automatic script identification in the wild57
A large-scale dataset with a great quantity of natural images and 10 types of widely-used languages is constructed and a deep learning based algorithm is proposed for script identification at word or line levels in natural scenes.
- NOH-NMS51
This work proposes \heatmapname (\heatmapnameshort ), which pinpoints the objects nearby each proposal with a Gaussian distribution, together with \nmsname, which dynamically eases the suppression for the space that might contain other objects with a high likelihood.
- Machine Learning-Based Intelligent Prediction of Elastic Modulus of Rocks at Thar Coalfield49
Using an ML-based intelligent approach, this study was able to provide alternative elucidations for predicting E with appropriate accuracy and run time at Thar coalfield, Pakistan.
- Transfer Deep Reinforcement Learning-Enabled Energy Management Strategy for Hybrid Tracked Vehicle49
An adaptive energy management strategy for hybrid electric vehicles by combining deep reinforcement learning (DRL) and transfer learning (TL) and the founded DRL and TL-enabled control policy is capable of enhancing energy efficiency and improving system performance.
- Towards convolutional neural networks compression via global error reconstruction47
A global error reconstruction method termed GER is presented, which firstly leverages an SVD-based low-rank approximation to coarsely compress the parameters in the fully connected layers in a layerwise manner, and jointly optimized in a global perspective via back-propagation.
- MEMS reservoir computing system with stiffness modulation for multi-scene data processing at the edge37
This work presents a novel MEMS RC with stiffness modulation, offering a simplified, efficient approach to integrate sensing and computing, and initiated edge computing, enabling emergent applications in MEMS for local computations.
- A review on control factors of pyrolysis technology for plants containing heavy metals36
Current literatures that emphasize the influencing factors on the metal content in the biochar, liquid and gaseous phases, as well as the potential risk of biochar are reviewed.
- 34
- Deep learning for solving inversion problem of atmospheric refractivity estimation30
A network mapping model is established between the sea clutter and the refractivity parameters of the evaporation duct and the surface based duct, combined with the deep learning to verify the feasibility of deep learning in the inversion problem.
- Dig into Multi-modal Cues for Video Retrieval with Hierarchical Alignment25
This paper leverages the hierarchical video-text alignment to fully explore the detailed diverse characteristics in multi-modal cues for fine-grained alignment with local semantics from phrases, as well as to capture a high-level semantic correspondence.
- 24
- A Coarse-to-fine Pyramidal Model for Person Re-identification via Multi-Loss Dynamic Training.24
A novel coarse-to-fine pyramid model is proposed that not only incorporates local and global information, but also integrates the gradual cues between them that is able to match the cues at different scales and then search for the correct image of the same identity even when the image pair are not aligned.
- Supervised latent Dirichlet allocation with a mixture of sparse softmax23
This work embeds a mixture of softmax model into latent Dirichlet allocation model, and proposes a supervised topic model, supervised latent Diriclet allocation with a mixtureof softmax, and its improved version, supervised Latent Dirichlets allocation with an improved version of sparse softmax.
- Rethinking Temporal Fusion for Video-Based Person Re-Identification on Semantic and Time Aspect22
A novel general temporal fusion framework to aggregate frame features on both semantic aspect and time aspect and a multi-stage fusion network is explored to fuse richer frame features at multiple semantic levels, which can effectively reduce the information loss caused by the traditional single- stage fusion.
- Ask&Confirm: Active Detail Enriching for Cross-Modal Retrieval with Partial Query21
This work introduces the partial-query problem and extensively analyze its influence on text-based image retrieval, and proposes a novel retrieval framework that conducts the interactive process in an Ask-and-Confirm fashion, where AI actively searches for discriminative details missing in the current query, and users only need to confirm AI’s proposal.
- One for More: Selecting Generalizable Samples for Generalizable ReID Model20
A one-for-more training objective that directly takes the generalization ability of selected samples as a loss function and learn a sampler to automatically select generalizable samples that can effectively improve the ReID model training and boost the performance of ReID models.
- Prediction of radar sea clutter based on LSTM20
A new method based on long short-term memory (LSTM) for predicting sea clutter at longer distances in the atmospheric duct environment using near-distance observations is proposed, the principle of LSTM network is introduced, and the factors affecting prediction accuracy are analyzed.
- 18
- 16
- Two-dimensional LSTM soft sensor using noisy process data14
A correntropy-based two-dimensional long short-term memory model is developed to handle noisy process data and is utilized to assign relatively small weights to outliers automatically, enabling reliable prediction.
- Enhancing the Recognition Task Performance of MEMS Resonator-Based Reservoir Computing System via Nonlinearity Tuning13
This work innovatively introduces a nonlinear tuning strategy to analyze the computing properties (the processing speed and recognition accuracy) of the presented RC and numerically and experimentally analyzes the influence of the hybrid nonlinear dynamics using the image classification task.
- 13
- Input–Output-Improved Reservoir Computing Based on Duffing Resonator Processing Dynamic Temperature Compensation for MEMS Resonant Accelerometer12
The study confirmed the feasibility of RC in realizing dynamic temperature compensation precisely, which provides a potential real-time online temperature compensation method and a sensor system with edge computing.
- An experimental investigation into the borehole drilling and strata characteristics12
The main purpose of this paper is to comprehensively analyze the response characteristics of borehole drilling parameters and find a better method to predict rock mechanical properties based on drilling parameters.
- Design and experimental study of a novel 7-DOF manipulator for transrectal ultrasound probe12
A manipulator for transrectal ultrasound probe is designed, which assists doctors in performing prostate biopsy and improves the efficiency and accuracy of biopsy procedure.
- An Improved YOLOv8 Model for Strip Steel Surface Defect Detection10
An enhanced detection model known as YOLOv8-BSPB, which includes a novel pooling layer module, SCRD, which replaces max pooling with average pooling, and integrates a polarized self-attention mechanism to improve the model’s feature representation and enhance its ability to focus on relevant information is proposed.
- 10
- 10
- 10
- A Part Power Set Model for Scale-Free Person Retrieval10
An end-to-end part power set model with multi-scale features is proposed, which captures the discriminative parts of pedestrians from global to local, and from coarse to fine, enabling part-based scale-free person re-ID.
- 9
- 9
- 7
- Aesthetic quality evaluation of packaging design with graph neural networks and composition features5
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- Devil's in the Detail: Graph-based Key-point Alignment and Embedding for Person Re-ID4
An end-to-end ReID method that integrates both key recognition patterns into a unified framework, called Siamese-GCN, and achieves state-of-the-art performance on three public datasets is proposed.
- 4
- Image-Text Dual Model for Small-Sample Image Classification4
The proposed image-text dual model aims to utilize the text information to overcome the problem of training deep models on small-sample datasets and can achieve the highest image classification accuracy among all the referred models on LabelMe and UIUC-Sports.
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- Low-Rank Matrix Recovery via Continuation-Based Approximate Low-Rank Minimization2
Convergence analysis on optimization, and experiments of background subtraction on seven challenging real-world videos show the efficacy of the proposed low-rank model through comparing tanh-RPCA with several state-of-the-art methods.
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- DGD: Densifying the Knowledge of Neural Networks with Filter Grafting and Knowledge Distillation.–
The impacts of the two techniques are surprisingly complementary: distillation mostly enhances the knowledge of valid filters while grafting mostly reactivates invalid filters, helping to design a unified training framework called DGD, where distillation and grafting are naturally combined to increase the knowledge density inside the filters given a fixed model structure.
- –
- –
- –
- –
- –
- –
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.