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
- M. TakaharaSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works114 from public data
- 260
- Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentation206
This work proposes regional semantic contrast and aggregation (RCA), equipped with a regional memory bank to store massive, diverse object patterns appearing in training data, which acts as strong support for exploration of dataset-level semantic structure.
- Unsupervised Domain Adaptation with Noise Resistible Mutual-Training for Person Re-identification186
A Noise Resistible Mutual-Training (NRMT) method, which maintains two networks during training to perform collaborative clustering and mutual instance selection, which outperforms the state-of-the-art UDA methods for person re-ID.
- 184
- Robust LSTM-Autoencoders for Face De-Occlusion in the Wild175
A robust LSTM-Autoencoders (RLA) model is proposed to effectively restore partially occluded faces even in the wild and provides significantly larger performance gain than other de-occlusion methods in promoting recognition performance over partially-occluded faces.
- Dual-Agent GANs for Photorealistic and Identity Preserving Profile Face Synthesis169
Experimental results show that the proposed Dual-Agent Generative Adversarial Network (DA-GAN) model not only presents compelling perceptual results but also significantly outperforms state-of-the-arts on the large-scale and challenging NIST IJB-A unconstrained face recognition benchmark.
- Look across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition104
This work proposes a deep Age-Invariant Model (AIM) for face recognition in the wild with three distinct novelties, and proposes a new large-scale Cross-Age Face Recognition (CAFR) benchmark dataset to facilitate existing efforts and push the frontiers of age-invariant face recognition research.
- Beyond Monocular Deraining: Parallel Stereo Deraining Network Via Semantic Prior78
A Paired Rain Removal Network (PRRNet), which exploits both stereo images and semantic information is presented, and a Semantic-Aware Deraining Module (SADM) is developed which solves both tasks of semantic segmentation and deraining of scenes.
- 76
- 70
- Dynamic Conditional Networks for Few-Shot Learning70
This paper proposes a novel Dynamic Conditional Convolutional Network (DCCN) to handle conditional few-shot learning, i.e, only a few training samples are available for each condition, and evaluates DCCN on four tasks which can be formulated as conditional model learning.
- Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry68
This work proposes a novel Residual RETargeting network (R2ET) structure, which relies on two neural modification modules, to adjust the source motions to fit the target skeletons and shapes progressively, and presents a balancing gate to conduct linear interpolation between them.
- Learning Anchored Unsigned Distance Functions with Gradient Direction Alignment for Single-view Garment Reconstruction65
AnchorUDF represents 3D shapes by predicting unsigned distance fields (UDFs) to enable open garment surface modeling at arbitrary resolution and achieves the state-of-the-art performance on single-view garment reconstruction.
- Attentive WaveBlock: Complementarity-Enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-Identification and Beyond64
A novel light-weight module, the Attentive WaveBlock (AWB), which can be integrated into the dual networks of mutual learning to enhance the complementarity and further depress noise in the pseudo-labels is proposed.
- Attentive WaveBlock: Complementarity-enhanced Mutual Networks for Unsupervised Domain Adaptation in Person Re-identification.62
A novel light-weight module, the Attentive WaveBlock (AWB), which can be integrated into the dual networks of mutual learning to enhance the complementarity and further depress noise in the pseudo-labels is proposed.
- Beyond Monocular Deraining: Stereo Image Deraining via Semantic Understanding55
A Paired Rain Removal Network (PRRNet) is presented, which exploits both stereo images and semantic information, and a Semantic-Aware Deraining Module (SADM) which solves both tasks of semantic segmentation and deraining of scenes, and a Semantic-Fusion Network (SFNet) and a View-Fusion Network (VFNet) which fuse semantic information and multi-view information respectively.
- Multi-Prototype Networks for Unconstrained Set-based Face Recognition52
A novel Multi-Prototype Network (MPNet) model is proposed to learn multiple prototype face representations adaptively from the media sets to demonstrate superiority of the proposed model over state-of-the-arts.
- Robust Face Recognition with Deep Multi-View Representation Learning47
This paper describes the proposed method targeting at the MSR Image Recognition Challenge MS-Celeb-1M, to recognize one million celebrities from their face images captured in the real world, which provides a large scale dataset crawled from the Web, which contains a large number of celebrities with many images for each subject.
- 34
- 34
- A Combined Model Based on Feature Selection and WOA for PM2.5 Concentration Forecasting30
The proposed hybrid model based on feature selection and whale optimization algorithm for the prediction of P M 2.5 concentration is better than benchmark models, such as single LSSVM model with default parameters optimization, single BP neural networks (BPNN), general regression neural network (GRNN) and some other combined models recently reported.
- Deep Attribute-preserving Metric Learning for Natural Language Object Retrieval28
A deep Attribute-Preserving Metric learning (AP-Metric) framework that jointly generates unique query-sensitive region proposals and conducts novel cross-modal feature learning that explicitly pursues consistency over semantic attribute abstraction within both domains for deep metric learning is proposed.
- Sparsity Adaptive Matching Pursuit Detection Algorithm Based on Compressed Sensing for Radar Signals26
The application of the emerging compressed sensing (CS) theory and the geometric characteristics of the targets in radar images are investigated and a novel sparsity adaptive matching pursuit (SAMP) detection algorithm is proposed, which adaptively completes the detection task without knowing the signal sparsity.
- Integrated Face Analytics Networks through Cross-Dataset Hybrid Training26
An integrated Face Analytics Network (iFAN) is proposed, which is able to perform multiple tasks jointly for face analytics with a novel carefully designed network architecture to fully facilitate the informative interaction among different tasks.
- On initial Brain Activity Mapping of episodic and semantic memory code in the hippocampus26
It is shown that appropriate large-scale statistical methods are essential to decipher and measure real-time memory traces and neural dynamics, and it is concluded that the specific-to-general categorical and combinatorial feature-coding cell assembly mechanism represents an emergent property for enabling the neural networks to generate and organize not only episodic memory, but also semantic knowledge and imagination.
- Foundation Model for Skeleton-Based Human Action Understanding23
A Unified Skeleton-based Dense Representation Learning (USDRL) framework is presented, which serves as a foundational model for skeleton-based human action understanding and significantly outperforms the current state-of-the-art methods.
- Human Parsing Based Texture Transfer from Single Image to 3D Human via Cross-View Consistency22
A human parsing based texture transfer model via cross-view consistency learning to generate the texture of 3D human body from a single image to reduce the appearance variation of human image and preserve the spatial distribution of semantic parts.
- 21
- 20
- An implicit opinion analysis model based on feature-based implicit opinion patterns18
The proposed model outperforms the traditional support vector machine model and the cutting-edge convolutional neural network model to perform implicit opinion analysis of Chinese customer reviews at both the feature and review levels.
- Computational Classification Approach to Profile Neuron Subtypes from Brain Activity Mapping Data18
It is demonstrated that the uncovered dopaminergic neuron subtypes encoded distinct aspects of fearful experiences such as valence or value, whereas distinct hippocampal CA1 pyramidal cells responded differentially to ketamine-induced anesthesia.
- AFANet: Adaptive Frequency-Aware Network for Weakly-Supervised Few-Shot Semantic Segmentation16
This paper utilizes the more challenging image-level annotations and proposes an adaptive frequency-aware network (AFANet) for weakly-supervised few-shot semantic segmentation (WFSS) and proposes a cross-granularity frequency-aware module (CFM) that decouples RGB images into high-frequency and low-frequency distributions and further optimizes semantic structural information by realigning them.
- 16
- 16
- 14
- 14
- Learning Anchor Transformations for 3D Garment Animation13
An anchor-based deformation model, namely AnchorDEF, to predict 3D garment animation from a body motion sequence that deforms a garment mesh template by a mixture of rigid transformations with extra nonlinear displacements and an adaptive anchor updating is proposed to optimize the anchor position.
- 13
- Biphasic Face Photo-Sketch Synthesis via Semantic-Driven Generative Adversarial Network With Graph Representation Learning13
A novel semantic-driven generative adversarial network to address the above issues, cooperating with graph representation learning, and presents a biphasic interactive cycle training strategy that outperforms the state-of-the-art competitors on the CUHK Face Sketch (CUFS) and CUHK Face Sketch FERET (CUFSF) datasets.
- LAD-Reasoner: Tiny Multimodal Models are Good Reasoners for Logical Anomaly Detection12
A new task, Reasoning Logical Anomaly Detection (RLAD), which extends traditional anomaly detection by incorporating logical reasoning, and proposes a new framework, LAD-Reasoner, a customized tiny multimodal language model built on Qwen2.5-VL 3B, which excels in producing concise and interpretable rationales.
- 11
- Research on PM2.5 Spatiotemporal Forecasting Model Based on LSTM Neural Network11
A new air quality spatiotemporal prediction model to predict future air quality and is based on a large number of environmental data and a long short-term memory (LSTM) neural network is proposed, which is better than other baseline models.
- Techniques for minimizing error propagation in decision feedback detectors for recording channels11
Two approaches are proposed for minimizing EP in DFE by using simple threshold techniques to detect the presence of decision errors and to either correct these errors or minimize the possibility of further errors.
- 10
- Learning Relevance Restricted Boltzmann Machine for Unstructured Group Activity and Event Understanding10
The experimental results demonstrate that the relevant features learned by the ReRBM provide better semantic and discriminative description for videos than a number of alternative supervised latent variable models, and achieves state of the art performance in terms of classification accuracy and retrieval precision.
- Recent advances in combatting bacterial infections via well-designed metallacycles/metallacages9
A review of the design strategy and applications of SCCs in antibacterials or anti-biofilms and an outlook on future research is provided.
- 9
- 9
- 8
- 6
- AnomalyControl: Highly-Aligned Anomalous Image Generation with Controlled Diffusion Model5
A controlled anomaly generation model named AnomalyControl is proposed to generate realistic anomalous images aligned highly with both text prompts and anomaly masks that outperform the state-of-the-art anomaly generation methods in terms of authenticity and consistency, and can significantly improve the performance of downstream anomaly detection tasks, especially anomaly localization.
- 5
- 5
- On brain activity mapping: insights and lessons from Brain Decoding Project to map memory patterns in the hippocampus5
It is proposed that in order to harness unique insights and extensive knowledge from various investigators working in diverse neuroscience subfields, the BRAIN project should create a set of International and National Brain Decoding Centers at which cutting-edge recording technologies and expertise on analyzing large datasets analyses can be made readily available to the entire community of neuroscientists.
- Research on Stalk Crops Internodes and Buds Identification based on Computer Vision4
The system of computer vision that used to identify the internodes and buds of stalk crops, including three modules: camera calibration, high-speed vision technology and digital image processing is summarized.
- 4
- 4
- 4
- Multiple-criteria call admission control scheme for ATM networks4
The proposed PMT CAC scheme implements the dynamic admission control which can be applied to the distinct delay-sensitive variable-bit-rate sources and has great flexibility in the bandwidth allocation according to the network status.
- 3
- Dual-domain superoxide dismutase: In silico prediction directed combinatorial mutation for enhanced robustness and catalytic efficiency3
Molecular dynamics simulations, structural and surface charge analysis revealed the possible mechanism by which combinatorial mutations improve the robustness and catalytic activity of GtSOD.
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- Combined Forecast of Calibration Interval Based on Linear Trend Model and Neural Network2
Improved MA - BP prediction model is given to optimize the calibration interval dynamically and the results show that the model has higher prediction precision and better universality.
- Design and Implementation of Web-Based Archive Dispatching Management System2
A web-based graduate archive dispatching management system is proposed, the process of system analysis and design from system modules, system framework and key technologies used in this system are introduced, and subsequent directions of deep research and improvement are summarized.
- An improved image-clarity evaluation function2
Experiments show that the improved image-clarity evaluation function based on Prewitt convolution kernel not only owns the characteristics of good unbiased, clear single apex, high sensitivity, and so on, but also has strong anti-noise performance.
- A naturally evolved metal ion transfer mechanism that improves the catalytic performance and stability of superoxide dismutase1
A previously undescribed metal ion transfer mechanism mediated by the metal ion binding domain (MIBD) of SOD, which significantly improves SOD activity and stability and provides valuable insights into the design of well‐performing metalloenzymes.
- ABounD: Adversarial Boundary-Driven Few-Shot Learning for Multi-Class Anomaly Detection1
A one-for-all learning framework called ABounD that unites semantic concept anchoring with geometric boundary optimization to resolve multi-class ambiguity and removes the requirement for isolated per-category retraining in few-shot settings.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- A Neural Network Classification Model Based on Covering and Immune Clustering Algorithm1
A novel neural network classification model was established based on the covering algorithm (CA) and the immune clustering algorithm (ICA) and was verified through experiments on real-world datasets.
- A Robust Fingerprinting Localization Algorithm Against Signal Strength Attacks1
This chapter designs two attack-resistant algorithms to assure the efficiency and validity of the localization information under signal strength attacks and test the algorithms on ICT’s localization engine with an IEEE 802.11(Wi-Fi) environment.
- A Study on the Automatic Identifying and Tacking Flow Shape Group Moving Targets:a Case of MCS1
The experiments show that the methods and skills can make a computer to automatically identify and track these multi flow shaped moving targets such as MCS and the algorithm of area overlapped method is improved.
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- EETTE: Efficient evolutionary travel time estimation with deep meta learning–
This work proposes a novel efficient evolutionary travel time estimation model, coined as EETTE, to learn travel patterns in both temporal and spatial dimensions with attention based neural networks and efficient meta learning mechanism to address the evolutionary dynamics in temporal dimension.
- –
- –
- Author response for "Multi-Granularity Aggregation Network for Remote Sensing Few-Shot Segmentation"–
- –
- –
- –
- –
- A Behavior-Driven Forum Spammer Recognition Method with Its Application in Automobile Forums–
This work is among the first to construct behavior-driven recognition models according to the different behavioral patterns of forum spammers, and its experimental results illustrate the effectiveness of the methods on classification spammer from common users.
- Comprehensive Analysis Method Based on Multi-attribute Fuzzy Granulation in Decision Evaluation–
Granular computing theory was applied to the evaluation and selection model of suppliers to verify the accuracy and feasibility of the decision analysis method and strengthened the enterprise’s position in the supply chain, and then improved the core competitiveness.
- –
- –
- –
- –
- –
- –
- –
- Ray-Casting Algorithm Based on BVH–
Good performance speed and 3D display were achieved by a three-dimensional reconstruction experiment with real medical chest CT images and the effectiveness of the improved lighting projection algorithm for rapid 3D visualization of thechest CT images was confirmed.
- Design and Implementation of Image Encryption Based on Logistic maps–
Experiments prove that the algorithms are easy to be accomplished and have strong security, decryption image's distortion is low and these algorithms have good encryption effect to color image.
- Research of Data Warehouse Technology–
The internal characteristics of DataWarehouse are introduced and the procedure of integrated Data Warehouse and building the data warehouse, Data Extract, Data Warehouse Storage and how to manage the Data Warehouse is analyzed.
- –
- –
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 2026-10-14. 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.