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
- Yong XiangSuggested from co-authorship
- Yi ZhangSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works224 from public data
- Contrastive Clustering862
An online clustering method called Contrastive Clustering (CC) which explicitly performs the instance- and cluster-level contrastive learning and jointly learns representations and cluster assignments in an end-to-end manner is proposed.
- 459
- Massive MIMO Linear Precoding: A Survey253
It is shown that a viable precoding technique for massive MIMO systems is still unknown to date, and several research potentials that are worthy of future research efforts are suggested.
- 199
- Spectrogram based multi-task audio classification178
This paper proposes a Deep Neural Network (DNN)-based multi-task model that exploits such relationships and deals with multiple audio classification tasks simultaneously and achieves higher accuracy than task-specific models which train the models separately.
- Twin Contrastive Learning for Online Clustering173
It is found that when the data is projected into a feature space with a dimensionality of the target cluster number, the rows and columns of its feature matrix correspond to the instance and cluster representation, respectively.
- Noisy-Correspondence Learning for Text-to-Image Person Re-Identification156
A novel Robust Dual Embedding method (RDE) that can learn robust visual-semantic associations even with noisy correspondence and achieves state-of-the-art results both with and without synthetic noisy correspondences on all three datasets.
- 156
- 138
- Deep Evidential Learning with Noisy Correspondence for Cross-modal Retrieval136
A generalized Deep Evidential Cross-modal Learning framework (DECL), which integrates a novel Cross- modal Evidential Learning paradigm (CEL) and a Robust Dynamic Hinge loss (RDH) with positive and negative learning to address the amplification problem and embrace higher robustness against high noise.
- Scalable Deep Multimodal Learning for Cross-Modal Retrieval133
Comprehensive experimental results on four widely-used benchmark datasets demonstrate that the proposed SDML is effective and efficient in multimodal learning and outperforms the state-of-the-art methods in cross-modal retrieval.
- 127
- Deep drug-target binding affinity prediction with multiple attention blocks117
Experimental results of DTI prediction on two benchmark datasets show the proposed end-to-end model outperforms existing methods, which are benefit from the correlation information encoded by the relation-aware self-attention block and the interaction information extracted by the multi-head attention block.
- 113
- 112
- 110
- Multi-View Linear Discriminant Analysis Network104
A Multi-view Linear Discriminant Analysis Network (MvLDAN) is proposed by seeking a nonlinear discriminant and view-invariant representation shared among multiple views by employing multiple feedforward neural networks and a novel eigenvalue-based multi-view objective function.
- Underdetermined Blind Source Separation Using Sparse Coding99
This paper proposes an effective approach to discover some 1-D subspaces from the set consisting of all the time-frequency representation vectors of observed mixture signals that are associated with TF points where only single source possesses dominant energy.
- 95
- Spread Spectrum Audio Watermarking Using Multiple Orthogonal PN Sequences and Variable Embedding Strengths and Polarities91
This paper proposes a novel SS-based audio watermarking method that can embed a large number of watermark bits into an audio signal without compromising the robustness against common attacks and is computationally efficient.
- 89
- 84
- Multimodal adversarial network for cross-modal retrieval73
A Multimodal Adversarial Network (MAN) method to project the multimodal data into a common space wherein the similarities between different modalities can be directly computed by the same distance measurement, and could be one of the first works to specifically design for the multi-modality representation learning with adversarial learning.
- 72
- 72
- DRSL: Deep Relational Similarity Learning for Cross-modal Retrieval66
Deep Relational Similarity Learning (DRSL) is a deep hybrid framework that integrates the relation networks module for relation learning, capturing the implicit nonlinear distance metric.
- 64
- 56
- 56
- 52
- 49
- Image Clustering with External Guidance48
An externally guided clustering method (Text-Aided Clustering, TAC), which leverages the textual semantics of WordNet to facilitate image clustering, which achieves state-of-the-art performance on five widely used and three more challengingimage clustering benchmarks, including the full ImageNet-1K dataset.
- 48
- Improving rare disease classification using imperfect knowledge graph47
This study develops a text classification algorithm that represents a document as a combination of a “bag of words” and a "bag of knowledge terms" where a "knowledge term" is a term shared between the document and the knowledge graph relevant to the disease classification task.
- 46
- Dual Self-Paced Cross-Modal Hashing45
This work proposes a novel Dual Self-Paced Cross-Modal Hashing (DSCMH) that mimics human cognitive learning to learn hashing from ``easy'' to ``hard'' in both instance and feature levels, thereby embracing robustness against noise/outliers.
- A Comprehensive Survey on Edge Data Integrity Verification: Fundamentals and Future Trends45
A comprehensive survey of the significance of the edge data integrity verification (EDIV) problem, the integrity verification difference between data cached on cloud and edge, and three typical system models with corresponding inspection processes is stated.
- Underdetermined blind separation of non-sparse sources using spatial time-frequency distributions42
Theoretical analysis and simulation results show the effectiveness of the proposed UBSS algorithm to separate n source signals from m (m=3) instantaneous linear mixtures.
- 41
- 40
- Adversarial correlated autoencoder for unsupervised multi-view representation learning39
AdvCAE could be one of the first unsupervised multi-view representation learning approaches that work in the manner of adversarial learning and remarkably outperforms than 15 state-of-the-art methods.
- scBridge embraces cell heterogeneity in single-cell RNA-seq and ATAC-seq data integration38
It is observed that the omics difference varies in cells, and cells with smaller omics differences are easier to be integrated, thus benefiting the integration for the rest cells.
- 37
- 37
- 37
- 36
- Separated Variational Hashing Networks for Cross-Modal Retrieval35
This paper proposes a novel approach called Separated Variational Hashing Networks (SVHNs), which adopts a label network (LabNet) to exploit available and nonspecific label annotations to learn a latent common Hamming space by projecting each semantic label into a common binary representation.
- Robust time‐spread echo watermarking using characteristics of host signals35
A robust audio watermarking method based on the time-spread (TS) echo hiding scheme is proposed, which is more robust as it exploits the characteristics of host signals in the encoding stage.
- 34
- Feature and Semantic Views Consensus Hashing for Image Set Classification31
This paper proposes a novel ISC method, termly feature and semantic views consensus hashing (FSVCH), and proposes TCHL guided optimal hash function inversion (TGHI) to learn a high-quality general hash function.
- Human-centered Interactive Learning via MLLMs for Text-to-Image Person Re-identification30
An Interactive Cross-modal Learning framework (ICL), which leverages human-centered interaction to enhance the discriminability of text queries through external multimodal knowledge, and introduces a novel Reorganization Data Augmentation (RDA) strategy based on information enrichment and diversity enhancement to enhance query discriminability.
- UAVData: A dataset for unmanned aerial vehicle detection30
This study collects and releases a dataset for UAV detection, called UAVData, and utilizes 4 different convolutional neural network models as the backbone models of these object detection methods to learn UAV-related features in images.
- 29
- Robust Contrastive Cross-modal Hashing with Noisy Labels29
This paper proposes a novel framework, termed Noise Resistance Cross-modal Hashing (NRCH), to learn hashing with noisy labels by overcoming two key challenges, i.e. noise overfitting and error accumulation.
- 28
- Deep Fair Clustering via Maximizing and Minimizing Mutual Information: Theory, Algorithm and Metric28
This work develops a mutual information theory for deep fair clustering and accordingly designs a novel algorithm, dubbed FCMI, designed to achieve four characteristics highly expected by deepFair clustering, i.e., compact, balanced, and fair clusters, as well as informative features.
- 28
- 28
- Robust Duality Learning for Unsupervised Visible-Infrared Person Re-Identification27
A novel robust duality learning framework (RoDE) for UVI-ReID is proposed to mitigate the adverse impact of noisy pseudo-labels and a novel Robust Adaptive Learning mechanism (RAL) is proposed to dynamically prioritize clean samples while deprioritizing noisy ones, thus avoiding overemphasizing noise.
- 27
- Cross-modal discriminant adversarial network27
This work proposes CDM to project the generated results into a single common space, accompanying with a novel eigenvalue-based loss, which could push as much discriminative power as possible into all latent directions.
- 27
- 26
- 26
- Local feature based multi-view discriminant analysis26
A novel local feature based multi-view discriminant analysis approach (FMDA) that addresses the small sample size (SSS) problem and preserving the discriminative information while reducing the redundant information in the LFD matrices.
- 25
- 24
- 24
- 23
- 22
- 22
- 22
- 21
- 20
- 20
- 19
- 19
- 19
- Kernel truncated regression representation for robust subspace clustering19
Kernel truncated regression representation has the advantages of a closed-form solution and the capacity of clustering data points that lie on nonlinear subspaces, which makes the method efficient in handling large-scale datasets and enables the proposed method to conquer the non linear subspace clustering challenge.
- Objective reduction for visualising many-objective solution sets19
An objective reduction-based visualisation method (ORV) is proposed to view many-objective solution sets that attempts to map a solution set from a high-dimensional objective space into a low-dimensional space while preserving the distribution and the Pareto dominance relation between solutions in the set.
- 19
- 18
- Underdetermined mixing matrix estimation by exploiting sparsity of sources18
The pairwise relationships among all of the mixture representations are utilized to detect the single source points in the time-frequency domain to estimate the underlying mixing matrix.
- 18
- Deep Evidential Hashing for Trustworthy Cross-Modal Retrieval17
This paper proposes a novel method called Deep Evidential Cross-modal Hashing (DECH), which equips hashing models with the ability to quantify the reliability level of the association between a query sample and each corresponding retrieved sample, bringing a new dimension of reliability to the cross-modal retrieval process.
- LLaVA-ReID: Selective Multi-image Questioner for Interactive Person Re-Identification17
This work proposes LLaVA-ReID, a question model that generates targeted questions based on visual and textual contexts to elicit additional details about the target person in a dialogue-based retrieval task called interactive person re-identification (Inter-ReID).
- 16
- 16
- 16
- Adjusting Parallel Coordinates for Investigating Multi-objective Search16
This paper attempts to adjust parallel coordinates to incorporate rare information of the relation between these objectives and also the Pareto dominance relation between solutions in multi-objective optimization.
- 16
- 16
- 16
- 16
- 16
- 15
- MetaQ: fast, scalable and accurate metacell inference via single-cell quantization15
The authors propose MetaQ, a metacell algorithm that reduces cell number while preserving biological characteristics through a cell quantisation process, supporting both uni- and multi-omics data.
- 15
- 15
- 14
- 14
- ROAD: Robust Unsupervised Domain Adaptation with Noisy Labels14
A robust unsupervised domain adaptation framework (ROAD), which prevents the network model from overfitting noisy labels to capture accurate discrimination knowledge for domain adaptation, and a Robust Adaptive Weighted Learning mechanism (RSWL) is proposed to adaptively assign weights to each sample based on its reliability to enforce the model to focus more on reliable samples and less on unreliable samples, thereby mining robust discrimination knowledge against noisy labels in the source domain.
- 14
- 14
- 13
- 13
- 13
- A neural networks learning algorithm for minor component analysis and its convergence analysis13
A neural networks learning algorithm for estimating adaptively minor component from input signals via a deterministic discrete time (DDT) method is proposed.
- Trustworthy Visual-Textual Retrieval12
A novel Trust-Consistent Learning framework is proposed to endow visual-textual retrieval with uncertainty evaluation for trustworthy retrieval, and first models the matching evidence according to cross-modal similarity to estimate the uncertainty for cross-modal uncertainty-aware learning.
- Locally linear representation for image clustering12
A novel scheme is proposed, where the similarity computation among different data points depends on both their pairwise distances and the linear representation relationships, and encodes each data point using a collection of data points that are close to the objective point.
- 11
- 11
- 11
- 11
- Underdetermined Blind Separation by Combining Sparsity and Independence of Sources11
This paper proposes an effective scheme to search some sample segments with the local sparsity and achieves source recovery by exploiting a mild sparsity constraint, which is proven to be a sufficient and necessary condition to guarantee recovery of source signals.
- 10
- 10
- 10
- 10
- 10
- 9
- 9
- 9
- 9
- 9
- 9
- 8
- 8
- 8
- 8
- 8
- Local Neighborhood Embedding for Unsupervised Nonlinear Dimension Reduction8
A novel algorithm, called Local NeighborhoodEmbedding (LNE), which preserves pairwise-distance basedsimilarity and reconstruction coefficient based similarity for finding the latent low dimensional structure of data and works well even in under-sampled case.
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- Free-gram phrase identification for modeling Chinese text3
A novel approach for key phrase identification is proposed which is capable of identify phrases with all lengths and thus improves the coding efficiency and discrimination of the data representation.
- 3
- 3
- 3
- PointCloud-Text Matching: Benchmark Datasets and a Baseline2
This paper presents and studies a new instance-level retrieval task: PointCloud-Text Matching (PTM), which aims to identify the exact cross-modal instance that matches a given point-cloud query or text query, and proposes a PTM baseline, named Robust PointCloud-Text Matching method (RoMa).
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- Locally linear representation for subspace learning and clustering1
The proposed algorithm can automatically encode each data point over a set of points that not only could denote the objective point with less residual error, but also are close to the point in Euclidean space.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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 2026-10-13. 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.