Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks165 from public data
- 1,597
- A Novel Bi-Hemispheric Discrepancy Model for EEG Emotion Recognition369
The effectiveness and advantage of the proposed BiHDM model in solving the EEG emotion recognition problem are demonstrated and the important brain areas in emotion expression are investigated.
- MPED: A Multi-Modal Physiological Emotion Database for Discrete Emotion Recognition336
A multi-modal physiological emotion database is designed and built, which collects four modal physiological signals, i.e., electroencephalogram (EEG), galvanic skin response, respiration, and electrocardiogram (ECG), and a novel attention-long short-term memory (A-LSTM), which strengthens the effectiveness of useful sequences to extract more discriminative features.
- Pattern-Affinitive Propagation Across Depth, Surface Normal and Semantic Segmentation331
A novel Pattern-Affinitive Propagation framework to jointly predict depth, surface normal and semantic segmentation and achieves the state-of-the-art or competitive results on the three related datasets, NYUD-v2, SUN-RGBD and KITTI.
- Deep Network Cascade for Image Super-resolution264
Experiments on image super-resolution demonstrate that the proposed DNC can gradually upscale a low-resolution image with the increase of network layers and achieve more promising results in visual quality as well as quantitative performance.
- Joint Task-Recursive Learning for Semantic Segmentation and Depth Estimation237
A novel joint Task-Recursive Learning (TRL) framework for the closing-loop semantic segmentation and monocular depth estimation tasks and propagate previous learning experiences on both tasks into the next network evolution by explicitly concatenating previous responses.
- Learning Normal Dynamics in Videos with Meta Prototype Network222
This work proposes a dynamic prototype unit (DPU) to encode the normal dynamics as prototypes in real time, free from extra memory cost, and introduces meta-learning to the authors' DPU to form a novel few-shot normalcy learner, namely Meta-Prototype Unit (MPU).
- 207
- Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection185
This work proposes a new MIL framework: Unbiased MIL (UMIL), to learn unbiased anomaly features that improve WSVAD and demonstrates the effectiveness of this framework on benchmarks UCF-Crime and TAD.
- 185
- 164
- 149
- 144
- 143
- VisDrone-DET2018: The Vision Meets Drone Object Detection in Image Challenge Results133
A large-scale drone-based dataset, including 8, 599 images with rich annotations, including object bounding boxes, object categories, occlusion, truncation ratios, etc, is released, to narrow the gap between current object detection performance and the real-world requirements.
- 130
- Instance-Adaptive Graph for EEG Emotion Recognition120
A novel instance-adaptive graph method (IAG), which employs a more flexible way to construct graphic connections so as to present different graphic representations determined by different input instances, which achieves the state-of-the-art performance.
- 117
- 102
- 94
- 91
- Cross-Database Micro-Expression Recognition: A Benchmark78
A CDMER experimental evaluation protocol is established and a standard platform for evaluating their proposed methods is provided and extensive benchmark experiments are conducted by using NINE state-of-the-art domain adaptation (DA) methods and SIX popular spatiotemporal descriptors for investigating the CDMER problem from two different perspectives.
- Consistent Instance False Positive Improves Fairness in Face Recognition75
A false positive rate penalty loss, which mitigates face recognition bias by increasing the consistency of instance False Positive Rate (FPR), and which requires no demographic annotations to be previously predefined during training.
- Flowing on Riemannian Manifold: Domain Adaptation by Shifting Covariance73
A new unsupervised domain adaptation method called domain adaptation by shifting covariance (DASC) by utilizing the principal components of each covariance matrix for object recognition without requiring any labeled samples from the target domain is proposed.
- A novel hybrid XAJ-LSTM model for multi-step-ahead flood forecasting71
The study concludes that the XAJ-LSTM model that integrates the conceptual model and machine learning can raise the accuracy of multi-step-ahead flood forecasts while improving the interpretability of data-driven model internals.
- Face recognition based on recurrent regression neural network70
This paper proposes a recurrent regression neural network framework to unify two classic tasks of cross-pose face recognition on still images and videos, and explicitly construct the potential dependencies of sequential images so as to regularizing the final learning model.
- Generalized Unsupervised Manifold Alignment67
Experimental results on dataset matching and real-world applications demonstrate the effectiveness and the practicability of the Generalized Unsupervised Manifold Alignment method.
- 61
- Joint sparse representation for video-based face recognition59
This paper proposes a reconstruction-based method for video-based face recognition, where all images from a probe video clip are jointly recovered and uses two sparse constraints to make representation more credible.
- Context-Dependent Diffusion Network for Visual Relationship Detection53
This paper proposes a context-dependent diffusion network (CDDN) framework to deal with visual relationship detection and designs a diffusion network to adaptively aggregate information from contexts, which can effectively learn latent representations of visual relationships and well cater toVisual relationship detection in view of its isomorphic invariance to graphs.
- Learning Object-Wise Semantic Representation for Detection in Remote Sensing Imagery49
An enhanced feature pyramid network is first designed to better extract hierarchical discriminative visual features to suppress background clutter as well as better estimate proposals, and specifically introduces a semantic segmentation module to guide horizontal proposals detection.
- 48
- 43
- 41
- 41
- 39
- Cross-Domain Facial Expression Recognition Based on Transductive Deep Transfer Learning35
The experimental results show that the proposed TDTLN method outperforms state-of-the-art methods in terms of recognition performance on four commonly used multi-view facial expression databases.
- Cross-Database Facial Expression Recognition via Unsupervised Domain Adaptive Dictionary Learning35
The extensive experiments on Multi-PIE and BU-3DFE databases demonstrate that the proposed UDADL is superior over most widely-used domain adaptation methods in dealing with cross-database FER, and achieves the state-of-the-art performance.
- 34
- 33
- 33
- 31
- Variational Pathway Reasoning for EEG Emotion Recognition30
This work proposes a heuristic Variational Pathway Reasoning (VPR) method to deal with EEG-based emotion recognition, which introduces random walk to generate a large number of candidate pathways along electrodes and proposes a sparse variational scaling (SVS) module to learn scaling factors of pseudo pathways.
- Automatic motion capture data denoising via filtered subspace clustering and low rank matrix approximation30
An automatic Motion Capture data denoising approach via filtered subspace clustering and low rank matrix approximation that does not need any physical information about the underling structure of MoCap data or require auxiliary data sets for training priors is presented.
- 29
- 29
- 27
- 27
- An attribution graph-based interpretable method for CNNs26
An Attribution Graph-based Interpretable method for CNNs (AGIC) is proposed which models the overall structure of CNNs as graphs and provides interpretability from global and local perspectives.
- Toward Bridging Microexpressions From Different Domains26
This paper proposes an effective method consisting of an auxiliary set selection model (ASSM) and a transductive transfer regression model (TTRM) that has a more satisfactory performance in dealing with the cross-domain microexpression recognition tasks.
- 26
- Robust tracking via patch-based appearance model and local background estimation25
This paper presents a local spatial co-occurrence based background modeling approach to automatically estimate the local context background model of an interested object captured from a single camera, which may be stationary or moving.
- Edit Temporal-Consistent Videos with Image Diffusion Model24
This article proposes an elegant yet effective Temporal-Consistent Video Editing (TCVE) method to mitigate the temporal inconsistency challenge for robust text-guided video editing, and establishes a dedicated temporal Unet architecture to faithfully capture the temporal coherence of the input video sequences.
- 24
- 24
- Graph Jigsaw Learning for Cartoon Face Recognition24
The proposed GraphJigsaw that constructs jigsaw puzzles at various stages in the classification network and solves the puzzles with the graph convolutional network (GCN) in a progressive manner avoids training the classification model with the deconstructed images that would introduce noisy patterns and are harmful for the final classification.
- Deep Cascaded Regression for Face Alignment24
This work proposes an end-to-end CNN architecture to learn highly discriminative shape-indexed features and proposes "Shape-Indexed Pooling" to extract the deep features from these high level descriptors.
- 23
- Deep Graph Structural Infomax21
This paper presents an effective model called Deep Graph Structural Infomax (DGSI), which extends DGI and could capture more fine-grained semantic information as well as beneficial structural information in a self-supervised manner, thereby improving node representation and further boosting the learning performance.
- 20
- 20
- Compact Video Code and Its Application to Robust Face Retrieval in TV-Series18
Compact Video Code is proposed, which is a compact and discriminative representation for the huge body of video data, named Compact Video Code, and evaluated in traditional video face recognition task on a standard Internet database, showing its quite promising performance.
- MMHCL: Multi-Modal Hypergraph Contrastive Learning for Recommendation17
A novel Multi-Modal Hypergraph Contrastive Learning (MMHCL) framework for user recommendation that obtains denser second-order hypergraphs and excavates more abundant shared attributes to explore the user–product associations, which to a certain extent alleviates the problems of data sparsity and cold-start.
- Deep Wasserstein Graph Discriminant Learning for Graph Classification17
This work proposes a deep Wasserstein graph discriminant learning (WGDL) framework to learn discriminative embeddings of graphs in W-metric matching space, and introduces a reference set of graphs (aka graph dictionary) to express those representative graph samples (aka dictionary keys).
- 16
- 15
- 15
- Walk-Steered Convolution for Graph Classification15
A walk-steered convolutional (WSC) network to assemble the essential success of standard CNNs, as well as the powerful representation ability of random walk, and stack graph coarsening upon Gaussian encoding by using dynamic clustering.
- 14
- Automatic Smile Detection of Infants in Mother-Infant Interaction via CNN-based Feature Learning14
A Convolutional Neural Network (CNN) based method for smile detection is proposed and it is evaluated on two public datasets, GENKI-4K and CelebA, and it achieved satisfactory result of mean accuracy of 94.55% and 92.60%, respectively.
- 14
- 13
- Transfer Vision Patterns for Multi-Task Pixel Learning13
A multi-task vision pattern transformation (VPT) method to adaptively correlate and transfer cross-task visual patterns by leveraging the powerful transformer mechanism and achieves the state-of-that-art performance in three pixel-level visual tasks.
- 12
- Dual-Attention Graph Convolutional Network12
A dual-attention GCN is proposed to model the structural information of various texts as well as tackle the graph-invariant problem through embedding two types of attention mechanisms, i.e. the connection-att attention and hop-attENTION, into the classic GCN.
- Online learning 3D context for robust visual tracking12
A3D context-based object tracking method that learns a set of 3D context key-points, which have spatial–temporal co-occurrence correlations with the tracked object, for collaborative tracking in binocular video data is proposed.
- 11
- 11
- 11
- 11
- 11
- 10
- 10
- 10
- 10
- 10
- 9
- 9
- Global Information Guided Video Anomaly Detection9
An end-to-end GIG anomaly detection framework for anomaly detection using the video-level annotations (i.e., weak labels) to first mine the global pattern cues by leveraging the weak labels in a GIG module, and build a spatial reasoning module to measure the relevance between vectors in spatial domain with the global cue vectors.
- Hashing Graph Convolution for Node Classification9
This paper proposes a simple but effective Hashing Graph Convolution (HGC) method by using global-hashing and local-projection on node aggregation for the task of node classification and introduces a prediction-consistent regularization term into HGC to constrain the score consistency of unlabeled nodes in the graph.
- Intelligence Science and Big Data Engineering. Visual Data Engineering9
An IA-DSM scheme is proposed for solving a doubly stochastic matrix (DSM) featured combinatorial tasks such as travelling salesman problem, and also a Subtree driven reasoning scheme is suggested for improving production rule based reasoning.
- 8
- 8
- Counterfactual discriminative micro-expression recognition8
A counterfactual discriminative micro-expression recognition (CoDER) method to effectively learn the slight temporal variations for video-based MER and results in comparable and superior MER performance compared with that of the state-of-the-art methods.
- Multiview Inherent Graph Hashing for Large-Scale Remote Sensing Image Retrieval8
A novel multiview inherent graph hashing (MvIGH) for RSIR that captures the latent similarities among RS images, and adaptively learns weights of each view to characterize its contribution, and develops an efficient alternating algorithm to solve the formulated optimization problem.
- Going Beyond Consistency: Target-oriented Multi-view Graph Neural Network7
Target-oriented Graph Neural Network is proposed, a novel framework that goes beyond traditional consistency by prioritizing task-relevant information, ensuring alignment with the target, and derives an upper bound on the loss discrepancy between training and test data, providing formal guarantees for generalization to test domains.
- Graph Game Embedding7
A novel graph learning framework, named graph game embedding, to learn discriminative node representation as well as encode graph structures, which possesses two advantages: the designed utility function ensures the stable graph evolution with theoretical convergence and Nash Equilibrium satisfaction.
- Re-Attentional Controllable Video Diffusion Editing6
This paper proposes a Re-Attentional Controllable Video Diffusion Editing (ReAtCo) method and proposes an Invariant Region-guided Joint Sampling (IRJS) strategy to mitigate the intrinsic sampling errors and faithfully preserve the invariant region content with less border artifacts.
- 6
- 6
- Sparsely encoded local descriptor for face verification5
Experimental results show that the proposed Sparsely Encoded Local Descriptor achieves a competitive accuracy compared with the state-of-the-art methods on the challenging Labeled Faces in the Wild (LFW) database.
- 4
- 4
- 4
- Exploratory Inference Learning for Scribble Supervised Semantic Segmentation4
This work proposes a novel exploratory inference learning (EIL) framework, which facilitates efficient probing on unlabeled pixels and promotes selecting confident candidates for boosting the evolved segmentation in scribble supervised semantic segmentation.
- 4
- Spatio-Temporal Relation Learning for Video Anomaly Detection4
A Spatial-Temporal Relation Learning (STRL) framework to tackle the video anomaly detection task, and the plausibility of object-scene relation is measured by jointly modeling object/scene features and optimizable object- Scene relation maps.
- 4
- 4
- Graph Deformer Network4
A simple yet effective Graph Deformer Network (GDN) to fulfill anisotropic convolution filtering on graphs, analogous to the standard convolution operation on images, and shows the promising property of graph isomorphism testing.
- LLM-Assisted Semantic Guidance for Sparsely Annotated Remote Sensing Object Detection3
An LLM-assisted semantic guidance framework tailored for sparsely annotated remote sensing object detection, exploiting the advanced semantic reasoning capabilities of large language models (LLMs) to distill high-confidence pseudo-labels.
- Physical education teaching: A biomechanical perspective of physical education educators and coaches3
- 3
- RecNet: A Resource-Constraint Aware Neural Network for Used Car Recommendation3
This paper proposes a resource-constraint-aware network to predict the user’s future interaction based on dynamic connections between users and items and introduces mutual information to measure the similarity between the future user action and fused historical behavior features to predict future interaction.
- Learning cross-modal interaction for RGB-T tracking3
A multi-domain convolutional neural network (MDNet) learning framework to address the problem of visual tracking, where a CNN pre-trained by multi- domain learning is updated online in the context of a new sequence to learn domain-specific information adaptively.
- 3
- 3
- Direction-induced convolution for point cloud analysis3
Comprehensive experiments on three benchmark datasets demonstrate that the proposed DIConv method achieves encouraging performance on both point cloud classification and semantic segmentation tasks.
- Graph Wasserstein Correlation Analysis for Movie Retrieval3
This work derives the solution of the graph comparison model as a classic generalized eigenvalue decomposition problem, which has an exactly closed-form solution.
- 3
- 3
- Fuzzy Level Comprehensive Evaluation Model and Example of Official Performance Evaluation3
The evaluation of official performance is sued to render the qualified problem to become the quantified one, improving the scientific characteristics and reliability of the official performance evaluation.
- 2
- 2
- Structure-Sensitive Graph Dictionary Embedding for Graph Classification2
This work proposes a structure-sensitive graph dictionary embedding (SS-GDE) framework to transform input graphs into the embedding space of a graph dictionary for the graph classification task, and introduces mutual information as the objective, which further deduces variational inference of the adapted graph dictionary.
- Progressive Bayesian Inference for Scribble-Supervised Semantic Segmentation2
A Progressive Bayesian Inference framework is proposed to boost the performance of the scribble-supervised semantic segmentation, which can effectively infer the semantic distribution of these unlabeled pixels to guide the optimization of the segmentation network.
- UniKG: A Benchmark and Universal Embedding for Large-Scale Knowledge Graphs2
This paper constructs a large-scale HG benchmark dataset named UniKG from Wikidata to facilitate knowledge mining and heterogeneous graph representation learning, and proposes a novel plug-and-play anisotropy propagation module (APM) to learn effective multi-hop anisOTropy propagation kernels.
- Global Variational Convolution Network for Semi-supervised Node Classification on Large-Scale Graphs2
- Extending generalized unsupervised manifold alignment2
An explicit relaxed integer programming method is adopted to solve the unsupervised manifold alignment problem, which reconciles three factors covering the updated local structure matching, the the feature comparability and geometric preservation.
- 2
- Fast Hyper-walk Gridded Convolution on Graph2
This paper proposes a high-efficient hyper-walk gridded convolution (hyper-WGC) method to encode non-regular graph data, which overcomes all these aforementioned problems, and proposes random hyper- walk by taking advantages of random-walks as well as node/edge encapsulation.
- KIL: Knowledge Interactiveness Learning for Joint Depth Estimation and Semantic Segmentation2
The proposed unified framework can mine and leverage the connections/complementations of these two tasks effectively and the network parameters can be jointly optimized for boosting the final predictions of depth estimation and semantic segmentation with the coarse-to-fine strategy.
- 2
- Intelligence Science and Big Data Engineering. Big Data and Machine Learning2
The location method based on Received Signal Strength Indication (RSSI) ranging has the advantages of low development cost and simple implementation mechanism, and is the mainstream indoor location method nowadays but there is a lack of systematic research on the characteristics of Access Point (AP) received signal strength.
- Similarity Search over Time Series Data Based on Walsh Transform2
Experimental results demonstrate that performance of the proposed method of indexing and similarity searching in time series databases based on DWHTW is more efficient than that of DFT (Discrete Fourier Transform) and DWT(Discrete Wavelet Transform).
- 1
- Big-model Driven Few-shot Continual Learning1
This work proposes a novel Big-model driven Few-shot Continual Learning (B-FSCL) framework to gradually evolve the model under the traction of the world's big-models (like human accumulative knowledge).
- 1
- 1
- 1
- 1
- 1
- 1
- Cooperative Intrusion Detection Based on K-SVD1
This paper applies the theory of sparse representation to learn robust features by fusing class information into the training process and applies discriminant K-SVD algorithm to intrusion detection, which optimizes the over-completed dictionary and the linear discriminant function together.
- Cooperative Intrusion Detection Algorithm Based on Sparse Representation1
A cooperative intrusion detection algorithm based on sparse representation that can guarantee higher detection rate and low false alarm rate, has good robustness in the imbalanced dataset experiment and has a good degree of differentiation for normal behavior and unusual behavior.
- –
- A Generalized Contour Vibration Model for Building Extraction–
A Generalized Contour Vibration Model (G-CVM) is proposed by inheriting the force and motion principle of contour wave for automatically estimating building contours by integrating the constant coefficient wave differential equation through a convolutional network.
- Visual-like 2D Geometric Template Diffusion for Boosting Single-Sequence Protein Structure Prediction–
This work demonstrates the effectiveness of leveraging powerful vision diffusion models to enhance protein 2D geometric template generation, thereby establishing a new paradigm for single-sequence protein structure prediction.
- –
- –
- –
- MPDS: A Movie Posters Dataset for Image Generation with Diffusion Model–
For movie poster generation, a multi-condition diffusion framework is developed that takes poster prompt, poster caption, and actor image (for personalization) as inputs, yielding excellent results through the learning of a diffusion model.
- –
- –
- –
- –
- –
- Max-margin class incremental learning with mixup augmentation–
This work introduces a maxmargin objective function to explicitly enforce the maximum distance between different classes larger than a predefined margin, which can avoid the ambiguity between old and new classes and then increase the discriminative ability of the learned classifier.
- –
- –
- –
- –
- Cooperative intrusion detection system based on sparse coding and multi-class support vector machine–
Experiments show that the sparsity can remove some noises and make mapping features more discrimi-native, and verify the proposed method, which guarantees higher detection rate and lower false alarm rate, has a good performance in multi-class classification.
- –
- Analysis of Some Problems in Hydroelectric Energy with Regard to Fuzzy Set–
In this paper defect of membership degree written by L.A.Zadeh,feasibility of maximum membership degree law, influence of distance parameter in Fuzzy optimization and defect of liner weight average model in FBuzzy judge are discussed.
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 2026-10-15. 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.