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
- Songde MaSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works309 from public data
- 780
- 728
- 634
- 615
- Content-based audio classification and retrieval by support vector machines494
The SVMs with a binary tree recognition strategy are used to tackle the audio classification problem and experimental comparisons for audio retrieval are presented to show the superiority of this novel metric, called distance-from-boundary (DFB).
- A survey on deep learning based face recognition485
Major deep learning concepts pertinent to face image analysis and face recognition are reviewed, and a concise overview of studies on specific face recognition problems is provided, such as handling variations in pose, age, illumination, expression, and heterogeneous face matching.
- Support vector machines for face recognition338
The performance of the SVMs based face recognition is compared with the standard eigenface approach, and also the more recently proposed algorithm called the nearest feature line (NFL).
- TransFER: Learning Relation-aware Facial Expression Representations with Transformers319
The proposed TransFER model outperforms the state-of-the-art methods on several FER benchmarks, showing its effectiveness and usefulness.
- Support Vector Machines Applications281
This book focuses on the recent advances and applications of the SVM, such as image processing, medical practice, computer vision, and pattern recognition, machine learning, applied statistics, and artificial intelligence.
- 274
- 270
- A survey on still image based human action recognition260
A detailed overview of the state-of-the-art methods for still image-based action recognition is presented, and various high-level cues and low-level features for action analysis in still images are described.
- 257
- 252
- 239
- 229
- CASIA-SURF: A Large-Scale Multi-Modal Benchmark for Face Anti-Spoofing226
A novel multi-modal multi-scale fusion method is presented as a strong baseline, which performs feature re-weighting to select the more informative channel features while suppressing the less useful ones for each modality across different scales.
- 225
- WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild222
A large and diverse dataset named WiderPerson for dense pedestrian detection in the wild, which contains dense pedestrians with various kinds of occlusions, and finds the classification ability of pedestrian detector needs to be improved to reduce false alarm and misdetection rates.
- 213
- 205
- Fusion-Mamba for Cross-Modality Object Detection190
This work investigates a novel cross-modality fusion approach by associating cross-modal features in a hidden state space based on an improved Mamba with a gating attention mechanism, and establishes a new baseline for cross-modality object detection.
- CASIA-SURF CeFA: A Benchmark for Multi-modal Cross-ethnicity Face Anti-spoofing181
This work introduces the largest CASIA-SURF Cross-ethnicity Face Anti-spoofing (CeFA) dataset, and proposes a novel multi-modal fusion method as a strong baseline to alleviate the ethnic bias.
- Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection170
A depth-conditioned dynamic message propagation (DDMP) network to effectively integrate the multi-scale depth information with the image context and dynamically predicting hybrid depth-dependent filter weights and affinity matrices for propagating information is proposed.
- Vision Transformer With Attentive Pooling for Robust Facial Expression Recognition161
Two attentive pooling (AP) modules to pool noisy features directly and intuitively reduce the computational cost while boosting the performance by pursuing the most discriminative features are presented.
- 159
- 157
- 156
- 141
- Multiple feature fusion by subspace learning139
This paper reformulates the multiple feature fusion as a general subspace learning problem to find a general linear subspace in which the cumulative pairwise canonical correlation between every pair of feature sets is maximized after the dimension normalization and subspace projection.
- 138
- 137
- 136
- Contrastive Context-Aware Learning for 3D High-Fidelity Mask Face Presentation Attack Detection130
This work introduces a large-scale High-Fidelity Mask dataset, namely HiFiMask, and proposes a novel Contrastive Context-aware Learning (CCL) framework for supervised PAD tasks, which is able to learn by leveraging rich contexts accurately among pairs of live faces and high-fidelity mask attacks.
- Nested Collaborative Learning for Long-Tailed Visual Recognition128
A Nested Collaborative Learning (NCL), which tackles the problem by collaboratively learning multiple experts together by using a nested way, and helps the network to capture not only global and robust features but also meticulous distinguishing ability.
- 127
- Evaluating spatiotemporal interest point features for depth-based action recognition122
This paper evaluates the spatiotemporal interest point (STIP) based features for depth-based action recognition, and investigates a fusion of the best STIP features with the prevalent skeleton features, to present a complementary use of the STip features for action recognition on 3D data.
- 112
- SAR-Net: Shape Alignment and Recovery Network for Category-level 6D Object Pose and Size Estimation111
This paper proposes a method of Category-level 6D Object Pose and Size Estimation (COPSE) from the point cloud of the target object, without external real pose-annotated training data, and deploys the approach to a physical Baxter robot to perform grasping tasks on unseen but category-known instances.
- 111
- 110
- Robust watermarking using orthogonal Fourier–Mellin moments and chaotic map for double images107
A robust watermarking scheme based on orthogonal Fourier-Mellin moments and chaotic map is introduced, which achieves copyright authentication for double images simultaneously and is more robust than previous schemes.
- FM-ViT: Flexible Modal Vision Transformers for Face Anti-Spoofing106
Experiments demonstrate that the single model trained based on FM-ViT can not only flexibly evaluate different modal samples, but also outperforms existing single- modal frameworks by a large margin, and approaches the multi-modal frameworks introduced with smaller FLOPs and model parameters.
- Relation-Aware Pedestrian Attribute Recognition with Graph Convolutional Networks104
This paper proposes a new end-to-end network, named Joint Learning of Attribute and Contextual relations (JLAC), to solve the task of pedestrian attribute recognition, which includes two novel modules: Attribute Relation Module (ARM) and contextual Relation module (CRM).
- 104
- A computational approach to body mass index prediction from face images104
This work develops a computational method to predict the BMI from face images automatically, formulate the BMI prediction from facial features as a machine vision problem, and evaluates the approach on a large database with more than 14,500 face images.
- 102
- A survey on 3D mask presentation attack detection and countermeasures100
This work presents a comprehensive overview of the state-of-the-art approaches in 3D mask spoofing and anti-spoofing, including existing databases and countermeasures, and quantitatively compares the performance of differentMask spoofing detection methods on a common ground.
- 100
- A framework for joint estimation of age, gender and ethnicity on a large database98
It is found that the canonical correlation analysis (CCA) based methods can derive an extremely low dimensionality in estimating age, gender and ethnicity.
- End-to-End Human-Gaze-Target Detection with Transformers96
Unlike existing two-stage methods that require human head locations as input and can predict only one human's gaze target at a time, HGTTR can directly predict the locations of all people and their gaze targets at one time in an end-to-end manner.
- Ensemble similarity learning for kinship verification from facial images in the wild96
Experiments results demonstrate that the proposed Ensemble similarity learning (ESL) method is superior to some state-of-the-art methods in terms of both verification rate and computational efficiency.
- 92
- 90
- Pale Transformer: A General Vision Transformer Backbone with Pale-Shaped Attention89
A Pale-Shaped self-Attention (PS-Att attention) is proposed, which performs self-attention within a pale-shaped region and can reduce the computation and memory costs significantly and capture richer contextual information under the similar computation complexity with previous local self-ATTention mechanisms.
- Cross‐ethnicity face anti‐spoofing recognition challenge: A review88
An overview of the Chalearn Face Anti-spoofing Attack Detection Challenge, including its design, evaluation protocol and a summary of results is presented, which analyzed the top ranked solutions and drew conclusions derived from the competition.
- 86
- 85
- 84
- 84
- 83
- CR-Net: A Deep Classification-Regression Network for Multimodal Apparent Personality Analysis79
A deep Classification-Regression Network (CR-Net) is presented for analyzing the Big Five personality problem and further assisting on job interview recommendation in a first impressions setup, which can obtain accurate predictions for both personality traits and interview recommendation.
- 79
- Joint Face Image Restoration and Frontalization for Recognition75
Qualitative and quantitative experiments demonstrate the superiority of MDFR over state-of-the-art methods on both face frontalization and face restoration and can generate frontalized high-quality face images by a single unified network, showing a strong capability of preserving face identity.
- 3D Face Anti-Spoofing With Factorized Bilinear Coding75
This work proposes a novel anti-spoofing method, based on factorized bilinear coding of multiple color channels (namely MC\_FBC), that achieves the state-of-the-art performance on both the authors' own WFFD and other face spoofing databases under various intra-database and inter-database testing scenarios.
- 75
- Learning deep compact similarity metric for kinship verification from face images74
This work proposes a new kinship metric learning (KML) method with a coupled deep neural network (DNN) model, and introduces the property of hierarchical compactness into the coupled network to facilitate deep metric learning with limited amount of kinship training data.
- 73
- 69
- 67
- 65
- 65
- EAN: Event Adaptive Network for Enhanced Action Recognition64
A unified action recognition framework to investigate the dynamic nature of video content by introducing the following designs, called the proposed framework as Event Adaptive Network because both key designs are adaptive to the input video content.
- Image-to-Video Generation via 3D Facial Dynamics62
This paper proposes to “imagine” a face video from a single face image according to the reconstructed 3D face dynamics, aiming to generate a realistic and identity-preserving face video, with precisely predicted pose and facial expression.
- 62
- 61
- 61
- 59
- Bayesian Optimized 1-Bit CNNs58
This paper proposes a novel approach, called Bayesian optimized 1-bit CNNs (denoted as BONNs), taking the advantage of Bayesian learning, a well-established strategy for hard problems, to significantly improve the performance of extreme 1- bit CNNs.
- 57
- 57
- 56
- Optimal local community detection in social networks based on density drop of subgraphs56
A novel algorithm which can output an optimal set of local communities automatically based on the Max-Flow Min-Cut theorem is proposed and validated through a variety of data sets ranging from synthetic graphs to real world benchmark data sets.
- Gender from Body: A Biologically-Inspired Approach with Manifold Learning56
This paper proposes to use the biologically-inspired features in combination with manifold learning techniques to represent human body images for the purpose of gender recognition and proposes a new representation and classification framework.
- Benchmarking deep learning techniques for face recognition52
This work compares three deep learning frameworks and benchmark the performance of different CNN models on five GPU platforms to help researchers select appropriate face recognition models,Deep learning frameworks, GPU platforms, and training datasets for their face recognition tasks.
- 52
- Q-DETR: An Efficient Low-Bit Quantized Detection Transformer51
This paper forms the DRD as a bi-level optimization problem, which can be derived by generalizing the information bottleneck (IB) principle to the learning of Q-DETR, and introduces a new foreground-aware query matching scheme to effectively transfer the teacher information to distillation-desired features to minimize the conditional information entropy.
- 51
- 51
- 50
- Cascaded Split-and-Aggregate Learning with Feature Recombination for Pedestrian Attribute Recognition49
A unified framework, named CAScaded Split-and-Aggregate Learning with Feature Recombination (CAS-SAL-FR), to learn the above modules jointly and concurrently achieves new state-of-the-art performance.
- 46
- GINet: Graph Interaction Network for Scene Parsing45
This work explores how to incorporate the linguistic knowledge to promote context reasoning over image regions by proposing a Graph Interaction unit (GI unit) and a Semantic Context Loss (SC-loss).
- Fusing Multiple Features for Depth-Based Action Recognition45
Experimental results show that the four different features investigated in the article can complement each other, and appropriate fusion methods can improve the recognition accuracies significantly over each individual feature.
- 45
- 3D High-Fidelity Mask Face Presentation Attack Detection Challenge44
An overview of the 3D High-Fidelity Mask Face Presentation Attack Detection Challenge, introducing and analyzing the top ranking algorithms, the conclusion summary, and the research ideas for mask attack detection provided by this competition are presented.
- Self-Conditioned Probabilistic Learning of Video Rescaling43
A self-conditioned probabilistic framework for video rescaling to learn the paired downscaling and upscaling procedures simultaneously, and extends the framework to a lossy video compression system, in which a gradient estimator for non-differential industrial lossy codecs is proposed for the end-to-end training of the whole system.
- Deeply-learned Hybrid Representations for Facial Age Estimation43
A novel unified network named Deep Hybrid-Aligned Architecture for facial age estimation that contains global, local and global-local branches, which are jointly optimized and thus can capture multiple types of features with complementary information.
- Coarse-to-Fine Cascaded Networks with Smooth Predicting for Video Facial Expression Recognition42
The Coarse-to-Fine Cascaded network with Smooth Predicting (CFC-SP) is proposed to improve the performance of facial expression recognition and achieved 3rd place in the Expression Classification Challenge of the 3rd Competition on Affective Behavior Analysis in-the-wild.
- Fast single image dehazing based on a regression model42
Experimental results demonstrate that the proposed approach has a lower computational complexity, and the dehazing results are visually appealing even on extremely challenging photos, such as street views, thick fog, and sky regions.
- 41
- 41
- On Applicability of Tunable Filter Bank Based Feature for Ear Biometrics: A Study from Constrained to Unconstrained39
Tunable filter moderately succeeds to distinguish ear features at par with the state-of-the-art features used for ear recognition, indicating that tunable filter is a candidate for recognizing human from ear images.
- Human Age Estimation and Sex Classification39
In this chapter, a detailed introduction of the computational approaches to human age estimation and sex classification will be given, and various methods for feature extraction and learning will be described.
- 38
- 37
- ChaLearn Looking at People: IsoGD and ConGD Large-Scale RGB-D Gesture Recognition37
This article proposes a bidirectional long short-term memory (Bi-LSTM) method, determining video division points based on skeleton points, and introduces the corrected segmentation rate (CSR) metric to evaluate the performance of temporal segmentation for continuous gesture recognition.
- On visual BMI analysis from facial images37
The studies provide some deep insights into the facial representations for visual BMI analysis: the deep model based methods perform better than geometry based methods and the Arcface, VGG-Face and PIGF are more robust than the others to head pose variations.
- 37
- 36
- A System for Automatic Iris Capturing36
Iris recognition provides the greatest accuracy among known biometrics, and usually the users need to adjust their eye positions for iris image acquiasion.
- NTIRE 2022 Challenge on Stereo Image Super-Resolution: Methods and Results35
The 1st NTIRE challenge on stereo image super-resolution (restoration of rich details in a pair of low-resolution stereo images) with a focus on new solutions and results establishes a new benchmark for stereo image SR.
- TRQ: Ternary Neural Networks With Residual Quantization35
A stem-residual framework which provides new insight into Ternary quantization, termed Residual Quantization (TRQ), to achieve more powerful TNNs and yields great recognition accuracy while being accelerated.
- 35
- 34
- 33
- 31
- 31
- 31
- 29
- 29
- 28
- 28
- 28
- 28
- 28
- Multi-human Parsing with a Graph-based Generative Adversarial Model27
A novel multi- human parsing model named MH-Parser is introduced, which uses a graph-based generative adversarial model to address the challenges of close-person interaction and occlusion in multi-human parsing.
- 26
- 26
- 24
- 24
- 24
- 24
- 24
- Learning Large Euclidean Margin for Sketch-based Image Retrieval.24
A novel loss function, named Euclidean Margin Softmax (EMS), is proposed that not only minimizes intra-class distances but also maximizes inter- class distances simultaneously simultaneously, enabling us to learn a feature space with high discriminability, leading to highly accurate retrieval.
- 24
- 23
- 23
- 23
- 23
- 23
- 22
- 22
- 22
- 21
- 21
- 21
- 19
- 18
- 18
- Domain-Aware SE Network for Sketch-based Image Retrieval with Multiplicative Euclidean Margin Softmax17
A Domain-Aware Squeeze-and-Excitation (DASE) network is presented, which seamlessly incorporates the prior knowledge of sample sketch or photo into SE module and make the SE module capable of emphasizing appropriate channels according to domain signal.
- 16
- 16
- 16
- 16
- 15
- 15
- 14
- 14
- 14
- 14
- 14
- 14
- 14
- 14
- 13
- 13
- 13
- 13
- 13
- 12
- 12
- 12
- 12
- 12
- 12
- 12
- 11
- 11
- 10
- 10
- 10
- 10
- 10
- 9
- 9
- 9
- 9
- 9
- 9
- 9
- 9
- 8
- 8
- 8
- 8
- 8
- 7
- GazeGAN: A Generative Adversarial Saliency Model based on Invariance Analysis of Human Gaze During Scene Free Viewing.7
A novel saliency model based on generative adversarial network (dubbed GazeGAN) is introduced, which combines classic skip connections with a novel center-surround connection in order to leverage multi level features, and a histogram loss based on Alternative Chi Square Distance (ACS HistLoss) is proposed to refine the saliency map in terms of luminance distribution.
- 7
- 7
- 7
- 7
- 7
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- Leverage eye-movement data for saliency modeling: Invariance Analysis and a Robust New Model4
A novel saliency model based on generative adversarial network (dubbed GazeGAN) is introduced, which combines classic skip connections with a novel center-surround connection in order to leverage multi level features, and a histogram loss based on Alternative Chi Square Distance (ACS HistLoss) is proposed to refine the saliency map in terms of luminance distribution.
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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.