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
- Stan Ziqing LiSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works76 from public data
- 1,147
- 1,137
- S^3FD: Single Shot Scale-Invariant Face Detector693
This paper presents a real-time face detector, named Single Shot Scale-invariant Face Detector (S3FD), which performs superiorly on various scales of faces with a single deep neural network, especially for small faces.
- Embedding Deep Metric for Person Re-identification: A Study Against Large Variations313
A novel moderate positive sample mining method to train robust CNN for person re-identification, dealing with the problem of large variation is proposed and the learning by a metric weight constraint is improved, so that the learned metric has a better generalization ability.
- FaceBoxes: A CPU real-time face detector with high accuracy298
This work proposes a novel face detector, named FaceBoxes, with superior performance on both speed and accuracy, and proposes a new anchor densification strategy to make different types of anchors have the same density on the image, which significantly improves the recall rate of small faces.
- Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognition281
A solution, named DMUE, is proposed to address the problem of annotation ambiguity from two perspectives: the latent Distribution Mining and the pairwise Uncertainty Estimation.
- A Dataset and Benchmark for Large-Scale Multi-Modal Face Anti-Spoofing208
A large-scale multi-modal dataset, namely CASIA-SURF, is introduced, which is the largest publicly available dataset for face anti-spoofing in terms of both subjects and visual modalities and a new multi- modal fusion method is presented, which performs feature re-weighting to select the more informative channel features while suppressing the less useful ones for each modal.
- Mis-Classified Vector Guided Softmax Loss for Face Recognition189
This paper develops a novel loss function, which adaptively emphasizes the mis-classified feature vectors to guide the discriminative feature learning and is the first attempt to inherit the advantages of feature margin and feature mining into a unified loss function.
- Multi-view subspace clustering with intactness-aware similarity182
A novel multi-view subspace clustering model that attempts to form an informative intactness-aware similarity based on the intact space learning technique is proposed and its superior performance over other state-of-the-art alternatives is revealed.
- CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-Identification174
This paper systematically study the manually designed architectures, and identifies that appropriately separating Batch Normalization layers is the key to bring a great boost towards cross-modality matching, and proposes a novel method, named Cross-Modality Neural Architecture Search (CM-NAS).
- The Elements of End-to-end Deep Face Recognition: A Survey of Recent Advances165
This survey article presents a comprehensive review about the recent advance of each element of the end-to-end deep face recognition, since the thriving deep learning techniques have greatly improved their capability of them.
- ScratchDet: Training Single-Shot Object Detectors From Scratch141
The ScratchDet achieves the state-of-the-art accuracy on PASCAL VOC 2007, 2012 and MS COCO among all the train-from-scratch detectors and even performs better than several one-stage pretrained methods.
- 140
- FaceX-Zoo124
A novel open-source project, named FaceX-Zoo, which is constructed with modular and scalable design, and oriented to the academic and industrial community of face-related analysis, to help the community to easily build stateof-the-art solutions for deep face recognition.
- 119
- A New Dataset and Boundary-Attention Semantic Segmentation for Face Parsing95
A simple yet effective Boundary-Attention Semantic Segmentation (BASS) method is proposed for face parsing, which contains a three-branch network with elaborately developed loss functions to fully exploit the boundary information.
- 76
- Edge-Aware Graph Representation Learning and Reasoning for Face Parsing72
This work proposes to model and reason the region-wise relations by learning graph representations, and leverage the edge information between regions for optimized abstraction, and encodes a facial image onto a global graph representation where a collection of pixels with similar features are projected to each vertex.
- 66
- Large-Scale Bisample Learning on ID Versus Spot Face Recognition57
To tackle the bisample problem with only two samples for each class, a classification–verification–classification training strategy is proposed to progressively enhance the IvS performance, and a dominant prototype softmax is incorporated to make the deep learning scalable on large-scale classes.
- Single-Shot Scale-Aware Network for Real-Time Face Detection51
This work proposes a scale-aware detection network using a wide scale range of layers associated with appropriate scales of anchors to handle faces with various scales, and describes a new equal density principle to ensure anchors with different scales to be evenly distributed on the image.
- Dual Spoof Disentanglement Generation for Face Anti-Spoofing With Depth Uncertainty Learning49
A lightweight Depth Uncertainty Module (DUM), which alleviates the adverse effects of noisy samples by depth uncertainty learning, developed without extra-dependency, thus can be flexibly integrated with any depth supervised network for face anti-spoofing.
- 47
- C2RL: Content and Context Representation Learning for Gloss-Free Sign Language Translation and Retrieval39
This paper introduces an innovative pretraining paradigm for gloss-free SLRL, called C2RL, and confirms that the joint optimization of ICL and ECL results in robust sign language representation and significant performance gains in gloss-free SLT and SLRet tasks.
- 38
- AGRNet: Adaptive Graph Representation Learning and Reasoning for Face Parsing37
An adaptive and differentiable graph abstraction method to represent the components on a graph via pixel-to-vertex projection under the initial condition of a predicted parsing map, where pixel features within a certain facial region are aggregated onto a vertex.
- Introduction to the Special Issue on Trustworthy Multimedia Computing and Applications in Urban Scenes36
The goal of this special issue (SI) is to encourage a collaborative endeavor to explore the possibilities and obstacles associated with trustworthy multimedia analysis and gather inventive approaches, systems, and applications focused on trustworthy multimedia computing and its applications in urban environments.
- Detecting Face with Densely Connected Face Proposal Network35
This work proposes a novel face detector, dubbed the Densely Connected Face Proposal Network (DCFPN), with high performance as well as real-time speed on the CPU devices, and uses the dense anchor strategy and a fair L1 loss function to handle small faces well.
- FasterPose: A Faster Simple Baseline for Human Pose Estimation32
This article proposes a design paradigm for cost-effective network with LR representation for efficient pose estimation, named FasterPose, and forms a novel regressive cross-entropy (RCE) loss function for accelerating the convergence and promoting the accuracy.
- 32
- 30
- Metric Embedded Discriminative Vocabulary Learning for High-Level Person Representation30
A metric embedded discriminative vocabulary learning for high-level person representation with application to person re-identification and a new and effective term is introduced which aims at making the same persons closer while different ones farther in the metric space.
- Semi-Siamese Training for Shallow Face Learning29
Extensive experiments on various benchmarks of face recognition show the proposed method significantly improves the training, not only in shallow face learning, but also for conventional deep face data.
- 28
- Grand Challenge of 106-Point Facial Landmark Localization27
A challenging dataset, named JD-landmark, which covers large variations on pose and expression, which brings a lot of difficulties to predict accurate landmarks, and holds a 106-point facial landmark localization competition on this dataset in conjunction with IEEE International Conference on Multimedia and Expo 2019.
- Boosting Semi-Supervised Face Recognition With Noise Robustness26
A multi-agent method, named GroupNet (GN), is introduced to endow the semi-supervised face recognition solution with the ability to identify the wrongly-labelled samples and preserve the clean samples, and it is shown that GN alone achieves the leading accuracy in traditional supervised face recognition even when the noisy labels take over 50% of the training data.
- ScratchDet: Exploring to Train Single-Shot Object Detectors from Scratch.24
The ScratchDet achieves the state-of-the-art accuracy on PASCAL VOC 2007, 2012 and MS COCO among all the train-from-scratch detectors and even performs better than several one-stage pretrained methods.
- 22
- Total astragalosides promote oligodendrocyte precursor cell differentiation and enhance remyelination in cuprizone-induced mice through suppression of Wnt/β-catenin signaling pathway21
It is clarified that TA could effectively enhance the differentiation and maturation of OPCs and accelerate remyelination in CPZ-induced mice through inhibition of Wnt/β-catenin signaling pathway.
- 18
- Trends and Controversies17
The development of automata able to work effectively in conditions that are currently confined to visual surveillance, so called “recognition-in-the-wild,” is the development of automata able to work effectively in conditions that are currently confined to visual surveillance.
- 15
- ChatEdit: Towards Multi-turn Interactive Facial Image Editing via Dialogue14
This paper introduces the ChatEdit benchmark dataset for evaluating image editing and conversation abilities in this context and presents a novel baseline framework that integrates a dialogue module for both tracking user requests and generating responses and an image editing module for image editing.
- NPCFace: A Negative-Positive Cooperation Supervision for Training Large-scale Face Recognition.13
A novel Negative-Positive Cooperation loss, named NPCFace, is formulated, which emphasizes the training on both the negative and positive hard cases via a cooperative-margin mechanism in the softmax logits, and also brings better interpretation of negative-positive hardness correlation.
- 12
- 12
- 11
- 11
- CASIA-SURF: A Dataset and Benchmark for Large-scale Multi-modal Face Anti-spoofing.10
This work introduces a large-scale multi-modal dataset, namely CASIASURF, which is the largest publicly available dataset for face anti-spoofing both in terms of subjects and visual modalities and presents a new multimodal fusion method as a strong baseline.
- Rethink and Redesign Meta learning10
This paper rethink the meta-learning algorithm and presents a novel paradigm of meta-learning approach with three developments to introduce attention mechanism and past knowledge step by step to improve the performance of meta-learning, and the TOF problem can be reduced.
- Dual-Structure Disentangling Variational Generation for Data-Limited Face Parsing8
A novel Dual-Structure Disentangling Variational Generation (D2VG) network is proposed, Benefiting from the interpretable factorized latent disentanglement in VAE, D2VG can learn a joint structural distribution of facial image and its corresponding parsing map and introduces a coarseness-tolerant learning algorithm to effectively handle these noisy or uncertain labels.
- Meta Anti-spoofing: Learning to Learn in Face Anti-spoofing.8
The proposed Meta-FAS addresses the above-mentioned problems by training the classifiers how to learn to detect the spoofing faces with few examples by implementing a novel face anti-spoofing approach via meta-learning named Meta Face Anti- Spoofing (Meta-Fas).
- 8
- Learning Discriminative Features with Class Encoder8
The supervised information is incorporated to propose a novel formulation, namely class-encoder, whose training objective is to reconstruct a sample from another one of which the labels are identical, whose performance on benchmarks of classification and face recognition is improved.
- 7
- ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model6
This work proposes ROSE, a Revolutionary Open-set dense SEgmentation LMM, which enables dense mask prediction and open-category generation through patch-wise perception, and introduces a conversation-based refinement paradigm, integrating the prediction result from previous step with textual prompt for revision.
- 5
- Multi-Agent Semi-Siamese Training for Long-Tail and Shallow Face Learning5
The theoretical and empirical analysis is given that, given the long-tail (or shallow) data and training loss, MASST smooths the loss landscape and satisfies the Lipschitz continuity with the help of multiple agents and the updating gallery queue.
- 4
- 3
- Thinker: A vision-language foundation model for embodied intelligence2
This work proposes Thinker, a large vision-language foundation model designed for embodied intelligence, and introduces a simple yet effective approach that substantially enhances the model's capacity for video comprehension by jointly incorporating key frames and full video sequences as inputs.
- 2
- 2
- One-stage Context and Identity Hallucination Network2
A novel one-stage context and identity hallucination network, which learns a series of hallucination maps to softly divide the context areas and identity areas and designs a novel two-cascading AdaIN to transfer the identity while retaining the context.
- 1
- GoHD: Gaze-oriented and Highly Disentangled Portrait Animation with Rhythmic Poses and Realistic Expressions1
Extensive experiments validate GoHD's advanced generalization capabilities, demonstrating its effectiveness in generating realistic talking face results on arbitrary subjects.
- 1
- 1
- –
- GoHD: Gaze-oriented and Highly Disentangled Portrait Animation with Rhythmic Poses and Realistic Expression–
Extensive experiments validate GoHD's advanced generalization capabilities, demonstrating its effectiveness in generating realistic talking face results on arbitrary subjects.
- –
- An Empirical Study of Self-Described Texts of Open Source Projects and Their Attention Levels–
It is proved that the amount of original knowledge and the amount of introduced knowledge are positively correlated with user attention, and the knowledge classification in the presentation of the text can effectively improve user recognition, while there may be a U-shaped relationship between the degree of systematization of the text knowledge and user recognition.
- –
- Scale Attention for Learning Deep Face Representation: A Study Against Visual Scale Variation–
This work reform the conv layer by resorting to the scale-space theory, and achieves two-fold facilities, which accomplish the hierarchical scale attention by stacking the reformed layers, building a novel style named SCAN-CNN.
- –
- Research on Trajectory Planning Technology of Coordinate Measuring Robot–
The correctness and feasibility of the principle of trajectory planning are verified in this paper, which lays a foundation for the next work on coordinate measuring robot.
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.