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
- Guangyou XuSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works170 from public data
- CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition676
This work proposes a novel Adaptive Curriculum Learning loss (CurricularFace) that embeds the idea of curriculum learning into the loss function to achieve a novel training strategy for deep face recognition, which mainly addresses easy samples in the early training stage and hard ones in the later stage.
- Towards Optimal Structured CNN Pruning via Generative Adversarial Learning585
This paper proposes an effective structured pruning approach that jointly prunes filters as well as other structures in an end-to-end manner and effectively solves the optimization problem by generative adversarial learning (GAL), which learns a sparse soft mask in a label-free and an end to end manner.
- DSFD: Dual Shot Face Detector506
A novel detection network named Dual Shot face Detector (DSFD) is proposed which inherits the architecture of SSD and introduces a Feature Enhance Module (FEM) for transferring the original feature maps to extend the single shot detector to dual shot detector.
- Rethinking Counting and Localization in Crowds: A Purely Point-Based Framework436
This paper proposes a purely point-based framework for joint crowd counting and individual localization, called Point to Point Network (P2PNet), and proposes a new metric, called density Normalized Average Precision (nAP), to provide more comprehensive and more precise performance evaluation.
- 432
- Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking382
The two major novelties: chained structure and paired attentive regression, make CTracker simple, fast and effective, setting new MOTA records on MOT16 and MOT17 challenge datasets (67.6 and 66.6, respectively), without relying on any extra training data.
- 368
- Dual-level Collaborative Transformer for Image Captioning366
A novel Dual-Level Collaborative Transformer (DLCT) network is introduced to realize the complementary advantages ofriptive region features extracted by object detection networks and address the semantic noises caused by the direct fusion of these two features.
- Learning Salient Boundary Feature for Anchor-free Temporal Action Localization329
This paper proposes the first purely anchor-free temporal localization method, which is both efficient and effective, and beats all anchor-based and actionness-guided methods with a remarkable margin on THUMOS14, achieving state-of-the-art results, and comparable ones on ActivityNet v1.3.
- 315
- 279
- 276
- TEINet: Towards an Efficient Architecture for Video Recognition275
The proposed TEINet can achieve a good recognition accuracy on these datasets but still preserve a high efficiency, and is able to capture temporal structure flexibly and effectively, but also efficient for model inference.
- Accelerating Convolutional Networks via Global & Dynamic Filter Pruning274
This paper proposes a novel global & dynamic pruning (GDP) scheme to prune redundant filters for CNN acceleration that achieves superior performance to accelerate several cutting-edge CNNs on the ILSVRC 2012 benchmark.
- 261
- Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization244
An attention convolutional binary neural tree architecture is presented to address problems for weakly supervised Fine-grained visual categorization and uses the attention transformer module to enforce the network to capture discriminative features.
- Spatiotemporal Inconsistency Learning for DeepFake Video Detection241
A novel temporal modeling paradigm in TIM is presented by exploiting the temporal difference over adjacent frames along with both horizontal and vertical directions and the ISM simultaneously utilizes the spatial information from SIM and temporal information from TIM to establish a more comprehensive spatial-temporal representation.
- Arbitrary Style Transfer via Multi-Adaptation Network229
The proposed multi-adaptation network leads to better results than the state-of-the-art style transfer methods and enables main style patterns and exact content structures to adapt to various input images, respectively.
- Fast Learning of Temporal Action Proposal via Dense Boundary Generator228
An efficient and unified framework to generate temporal action proposals named Dense Boundary Generator (DBG), which draws inspiration from boundary-sensitive methods and implements boundary classification and action completeness regression for densely distributed proposals.
- Learning by Analogy: Reliable Supervision From Transformations for Unsupervised Optical Flow Estimation218
This work twists the general unsupervised learning pipeline by running another forward pass with transformed data from augmentation, along with using transformed predictions of original data as the self-supervision signal, and introduces a lightweight network with multiple frames by a highly-shared flow decoder.
- HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping173
This work proposes 3D shape-aware identity to control the face shape with the geometric supervision from 3DMM and 3D face reconstruction method and introduces the Semantic Facial Fusion module to optimize the combination of encoder and decoder features and make adaptive blending, which makes the results more photo-realistic.
- Asymmetric Co-Teaching for Unsupervised Cross-Domain Person Re-Identification172
An asymmetric co-teaching framework, which resists noisy labels by cooperating two models to select data with possibly clean labels for each other, which can consistently benefit most clustering based methods, and boost the state-of-the-art adaptation accuracy.
- Toward an Expert Level of Lung Cancer Detection and Classification Using a Deep Convolutional Neural Network167
The three-dimensional convolutional neural network described in this article demonstrated both high sensitivity and high specificity in classifying pulmonary nodules regardless of diameters as well as superiority compared with manual assessment.
- Image-to-image Translation via Hierarchical Style Disentanglement165
Hierarchical Style Disentanglement is proposed, which organizes the labels into a hierarchical tree structure, in which independent tags, exclusive attributes, and disentangled styles are allocated from top to bottom.
- Face Anti-Spoofing via Disentangled Representation Learning157
A novel perspective of face anti-spoofing is proposed that disentangles the liveness features and content features from images, and theLiveness features is further used for classification, and a Convolutional Neural Network architecture is put forward.
- Transformers in computational visual media: A survey143
This study comprehensively surveys recent visual transformer works and focuses on visual transformer methods in low-level vision and generation, which use a self-attention mechanism rather than the RNN sequential structure.
- Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression143
KSE is capable of simultaneously compressing each layer in an efficient way, which is significantly faster compared to previous data-driven feature map pruning methods, and significantly outperforms state-of-the-art methods.
- Learning Dynamic Alignment via Meta-filter for Few-shot Learning134
This paper proposes to learn a dynamic alignment, which can effectively highlight both query regions and channels according to different local support information and facilitates dynamical knowledge adaptation for few-shot learning.
- Generalizable Representation Learning for Mixture Domain Face Anti-Spoofing127
This work designs a domain feature based on Instance Normalization and proposes a domain representation learning module (DRLM) to extract discriminative domain features for clustering and designs a generalizable face anti-spoofing with meta-learning to enhance the interpretability through visualization.
- Attention-based Multi-Patch Aggregation for Image Aesthetic Assessment122
A novel multi-patch aggregation method for image aesthetic assessment using an attention-based mechanism that adaptively adjusts the weight of each patch during the training process to improve learning efficiency and outperforms existing methods by a large margin.
- Transformer-based Dual Relation Graph for Multi-label Image Recognition120
This paper proposes a novel Transformer-based Dual Relation learning framework, constructing complementary relationships by exploring two aspects of correlation, i.e., structural relation graph and semantic relation graph, which aims to capture long-range correlations from object context by developing a cross-scale transformer-based architecture.
- Adaptive Normalized Representation Learning for Generalizable Face Anti-Spoofing118
A novel perspective of face anti-spoofing that focuses on the normalization selection in the feature extraction process is proposed, which adaptively selects feature normalization methods according to the inputs, aiming to learn domain-agnostic and discriminative representation.
- 116
- 115
- Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning115
Self-supervised learning has shown great potentials in improving the video representation ability of deep neural networks by getting supervision from the data itself, but some of the current methods tend to cheat from the background, so this work proposes to remove the background impact by adding the background.
- Fast and Accurate Neural Word Segmentation for Chinese106
This paper proposes a greedy neural word segmenter with balanced word and character embedding inputs to alleviate the existing drawbacks of current neural models, capable of performing segmentation much faster and even more accurate than state-of-the-art neural models on Chinese benchmark datasets.
- Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization100
A two-stage approach, termed structure-preserving activation (SPA), toward fully leveraging the structure information incorporated in convolutional features for WSOL by utilizing the high-order self-correlation (HSC) to extract the inherent structural information retained in the learned model and then aggregate HSC of multiple points for precise object localization.
- Viewpoint-Aware Loss with Angular Regularization for Person Re-Identification100
This work proposes a novel approach to viewpoint-aware adaptive label smoothing regularization (VALSR) that assigns the adaptive soft label to feature representation and demonstrates that it outperforms the state-of-the-art supervised Re-ID methods.
- 99
- 97
- Towards Highly Accurate and Stable Face Alignment for High-Resolution Videos82
A Fractional Heatmap Regression (FHR) for high-resolution video-based face alignment and a novel stabilization loss that contains two terms to address time delay and non-smooth issues, respectively are proposed.
- Towards Optimal Fine Grained Retrieval via Decorrelated Centralized Loss with Normalize-Scale Layer79
A novel metric learning scheme, termed Normalize-Scale Layer and Decorrelated Global Centralized Ranking Loss, which achieves extremely efficient and discriminative learning, i.e., 5× speedup over triplet loss and 12% recall boost on CARS196.
- 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.
- Delving into Data: Effectively Substitute Training for Black-box Attack73
A novel perspective substitute training that focuses on designing the distribution of data used in the knowledge stealing process and the combination of these two modules can further boost the consistency of the substitute model and target model, which greatly improves the effectiveness of adversarial attack.
- Network Pruning Using Adaptive Exemplar Filters71
Inspired by the face recognition community, a message-passing algorithm Affinity Propagation on the weight matrices is used to obtain an adaptive number of exemplars, which then act as the preserved filters, resulting in an automatic and efficient pruning approach called EPruner.
- Adversarial Semantic Data Augmentation for Human Pose Estimation69
Semantic Data Augmentation (SDA), a method that augments images by pasting segmented body parts with various semantic granularity, is proposed, which exploits a generative network to dynamiclly predict tailored pasting configuration.
- Centralized Ranking Loss with Weakly Supervised Localization for Fine-Grained Object Retrieval66
A novel centralized ranking loss (CRL) is introduced, which achieves a very efficient (1,000times training speedup comparing to the triplet loss) and discriminative feature learning by a ?
- Towards Lightweight Transformer Via Group-Wise Transformation for Vision-and-Language Tasks65
WL-Transformer applies Group-wise Transformation to reduce both the parameters and computations of Transformer, while also preserving its two main properties, i.e., the efficient attention modeling on diverse subspaces of MHA, and the expanding-scaling feature transformation of FFN.
- 65
- Adversarial Attribute-Image Person Re-identification65
This work conducted extensive experiments on three attribute datasets and demonstrated that the regularized adversarial modelling is so far the most effective method for the attribute-image cross-modality person Re-ID problem.
- Learning Semantic Neural Tree for Human Parsing63
A novel semantic neural tree for human parsing is designed, which uses a tree architecture to encode physiological structure of human body, and designs a coarse to fine process in a cascade manner to generate accurate results.
- 63
- Improving Face Recognition from Hard Samples via Distribution Distillation Loss63
This work proposes a novel Distribution Distillation Loss to narrow the performance gap between easy and hard samples, which is a simple, effective and generic for various types of facial variations.
- Lifelong Person Re-identification by Pseudo Task Knowledge Preservation61
This work casts LReID as a domain adaptation problem and proposes a pseudo task knowledge preservation framework to alleviate the task-wise domain gap, and proposes to preserve knowledge on extra pseudo tasks which jointly distills knowledge and discriminates identity.
- Semi-Supervised Adversarial Monocular Depth Estimation57
This paper proposes a semi-supervised adversarial learning framework that only utilizes a small number of image-depth pairs in conjunction with a large number of easily-available monocular images to achieve high performance.
- Automatic script identification in the wild57
A large-scale dataset with a great quantity of natural images and 10 types of widely-used languages is constructed and a deep learning based algorithm is proposed for script identification at word or line levels in natural scenes.
- 53
- Harnessing Synthesized Abstraction Images to Improve Facial Attribute Recognition52
This paper builds a dual-path facial attribute recognition network to utilize features from the original face images and facial abstraction images to improve facial attributes recognition, especially the attributes located on small face regions.
- NOH-NMS51
This work proposes \heatmapname (\heatmapnameshort ), which pinpoints the objects nearby each proposal with a Gaussian distribution, together with \nmsname, which dynamically eases the suppression for the space that might contain other objects with a high likelihood.
- 50
- 50
- 49
- 49
- Black-Box Dissector: Towards Erasing-Based Hard-Label Model Stealing Attack47
A novel hard-label model stealing method termed \emph{black-box dissector}, which consists of two erasing-based modules that utilizes soft labels from the substitute model to mitigate overfitting and promotes other downstream tasks, including transfer adversarial attacks.
- 40
- Dense Auto-Encoder Hashing for Robust Cross-Modality Retrieval40
This paper proposes a novel cross-modality hashing scheme, termed Dense Auto-encoder Hashing (DAH), which can explicitly impute the missed modality and produce robust binary codes by leveraging the relatedness among different modalities.
- 38
- UWSOD: Toward Fully-Supervised-Level Capacity Weakly Supervised Object Detection37
The proposed UWSOD achieves competitive results with the state-of-the-art WSOD methods while not requiring external modules or additional supervision, and the upper-bound performance of UWSOD with class-agnostic ground-truth bounding boxes approaches Faster R-CNN, which demonstrates UWSOD has fully-supervised-level capacity.
- Revisiting Image Aesthetic Assessment via Self-Supervised Feature Learning37
This paper designs two novel pretext tasks to identify the types and parameters of editing operations applied to synthetic instances and adapt them for a one-layer linear classifier to evaluate the performance in terms of binary aesthetic classification.
- NTIRE 2021 Challenge on Video Super-Resolution36
This paper presents evaluation results from two competition tracks as well as the proposed solutions to the NTIRE 2021 Challenge on Video Super-Resolution, and develops conventional video SR methods focusing on the restoration quality.
- Learning to Aggregate and Personalize 3D Face from In-the-Wild Photo Collection36
A novel Learning to Aggregate and Personalize (LAP) framework for unsupervised robust 3D face modeling that recovers superior or competitive face shape and texture compared with state-of-the-art (SOTA) methods with or without prior and supervision.
- Temporal Distinct Representation Learning for Action Recognition36
This paper designs a sequential channel filtering mechanism, i.e., Progressive Enhancement Module (PEM), to excite the discriminative channels of features from different frames step by step to avoid repeated information extraction and achieves visible improvements over the best competitor by 2.4% and 1.3%, respectively.
- Multi-modal Multi-layer Fusion Network with Average Binary Center Loss for Face Anti-spoofing33
A novel Multi-modal Multi-layer Fusion Convolutional Neural Network (mmfCNN), which targets at finding a discriminative model for recognizing the subtle differences between live and spoof faces, and utilizes a multi-layer fusion model to further aggregate the features from different layers.
- Variational Structured Semantic Inference for Diverse Image Captioning33
A Variational Structured Semantic Inferring model executed in a novel structured encoder-inferer-decoder schema that achieves significant improvements over the state-of-the-arts in image captioning.
- Deepwalk-aware graph convolutional networks29
A deepwalk strategy is introduced into GCNs to efficiently explore the global graph information and can complement the local neighborhood information of a graph, resulting in the more robust representation for the graph data.
- 29
- 28
- 27
- 27
- 27
- A Coarse-to-fine Pyramidal Model for Person Re-identification via Multi-Loss Dynamic Training.24
A novel coarse-to-fine pyramid model is proposed that not only incorporates local and global information, but also integrates the gradual cues between them that is able to match the cues at different scales and then search for the correct image of the same identity even when the image pair are not aligned.
- Ordinal Constrained Binary Code Learning for Nearest Neighbor Search24
A novel ranking-preserving hashing method, dubbed Ordinal Constraint Hashing (OCH), which efficiently learns the optimal hashing functions with a graph-based approximation to embed the ordinal relations through a small data set (such as clusters or random samples).
- ESPACE: Accelerating Convolutional Neural Networks via Eliminating Spatial and Channel Redundancy24
The first attempt of reducing spatial and channel redundancy directly from the visual input for CNNs acceleration is made, which demonstrates new state-of-the-art acceleration performance by a factor of 5.48* and 4.12* speedup on AlexNet and GoogLeNet, respectively.
- SSCGAN: Facial Attribute Editing via Style Skip Connections23
A style skip connection based generative adversarial network, referred to as SSCGAN, is developed which enables accurate facial attribute manipulation and can produce better results in terms of attribute generation accuracy and image quality.
- Supervised latent Dirichlet allocation with a mixture of sparse softmax23
This work embeds a mixture of softmax model into latent Dirichlet allocation model, and proposes a supervised topic model, supervised latent Diriclet allocation with a mixtureof softmax, and its improved version, supervised Latent Dirichlets allocation with an improved version of sparse softmax.
- 22
- Dense Scene Multiple Object Tracking with Box-Plane Matching22
The Box-Plane Matching method is proposed to improve the MOT performacne in dense scenes and achieve data association according to the motion similarity and appearance similarity between tracklets and detections.
- 22
- Rethinking Temporal Fusion for Video-Based Person Re-Identification on Semantic and Time Aspect22
A novel general temporal fusion framework to aggregate frame features on both semantic aspect and time aspect and a multi-stage fusion network is explored to fuse richer frame features at multiple semantic levels, which can effectively reduce the information loss caused by the traditional single- stage fusion.
- 22
- Architecture Disentanglement for Deep Neural Networks21
This paper introduces neural architecture disentanglement (NAD), which learns to disentangle a pre-trained DNN into sub-architectures according to independent tasks, forming information flows that describe the inference processes.
- Ask&Confirm: Active Detail Enriching for Cross-Modal Retrieval with Partial Query21
This work introduces the partial-query problem and extensively analyze its influence on text-based image retrieval, and proposes a novel retrieval framework that conducts the interactive process in an Ask-and-Confirm fashion, where AI actively searches for discriminative details missing in the current query, and users only need to confirm AI’s proposal.
- 21
- 21
- Data-driven face cartoon stylization21
This paper presents a data-driven framework for generating cartoon-like facial representations from a given portrait image by an optimization that simultaneously considers a desired artistic style, image-cartoon relationships of facial components as well as automatic adjustment of the image composition.
- Viewpoint Insensitive Action Recognition Using Envelop Shape21
This work proposes a representation named "Envelop Shape" which is viewpoint insensitive, easy to acquire from silhouettes using two orthogonal cameras, and contains enough discriminating features for action recognition.
- Detecting Adversarial Patch Attacks through Global-local Consistency20
This paper proposes a simple but very effective approach to detect adversarial patches based on an interesting observation called global-local consistency and proposes to use Random-Local-Ensemble strategy to further enhance it in the detection.
- 20
- Joint face alignment and segmentation via deep multi-task learning19
This work presents a joint multi-task learning algorithm for both face alignment and segmentation using deep convolutional neural network (CNN) and demonstrates the effectiveness of the model in two practical applications: virtual makeup and face swap.
- 17
- Elucidating the heterogeneity of prediabetes through subphenotyping with a two-dimensional tree structure16
The Discriminative Dimensionality Reduction Tree (DDRTree) algorithm is applied to explore prediabetes heterogeneity in 55,777 participants from the China Cardiometabolic Disease and Cancer Cohort (4C) study and elucidates the intricate dynamics of prediabetes progression, aiding in personalized management for prediabetes care.
- 15
- 15
- Frequency Consistent Adaptation for Real World Super Resolution13
A novel Frequency Consistent Adaptation (FCA) that ensures the frequency domain consistency when applying existing Super-Resolution methods to the real scene and improves the performance of the SR model under real-world setting achieving state-of-the-art results with high fidelity and plausible perception.
- 13
- 13
- 13
- Viewpoint Insensitive Posture Representation for Action Recognition13
It is proved from both theory and experiments that such representation, named “Envelop Shape”, is viewpoint insensitive and achieves an impressive distinguishable result under different viewpoints.
- 12
- Learning Comprehensive Motion Representation for Action Recognition12
A Comprehensive Motion Representation (CMR) learning method for action recognition, which achieves competitive performance on Something-Something V1 & V2 and Kinetics-400, and outperforms the current state-of-the-art on the temporal reasoning datasets Something- something V1 and V2.
- 12
- 11
- 11
- 11
- Similarity metric learning for face verification using sigmoid decision function11
The proposed face verification method is based on the idea that it would like the similarity between positive pairs larger than negative pairs, and obtain a similarity estimation of two images, and belongs to nonlinear metric which is more robust to handle heterogeneous data than linear metric.
- 10
- A Part Power Set Model for Scale-Free Person Retrieval10
An end-to-end part power set model with multi-scale features is proposed, which captures the discriminative parts of pedestrians from global to local, and from coarse to fine, enabling part-based scale-free person re-ID.
- 10
- 10
- Centroid-aware local discriminative metric learning in speaker verification10
To ensure learning efficiency against class-imbalance, the centroid-aware balanced boosting sampling is proposed to collect balanced mini-batch and to strengthen local discriminative modeling on the mini-batches, neighborhood component analysis (NCA) and magnet loss are adopted in ASV-specific modifications.
- 9
- Learning Efficient GANs using Differentiable Masks and co-Attention Distillation.9
A novel GAN compression method, termed DMAD, is introduced, by proposing a Differentiable Mask and a co-Attention Distillation that simultaneously distills informative attention maps from both the generator and discriminator of a pre-trained model to the searched generator, effectively stabilizing the adversarial training of the light-weight model.
- Interpretable Neural Network Decoupling9
A novel architecture decoupling method to interpret the network from a perspective of investigating its calculation paths, and introduces a novel architecture controlling module in each layer to encode the network architecture by a vector.
- 8
- Adversarial Refinement Network for Human Motion Prediction8
This work proposes an Adversarial Refinement Network (ARNet) following a simple yet effective coarse-to-fine mechanism with novel adversarial error augmentation, which outperforms other state-of-the-art methods, especially on challenging aperiodic actions in both short-term and long-term predictions.
- 8
- LSTC: Boosting Atomic Action Detection with Long-Short-Term Context7
This paper place the atomic action detection problem into a Long-Short Term Context (LSTC) to analyze how the temporalreliance among video signals affect the action detection results, and demonstrates that both temporal grains are beneficial to atomic action recognition.
- 7
- Accurate Depth-of-Field Rendering Using Adaptive Bilateral Depth Filtering7
This paper develops a new DoF filter, called adaptive bilateral depth filter, to adaptively postfilter the pixels according to their depth variance, which can generate adaptive high-quality DoF rendering effects dynamically, and can be fully implemented in GPU parallelization.
- 7
- 7
- 6
- 5
- 5
- 5
- 5
- Devil's in the Detail: Graph-based Key-point Alignment and Embedding for Person Re-ID4
An end-to-end ReID method that integrates both key recognition patterns into a unified framework, called Siamese-GCN, and achieves state-of-the-art performance on three public datasets is proposed.
- Exploring Language Prior for Mode-Sensitive Visual Attention Modeling4
A new probabilistic framework for attention is proposed, and the concept of mode is introduced to model the flexibility and adaptability of attention modulation in complex environments to convert an arbitrary learning-based backbone attention model to a more robust multi-mode version.
- 4
- 4
- Dynamic Neural Network Decoupling.4
A novel architecture decoupling method is proposed, which dynamically discovers the hierarchical path consisting of activated filters for each input image, and subsequently disentangles the filters by limiting the outputs of filter during training.
- Transformer-based models for predicting cardiovascular risk in Chinese adults: development and validation3
The transformer-based China-AIHeart models predicted 10-year CVD risk and outperformed traditional Cox-based approaches, providing a practical tool for risk stratification in Chinese adults.
- 3
- Data-driven phenotypic profiling of prediabetes reveals heterogeneous cardiometabolic risks in Chinese adults3
Incorporating phenotypic probabilities into multivariable models significantly improved the prediction of disease risks and delineation of distinct metabolic profiles enables refined risk stratification and informs precision prevention strategies.
- D-CAM: Learning Generalizable Weakly-Supervised Medical Image Segmentation from Domain-Invariant CAM3
- 3
- Distribution Distillation Loss: Generic Approach for Improving Face Recognition from Hard Samples3
This work proposes a novel Distribution Distillation Loss to narrow the performance gap between easy and hard samples, which is a simple, effective and generic for various types of facial variations.
- Evaluating the Quality of Face Alignment without Ground Truth3
This study aims to develop a method that can select an input image with good face alignment results from many results produced by a single method or multiple ones, which can enhance the overall performance of a face alignment method with a random strategy.
- Rio: a personal storage system in multi-device and cloud2
In the experiment, Rio, a personal storage system in multi-device and cloud storage is proposed, and users can store, retrieve and access data through RESTful URI, no matter in which device or cloud services data are stored.
- Animated construction of ink-wash paintings2
An effective solution for estimating an order given a number of 2D strokes extracted from ink-wash painting images is proposed and the ordering of strokes is formulated as breadth first search on a graph encoding both the individual features of strokes and their spatial relationships.
- A Novel Customized Recompression Framework for Massive Internet Images2
This paper proposes a novel framework to efficiently customize image recompression according to a variety of applications, and this new framework has been successfully applied to many commercial applications, such as web portals, e-commerce, online game and so on.
- A Customized Framework to Recompress Massive Internet Images2
A novel framework to efficiently customize image recompression according to a variety of applications is proposed and has been successfully applied to many commercial applications, such as web portals, e-commerce, online game, and so on.
- 1
- 1
- 1
- 1
- 1
- 1
- Robust Federated Video-based Remote Physiological Measurement for Heterogeneous Multi-source Data–
This work characterize the heterogeneity of multi-source rPPG data from both the input and output domain perspectives and introduces pseudo-labeling techniques and proposes a novel FL framework, FedGRC, which incorporates automatic gradient regularization calibration to mitigate the impact of input domain discrepancies on model performance.
- Robust Source-Free Domain Adaptation for Medical Image Segmentation based on Curriculum Learning–
A curriculum-based framework, namely learning from curriculum (LFC), for source-free domain adaptation, which consists of easy-to-hard and source-to-target curricula is proposed, which surpasses the existing approaches and achieves a new state-of-the-art.
- –
- –
- –
- –
- Correction to: Rio: a personal storage system in multi-device and cloud–
Dr Feng Wang’s first affiliation is missing in the original article, so his second affiliation is given here.
- DGD: Densifying the Knowledge of Neural Networks with Filter Grafting and Knowledge Distillation.–
The impacts of the two techniques are surprisingly complementary: distillation mostly enhances the knowledge of valid filters while grafting mostly reactivates invalid filters, helping to design a unified training framework called DGD, where distillation and grafting are naturally combined to increase the knowledge density inside the filters given a fixed model structure.
- –
- –
- Content-based measure of image set diversity–
It is important considering to evaluate the diversity of an image set to have a global view of the whole set and to effectively manage or explore a series of shots of different scenes.
- Human Parsing via Shape Boltzmann Machine Networks–
An approach is presented that exploits Shape Boltzmann Machine networks to improve the accuracy of human body parsing, and the proposed Curve Correction method refines the final segmentation results.
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 2026-10-12. 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.