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
- Stephen Shaoyi LiaoSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works87 from public data
- Deep Convolutional Neural Network for Image Deconvolution999
This work develops a deep convolutional neural network to capture the characteristics of degradation, establishing the connection between traditional optimization-based schemes and a neural network architecture where a novel, separable structure is introduced as a reliable support for robust deconvolution against artifacts.
- Cascade Residual Learning: A Two-Stage Convolutional Neural Network for Stereo Matching502
A novel cascade CNN architecture composing of two stages that advances the recently proposed DispNet by equipping it with extra up-convolution modules, leading to disparity images with more details, and shows that residual learning provides more effective refinement.
- 3D Human Pose Estimation in the Wild by Adversarial Learning424
An adversarial learning framework is proposed, which distills the 3D human pose structures learned from the fully annotated dataset to in-the-wild images with only 2D pose annotations and designs a geometric descriptor, which computes the pairwise relative locations and distances between body joints, as a new information source for the discriminator.
- 409
- PIPAL: A Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration320
It is indicated that existing IQA methods cannot fairly evaluate GAN-based IR algorithms, and a large-scale IQA dataset, called Perceptual Image Processing Algorithms (PIPAL) is contributed, which includes the results of GAn-based methods, which are missing in previous datasets.
- Accurate Single Stage Detector Using Recurrent Rolling Convolution297
A novel single stage end-to-end trainable object detection network is proposed by introducing Recurrent Rolling Convolution (RRC) architecture over multi-scale feature maps to construct object classifiers and bounding box regressors which are deep in context.
- Dual Student: Breaking the Limits of the Teacher in Semi-Supervised Learning276
This work shows that the coupled EMA teacher causes a performance bottleneck and introduces Dual Student, which replaces the teacher with another student, and defines a novel concept, stable sample, following which a stabilization constraint is designed for the structure to be trainable.
- Spatio-Temporal Filter Adaptive Network for Video Deblurring237
The proposed Spatio-Temporal Filter Adaptive Network (STFAN) takes both blurry and restored images of the previous frame as well as blurry image of the current frame as input, and dynamically generates the spatially adaptive filters for the alignment and deblurring.
- Learning Monocular Depth by Distilling Cross-Domain Stereo Networks221
This paper proposes to use the stereo matching network as a proxy to learn depth from synthetic data and use predicted stereo disparity maps for supervising the monocular depth estimation network.
- Learning Dual Convolutional Neural Networks for Low-Level Vision221
The proposed DualCNN consists of two parallel branches, which respectively recovers the structures and details in an end-to-end manner, and can generate the target signals according to the formation model for each particular application.
- Single View Stereo Matching209
This paper shows for the first time that the monocular depth estimation problem can be reformulated as two sub-problems, a view synthesis procedure followed by stereo matching, with two intriguing properties, namely i) geometrical constraints can be explicitly imposed during inference; ii) demand on labelled depth data can be greatly alleviated.
- Deep Edge-Aware Filters205
This work makes the attempt to learn a big and important family of edge-aware operators from data based on a deep convolutional neural network with a gradient domain training procedure, which gives rise to a powerful tool to approximate various filters without knowing the original models and implementation details.
- Learning Event-Based Motion Deblurring200
This paper starts from a sequential formulation of event-based motion deblurring, then shows how its optimization can be unfolded with a novel end-toend deep architecture, and proposes a differentiable directional event filtering module to effectively extract rich boundary prior from the evolution of events.
- Deep Reasoning with Knowledge Graph for Social Relationship Understanding198
This work has found that the interplay between these two factors can be effectively modeled by a novel structured knowledge graph with proper message propagation and attention and can be efficiently integrated into the deep neural network architecture to promote social relationship understanding.
- Shepard convolutional neural networks190
This paper draws on Shepard interpolation and design Shepard Convolutional Neural Networks (ShCNN) which efficiently realizes end-to-end trainable TVI operators in the network and shows that by adding only a few feature maps in the new Shepard layers, the network is able to achieve stronger results than a much deeper architecture.
- Physics-Based Generative Adversarial Models for Image Restoration and Beyond188
An algorithm to directly solve numerous image restoration problems (e.g., image deblurring, image dehazing, and image deraining) by generative models with adversarial learning within the GAN framework.
- Learning Event-Driven Video Deblurring and Interpolation163
An effective event-driven video deblurring and interpolation algorithm based on deep convolutional neural networks (CNNs) that achieves superior performance against state-of-the-art methods on both synthetic and real datasets.
- LSTM Pose Machines148
It is shown that if the weight sharing scheme is imposed to the multi-stage CNN, it could be re-written as a Recurrent Neural Network (RNN), which decouples the relationship among multiple network stages and results in significantly faster speed in invoking the network for videos.
- 133
- Look, Listen and Learn — A Multimodal LSTM for Speaker Identification115
A novel multimodal Long Short-Term Memory (LSTM) architecture which seamlessly unifies both visual and auditory modalities from the beginning of each sequence input is described which outperforms the state-of-the-art systems in speaker identification with lower false alarm rate and higher recognition accuracy.
- DAVANet: Stereo Deblurring With View Aggregation108
This work proposes a novel stereo image deblurring network with Depth Awareness and View Aggregation, named DAVANet, which outperforms state-of-the-art methods in terms of accuracy, speed, and model size.
- 95
- On Vectorization of Deep Convolutional Neural Networks for Vision Tasks89
This paper studied the vectorization process of key building blocks in deep CNNs, in order to better understand and facilitate parallel implementation, and developed and compared six implementations with various degrees of vectorization.
- Learning to See in the Dark with Events85
A novel unsupervised domain adaptation network is proposed that explicitly separates domain-invariant features from the domain-specific ones to ease representation learning and achieves superior performance than various state-of-the-art architectures.
- NTIRE 2022 Challenge on Perceptual Image Quality Assessment84
This paper reports on the NTIRE 2022 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2022 to address the emerging challenge of IQA by perceptual image processing algorithms.
- A New Journey from SDRTV to HDRTV80
A lightweight network that utilizes global statistics as guidance to conduct image-adaptive color mapping and achieves state-of-the-art performance in quantitative comparisons and visual quality is presented.
- 70
- Zoom and Learn: Generalizing Deep Stereo Matching to Novel Domains66
This work proposes a self-adaptation approach for CNN training, utilizing both synthetic training data and stereo pairs in the new domain (without ground-truths), and forms an iterative optimization problem with graph Laplacian regularization.
- EfficientFCN: Holistically-Guided Decoding for Semantic Segmentation61
The EfficientFCN is proposed, whose backbone is a common ImageNet pre-trained network without any dilated convolution, and achieves comparable or even better performance than state-of-the-art methods with only 1/3 of the computational cost.
- NTIRE 2021 Challenge on Perceptual Image Quality Assessment60
The NTIRE 2021 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2021, achieved much better results than existing IQA methods, while the winning method can demonstrate state-of-the-art performance.
- 50
- 49
- 48
- Classifying Consumer Comparison Opinions to Uncover Product Strengths and Weaknesses46
A novel Support Vector Machine-based method is proposed to automatically identify comparison opinions, extract comparison relations, and display results with the comparison relation maps by mining the volume of consumer opinions posted on the Web.
- Harnessing Diffusion-Yielded Score Priors for Image Restoration45
HYPIR outperforms previous state-of-the-art methods, achieving efficient and high-quality image restoration, and inherits the capabilities of diffusion models with rich user control, enabling text-guided restoration and adjustable texture richness.
- Trinity of Pixel Enhancement: a Joint Solution for Demosaicking, Denoising and Super-Resolution.42
This paper proposes the Trinity Enhancement Network (TENet), a specially designed learning-based method for the mixture problem, which adopts a novel image processing pipeline order and a joint learning strategy, and contributes a new dataset namely PixelShift200, which consists of high-quality full color sampled real-world images using the advanced pixel shift technique.
- 41
- Generalizing Monocular 3D Human Pose Estimation in the Wild40
This paper proposes a principled approach to generate high quality 3D pose ground truth given any in-the-wild image with a person inside, and builds a large-scale dataset, which enables the training of a high quality neural network model, without specialized training scheme and auxiliary loss function, which performs favorably against the state-of theart3D pose estimation methods.
- Deep Richardson–Lucy Deconvolution for Low-Light Image Deblurring37
A data-driven approach to model the saturated pixels by a learned latent map is developed and performs favorably against state-of-the-art algorithms both quantitatively and qualitatively on synthetic and real-world images.
- Rethinking Learning-based Demosaicing, Denoising, and Super-Resolution Pipeline35
This work comprehensively study the effects of pipelines on the mixture problem of learning-based DN, DM, and SR, in both sequential and joint solutions, and proposes an end-to-end Trinity Pixel Enhancement NETwork (TENet) that achieves the state-of-the-art performance for the mixture Problem.
- 34
- Learning to Predict Context-Adaptive Convolution for Semantic Segmentation31
A Context-adaptive Convolution Network (CaC-Net) is proposed to predict a spatially-varying feature weighting vector for each spatial location of the semantic feature maps and achieves superior segmentation performance on three public datasets.
- 30
- 28
- Learning to Deblur Face Images via Sketch Synthesis26
An effective face deblurring algorithm based on deep convolutional neural networks (CNNs) that is able to deblur face images with favorable performance against state-of-the-art methods.
- Very Power Efficient Neural Time-of-Flight25
It is shown that despite the weak signals in many areas under extreme short exposure setting, these signals as a whole can be well utilized through a learning process which directly translates the weak and noisy ToF camera raw to depth map.
- Learning a Reinforced Agent for Flexible Exposure Bracketing Selection24
A novel deep neural network to automatically select exposure bracketing, named EBSNet, which is sufficiently flexible without having the above restrictions and can be jointly trained to produce favorable results against recent state-of-the-art approaches.
- 24
- 19
- 18
- Efficient Deep Image Denoising via Class Specific Convolution17
Quantitative and qualitative evaluations on public datasets demonstrate that the proposed method for image denoising based on pixel-wise classification can reduce the computational costs without sacrificing the performance compared to state-of-the-art algorithms.
- 15
- Image Formation Model Guided Deep Image Super-Resolution15
This work presents a simple and effective image super-resolution algorithm that imposes an image formation constraint on the deep neural networks via pixel substitution and shows that the proposed algorithm performs favorably against state-of-the-art methods.
- DSR: Direct Self-Rectification for Uncalibrated Dual-Lens Cameras15
This paper proposes a cost-effective solution to perform stereo rectification for dual-lens cameras called direct self-rectification, short for DSR, which removes the need of individual offline calibration for every pair of dual- lens cameras.
- DeblurDiff: Real-World Image Deblurring with Generative Diffusion Models14
The proposed Latent Kernel Prediction Network (LKPN) outperforms state-of-the-art image deblurring methods on both benchmark and real-world images and iterative refinement enhances the accuracy and robustness of the deblurring process.
- An unsupervised feature learning approach to improve automatic incident detection14
This paper proposes to use an unsupervised feature learning algorithm to generate higher level features to represent incidents and finds that effective feature mapping function can be learnt from the data crosses the test sites.
- 13
- 11
- Deep Bayesian Video Frame Interpolation10
Deep Bayesian video frame interpolation is presented, a novel approach for upsampling a low frame-rate video temporally to its higher frame- rate counterpart, using an architecture with half the parameters of the state-of-the-art model.
- Semantic Segmentation Prior for Diffusion-Based Real-World Super-Resolution9
SegSR, inspired by the fact that image super-resolution and segmentation can benefit each other, is proposed which introduces a dual-diffusion framework to facilitate interaction between the image super-resolution and segmentation diffusion models, achieving mutual benefit during the reverse diffusion process.
- 9
- 9
- 8
- EFFECTIVE SENTIMENT ANALYSIS OF CORPORATE FINANCIAL REPORTS8
This paper drew on statistical learning theory to perform extensive theoretic analysis in sentiment analysis by using real corporate financial reports and utilized the cheap and ubiquitous unlabelled data to further improve the sentiment analysis performance.
- A Diffusion-Based Framework for Occluded Object Movement7
This work proposes a Diffusion-based framework specifically designed for Occluded Object Movement, named DiffOOM, which consists of two parallel branches that perform object de-occlusion and movement simultaneously.
- Low-Dose CT Denoising Using A Structure-Preserving Kernel Prediction Network7
A Structure-preserving Kernel Prediction Network (StructKPN) is proposed that combines the kernel prediction network with a structure-aware loss function that utilizes the pixel gradient statistics and guides the model towards spatially-variant filters that enhance noise removal, prevent over-smoothing and preserve detailed structures for different regions in CT imaging.
- Color4E: Event Demosaicing for Full-color Event Guided Image Deblurring6
A novel network called Color4E is proposed to enhance the color restoration quality for the image deblurring task and enables high-quality event-based image deblurring compared to state-of-the-art methods.
- Image Deblurring Aided by Low-Resolution Events6
An alternately performed model is proposed in this paper to deblur high-resolution images with the help of low-resolution events and enhances the quality of events with EventSRNet by extracting the structure information in the generated sharp image.
- Towards Efficient SDRTV-to-HDRTV by Learning From Image Formation5
This paper delineates and analyzes the SDRTV-to-HDRTV conversion by modeling the formation of SDRTV/HDRTV content, and proposes a new three-step solution called HDRTVNet++, which includes adaptive global color mapping, local enhancement, and highlight refinement.
- 4
- 3
- Cross-spectral stereo matching for facial disparity estimation in the dark3
A neural network composed of a multi-spectral transfer network (MSTN) and a disparity estimation network (DEN) that performs favorably against state-of-the-art algorithms on both synthetic and real data is developed.
- 2
- 2
- 2
- When multivariate forecasting meets unsupervised feature learning: Towards a novel anomaly detection framework for decision support2
It is argued that by using multivariate forecasting and unsupervised feature learning, these two important research gaps could be filled and decision support performance was significantly improved.
- 1
- Exploring the Contribution of Unlabeled Data in Financial Sentiment Analysis1
It is shown that the well-known performance degradation issue caused by unlabeled data can be reproduced as a subset of the whole scenario and argued that if the bias-variance trade-off is to be better balanced by a more effective feature selection method unlabeling data is very likely to boost the classification performance.
- 1
- WHEN MULTIVARIATE FORECASTING MEETS UNSUPERVISED FEATURE LEARNING - TOWARDS A NOVEL ANOMALY DETECTION FRAMEWORK FOR DECISION SUPPORT Research-in-Progress1
It is argued that by using multivariate forecasting and unsupervised feature learning, these two important research gaps could be filled and decision support performance was significantly improved.
- 1
- –
- –
- –
- Optimal refactoring policy for agile information systems maintenance: A control theoretic approach–
To the knowledge, this paper is the pioneer in understanding agile ISM policy analytically and builds an optimal control model to balance the tradeoff between defect correction and refactoring.
- Improving Information Systems Development Agility by Organizational Learning in Large Scale Company- A Case Study–
A case study in a leading large scale telecommunication company is designed to study how organizational learning behaviors interact with ISD agility and result shows that double loop learning behaviors could be identified in the implementation of most agile practices and could improve agility by enhancing the change management ability.
- –
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.