Search Results for author:
Found 44 papers, 14 papers with code
Dual Illumination Estimation for Robust Exposure Correction
By performing dual illumination estimation, we obtain two intermediate exposure correction results for the input image, with one fixes the underexposed regions and the other one restores the overexposed regions.
A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction
In this paper, we propose $\text{HF}^2$-VAD, a Hybrid framework that integrates Flow reconstruction and Frame prediction seamlessly to handle Video Anomaly Detection.
Ranked #1 on
Video Anomaly Detection
on ShanghaiTech Campus
PosterLayout: A New Benchmark and Approach for Content-aware Visual-Textual Presentation Layout
Content-aware visual-textual presentation layout aims at arranging spatial space on the given canvas for pre-defined elements, including text, logo, and underlay, which is a key to automatic template-free creative graphic design.
A Multi-Task Network for Joint Specular Highlight Detection and Removal
Specular highlight detection and removal are fundamental and challenging tasks.
MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction
The extracted features at each scale are then combined and decoded to obtain the residuals between the input and target poses.
Ranked #7 on
Human Pose Forecasting
on Human3.6M
Learning to Detect Specular Highlights from Real-world Images
Specular highlight detection is a challenging problem, and has many applications such as shiny object detection and light source estimation.
Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction
This motivates us to propose a novel two-stage prediction framework, including an init-prediction network that just computes the good guess and then a formal-prediction network that predicts the target future poses based on the guess.
Ranked #5 on
Human Pose Forecasting
on Human3.6M
From Synthetic to Real: Image Dehazing Collaborating with Unlabeled Real Data
Our DID-Net predicts the three component maps by progressively integrating features across scales, and refines each map by passing an independent refinement network.
Ranked #6 on
Image Dehazing
on Haze4k
Document Image Shadow Removal Guided by Color-Aware Background
In this paper, we present a color-aware background extraction network (CBENet) for extracting a spatially varying background image that accurately depicts the background colors of the document.
Towards High-Quality Specular Highlight Removal by Leveraging Large-Scale Synthetic Data
This paper aims to remove specular highlights from a single object-level image.
Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Space
In this paper, we propose a novel sampling strategy for sampling very diverse results from an imbalanced multimodal distribution learned by a deep generative model.
Ranked #2 on
Human Pose Forecasting
on HumanEva-I
NECA: Neural Customizable Human Avatar
The core of our approach is to represent humans in complementary dual spaces and predict disentangled neural fields of geometry, albedo, shadow, as well as an external lighting, from which we are able to derive realistic rendering with high-frequency details via volumetric rendering.
Debiasing Recommendation by Learning Identifiable Latent Confounders
Confounding bias arises due to the presence of unmeasured variables (e. g., the socio-economic status of a user) that can affect both a user's exposure and feedback.
Applying Deep Learning To Airbnb Search
The application to search ranking is one of the biggest machine learning success stories at Airbnb.
On Multi-resident Activity Recognition in Ambient Smart-Homes
Increasing attention to the research on activity monitoring in smart homes has motivated the employment of ambient intelligence to reduce the deployment cost and solve the privacy issue.
Towards Monetary Incentives in Social Q&A Services
Community-based question answering (CQA) services are facing key challenges to motivate domain experts to provide timely answers.
Pyramid Embedded Generative Adversarial Network for Automated Font Generation
The generator is built using one encoder-decoder structure with cascaded refinement connections and mirror skip connections.
A Novel Integrated Framework for Learning both Text Detection and Recognition
In this paper, we propose a novel integrated framework for learning both text detection and recognition.
Graph-Adaptive Pruning for Efficient Inference of Convolutional Neural Networks
In this method, the network is viewed as a computational graph, in which the vertices denote the computation nodes and edges represent the information flow.
Noise-Clustered Distant Supervision for Relation Extraction: A Nonparametric Bayesian Perspective
For the task of relation extraction, distant supervision is an efficient approach to generate labeled data by aligning knowledge base with free texts.
Quality Dynamic Human Body Modeling Using a Single Low-cost Depth Camera
In this paper we present a novel autonomous pipeline to build a personalized parametric model (pose-driven avatar) using a single depth sensor.
Enhancing Underexposed Photos using Perceptually Bidirectional Similarity
To obtain high-quality results free of these artifacts, we present a novel underexposed photo enhancement approach that is able to maintain the perceptual consistency.
Zero-Shot Paraphrase Generation with Multilingual Language Models
Leveraging multilingual parallel texts to automatically generate paraphrases has drawn much attention as size of high-quality paraphrase corpus is limited.
Automatic marker-free registration of tree point-cloud data based on rotating projection
In coarse registration, point clouds produced by each scan are projected onto a spherical surface to generate a series of two-dimensional (2D) images, which are used to estimate the initial positions of multiple scans.
Automated classification of stems and leaves of potted plants based on point cloud data
A classification method was proposed to classify the leaves and stems of potted plants automatically based on the point cloud data of the plants, which is a nondestructive acquisition.
Automatic sampling and training method for wood-leaf classification based on tree terrestrial point cloud
The point cloud data of ten trees were tested by using the proposed method and a manual selection method.
Toward the endoscopic classification of unipotent representations of $p$-adic $G_2$
In this paper, we review the Langlands correspondence for unipotent representations of the exceptional group of type $G_2$ over a $p$-adic field $F$ and present it in an explicit form.
Representation Theory Algebraic Geometry 11F70 (Primary) 22E50, 32S30, 32S60 (Secondary)
Roles of the Narrow Electronic Band near the Fermi Level in 1$T$-TaS$_2$-Related Layered Materials
4$H_{\rm b}$-TaS$_2$ is a superconducting compound with alternating 1$T$-TaS$_2$ and 1$H$-TaS$_2$ layers, where the 1$H$-TaS$_2$ layer has weak charge density wave (CDW) pattern and reduces the CDW coupling between the adjacent 1$T$-TaS$_2$ layers.
Mesoscale and Nanoscale Physics Materials Science
NTIRE 2021 Challenge on Perceptual Image Quality Assessment
This paper reports on 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.
Two New Stenosis Detection Methods of Coronary Angiograms
Two vascular stenosis detection methods are proposed to assist the diagnosis.
Two New Stenosis Detection Methods of Coronary Angiograms
Two vascular stenosis detection methods are proposed to assist the diagnosis.
Deep Filtering with DNN, CNN and RNN
The idea is to train a neural network with Monte Carlo samples generated from a nominal dynamic model.
Atomic Filter: a Weak Form of Shift Operator for Graph Signals
In order to establish the theory of filtering, windowed Fourier transform and wavelet transform in the setting of graph signals, we need to extend the shift operation of classical signals to graph signals.
基于话头话体共享结构信息的机器阅读理解研究(Rearch on Machine reading comprehension based on shared structure information between Naming and Telling)
“机器阅读理解(Machine Reading Comprehension, MRC)任务旨在让机器回答给定上下文的问题来测试机器理解自然语言的能力。目前, 基于大规模预训练语言模型的神经机器阅读理解模型已经取得重要进展, 但在涉及答案要素、线索要素和问题要素跨标点句、远距离关联时, 答案抽取的准确率还有待提升。本文通过篇章内话头话体结构分析, 建立标点句间远距离关联关系、补全共享缺失成分, 辅助机器阅读理解答案抽取;设计和实现融合话头话体结构信息的机器阅读理解模型, 在公开数据集CMRC2018上的实验结果表明, 模型的F1值相对于基线模型提升2. 4%, EM值提升6%。”
Evaluating the Efficacy of Skincare Product: A Realistic Short-Term Facial Pore Simulation
In this paper, we propose the first simulation model to reveal facial pore changes after using skincare products.
Pyramid Texture Filtering
We present a simple but effective technique to smooth out textures while preserving the prominent structures.
An Equivalent Graph Reconstruction Model and its Application in Recommendation Prediction
Recently, a recommendation algorithm based on the graph Laplacian regularization was proposed, which treats the prediction problem of the recommendation system as a reconstruction issue of small samples of the graph signal under the same graph model.
Pairs Trading: An Optimal Selling Rule with Constraints
In pairs trading, a long position is held in one stock while a short position is held in another.
Cross-Layer Optimization for Fault-Tolerant Deep Learning
Fault-tolerant deep learning accelerator is the basis for highly reliable deep learning processing and critical to deploy deep learning in safety-critical applications such as avionics and robotics.
Interleaving One-Class and Weakly-Supervised Models with Adaptive Thresholding for Unsupervised Video Anomaly Detection
In previous work, the two models are closely entangled with each other, and it is not known how to upgrade their method without modifying their training framework significantly.
Incorporating Exemplar Optimization into Training with Dual Networks for Human Mesh Recovery
(2) We devise a dual-network architecture to convey the novel training paradigm, which is composed of a main regression network and an auxiliary network, in which we can formulate the exemplar optimization loss function in the same form as the training loss function.
Multiple-Crop Human Mesh Recovery with Contrastive Learning and Camera Consistency in A Single Image
We tackle the problem of single-image Human Mesh Recovery (HMR).
Stable-Makeup: When Real-World Makeup Transfer Meets Diffusion Model
Current makeup transfer methods are limited to simple makeup styles, making them difficult to apply in real-world scenarios.
