Search Results for author: Jie Guo

Found 29 papers, 2 papers with code

Attention-Based Graph Neural Network with Global Context Awareness for Document Understanding

no code implementations CCL 2020 Yuan Hua, Zheng Huang, Jie Guo, Weidong Qiu

Information extraction from documents such as receipts or invoices is a fundamental and crucial step for office automation.

graph construction

Deep Surface Normal Estimation on the 2-Sphere with Confidence Guided Semantic Attention

no code implementations ECCV 2020 Quewei Li, Jie Guo, Yang Fei, Qinyu Tang, Wenxiu Sun, Jin Zeng, Yanwen Guo

We propose a deep convolutional neural network (CNN) to estimate surface normal from a single color image accompanied with a low-quality depth channel.

Surface Normal Estimation

Completing Partial Point Clouds with Outliers by Collaborative Completion and Segmentation

no code implementations18 Mar 2022 Changfeng Ma, Yang Yang, Jie Guo, Chongjun Wang, Yanwen Guo

We propose in this paper an end-to-end network, named CS-Net, to complete the point clouds contaminated by noises or containing outliers.

Point Cloud Completion

Deep Point Cloud Simplification for High-quality Surface Reconstruction

no code implementations17 Mar 2022 Yuanqi Li, Jianwei Guo, Xinran Yang, Shun Liu, Jie Guo, Xiaopeng Zhang, Yanwen Guo

In this paper, we propose a novel point cloud simplification network (PCS-Net) dedicated to high-quality surface mesh reconstruction while maintaining geometric fidelity.

Scene Understanding Surface Reconstruction

Deep Graph Learning for Spatially-Varying Indoor Lighting Prediction

no code implementations13 Feb 2022 Jiayang Bai, Jie Guo, Chenchen Wan, Zhenyu Chen, Zhen He, Shan Yang, Piaopiao Yu, Yan Zhang, Yanwen Guo

At its core is a new lighting model (dubbed DSGLight) based on depth-augmented Spherical Gaussians (SG) and a Graph Convolutional Network (GCN) that infers the new lighting representation from a single LDR image of limited field-of-view.

Graph Learning

GLPanoDepth: Global-to-Local Panoramic Depth Estimation

no code implementations6 Feb 2022 Jiayang Bai, Shuichang Lai, Haoyu Qin, Jie Guo, Yanwen Guo

In this paper, we propose a learning-based method for predicting dense depth values of a scene from a monocular omnidirectional image.

Depth Estimation

ISNet: Shape Matters for Infrared Small Target Detection

1 code implementation CVPR 2022 Mingjin Zhang, Rui Zhang, Yuxiang Yang, Haichen Bai, Jing Zhang, Jie Guo

TOAA block calculates the low-level information with attention mechanism in both row and column directions and fuses it with the high-level information to capture the shape characteristic of targets and suppress noises.

Task-Oriented Image Transmission for Scene Classification in Unmanned Aerial Systems

no code implementations21 Dec 2021 Xu Kang, Bin Song, Jie Guo, Zhijin Qin, F. Richard Yu

The vigorous developments of Internet of Things make it possible to extend its computing and storage capabilities to computing tasks in the aerial system with collaboration of cloud and edge, especially for artificial intelligence (AI) tasks based on deep learning (DL).

Classification Edge-computing +1

SVBRDF Recovery From a Single Image With Highlights using a Pretrained Generative Adversarial Network

no code implementations29 Oct 2021 Tao Wen, Beibei Wang, Lei Zhang, Jie Guo, Nicolas Holzschuch

For efficiency, we train the network in two stages: reusing a trained model to initialize the SVBRDFs and fine-tune it based on the input image.

Scale Invariant Domain Generalization Image Recapture Detection

no code implementations7 Oct 2021 Jinian Luo, Jie Guo, Weidong Qiu, Zheng Huang, Hong Hui

However, most of them ignored the domain generalization scenario and scale variances, with an inferior performance on domain shift situations, and normally were exacerbated by intra-domain and inter-domain scale variances.

Domain Generalization Face Identification

Temporal Alignment Prediction for Few-Shot Video Classification

no code implementations26 Jul 2021 Fei Pan, Chunlei Xu, Jie Guo, Yanwen Guo

In order to obtain the similarity of a pair of videos, we predict the alignment scores between all pairs of temporal positions in the two videos with the temporal alignment prediction function.

Classification Video Classification

A Transductive Maximum Margin Classifier for Few-Shot Learning

no code implementations26 Jul 2021 Fei Pan, Chunlei Xu, Jie Guo, Yanwen Guo

We introduce a transductive maximum margin classifier for few-shot learning (FS-TMMC).

Few-Shot Learning

GLAVNet: Global-Local Audio-Visual Cues for Fine-Grained Material Recognition

no code implementations CVPR 2021 Fengmin Shi, Jie Guo, Haonan Zhang, Shan Yang, Xiying Wang, Yanwen Guo

We demonstrate that local geometry has a greater impact on the sound than the global geometry and offers more cues in material recognition.

Material Recognition

A Survey on Natural Language Video Localization

no code implementations1 Apr 2021 Xinfang Liu, Xiushan Nie, Zhifang Tan, Jie Guo, Yilong Yin

Natural language video localization (NLVL), which aims to locate a target moment from a video that semantically corresponds to a text query, is a novel and challenging task.

Rendering Discrete Participating Media with Geometrical Optics Approximation

no code implementations24 Feb 2021 Jie Guo, Bingyang Hu, Yanjun Chen, Yuanqi Li, Yanwen Guo, Ling-Qi Yan

We consider the scattering of light in participating media composed of sparsely and randomly distributed discrete particles.

Graphics Optics

Hierarchical Disentangled Representation Learning for Outdoor Illumination Estimation and Editing

no code implementations ICCV 2021 Piaopiao Yu, Jie Guo, Fan Huang, Cheng Zhou, Hongwei Che, Xiao Ling, Yanwen Guo

However, naively compressing an outdoor panorama into a low-dimensional latent vector, as existing models have done, causes two major problems.

Representation Learning

Partially Observable Online Change Detection via Smooth-Sparse Decomposition

no code implementations22 Sep 2020 Jie Guo, Hao Yan, Chen Zhang, Steven Hoi

We consider online change detection of high dimensional data streams with sparse changes, where only a subset of data streams can be observed at each sensing time point due to limited sensing capacities.

Bayesian Inference Change Detection

Image Stitching Based on Planar Region Consensus

no code implementations6 Jul 2020 Aocheng Li, Jie Guo, Yanwen Guo

We specifically design a new module to make fully use of existing semantic segmentation networks to accommodate planar segmentation.

Image Stitching Semantic Segmentation

FA-GANs: Facial Attractiveness Enhancement with Generative Adversarial Networks on Frontal Faces

no code implementations17 May 2020 Jingwu He, Chuan Wang, Yang Zhang, Jie Guo, Yanwen Guo

To the best of our knowledge, we are the first to enhance the facial attractiveness with GANs in both geometry and appearance aspects.

Hybrid Models for Open Set Recognition

no code implementations ECCV 2020 Hongjie Zhang, Ang Li, Jie Guo, Yanwen Guo

We propose the OpenHybrid framework, which is composed of an encoder to encode the input data into a joint embedding space, a classifier to classify samples to inlier classes, and a flow-based density estimator to detect whether a sample belongs to the unknown category.

Open Set Learning Out-of-Distribution Detection

Learning Actor Relation Graphs for Group Activity Recognition

2 code implementations CVPR 2019 Jianchao Wu, Li-Min Wang, Li Wang, Jie Guo, Gangshan Wu

To this end, we propose to build a flexible and efficient Actor Relation Graph (ARG) to simultaneously capture the appearance and position relation between actors.

Action Recognition Group Activity Recognition

Self-Selective Correlation Ship Tracking Method for Smart Ocean System

no code implementations26 Feb 2019 Xu Kang, Bin Song, Jie Guo, Xiaojiang Du, Mohsen Guizani

In recent years, with the development of the marine industry, navigation environment becomes more complicated.

Interest-Related Item Similarity Model Based on Multimodal Data for Top-N Recommendation

no code implementations13 Feb 2019 Junmei Lv, Bin Song, Jie Guo, Xiaojiang Du, Mohsen Guizani

Specifically, the Multimodal IRIS model consists of three modules, i. e., multimodal feature learning module, the Interest-Related Network (IRN) module and item similarity recommendation module.

Recommendation Systems

Single Image Highlight Removal with a Sparse and Low-Rank Reflection Model

no code implementations ECCV 2018 Jie Guo, Zuojian Zhou, Li-Min Wang

We propose a sparse and low-rank reflection model for specular highlight detection and removal using a single input image.

Highlight Detection

Stochastic Channel Decorrelation Network and Its Application to Visual Tracking

no code implementations3 Jul 2018 Jie Guo, Tingfa Xu, Shenwang Jiang, Ziyi Shen

Deep convolutional neural networks (CNNs) have dominated many computer vision domains because of their great power to extract good features automatically.

Visual Tracking

FPAN: Fine-grained and Progressive Attention Localization Network for Data Retrieval

no code implementations5 Apr 2018 Sijia Chen, Bin Song, Jie Guo, Xiaojiang Du, Mohsen Guizani

The Localization of the target object for data retrieval is a key issue in the Intelligent and Connected Transportation Systems (ICTS).

Multi-Task Learning Object Localization +1

Fused Text Segmentation Networks for Multi-oriented Scene Text Detection

no code implementations11 Sep 2017 Yuchen Dai, Zheng Huang, Yuting Gao, Youxuan Xu, Kai Chen, Jie Guo, Weidong Qiu

In this paper, we introduce a novel end-end framework for multi-oriented scene text detection from an instance-aware semantic segmentation perspective.

Multi-Oriented Scene Text Detection object-detection +4

Cannot find the paper you are looking for? You can Submit a new open access paper.