摘要:
A dense point cloud with rich and realistic texture is generated from multiview images using dense reconstruction algorithms such as Multi View Stereo (MVS). However, its spatial precision depends on the performance of the matching and dense reconstruction algorithms used. Moreover, outliers are usually unavoidable as mismatching of image features. The lidar point cloud lacks texture but performs better spatial precision because it avoids computational errors. This paper proposes a multiresolution patch-based 3D dense reconstruction method based on integrating multiview images and the laser point cloud. A sparse point cloud is firstly generated with multiview images by Structure from Motion (SfM), and then registered with the laser point cloud to establish the mapping relationship between the laser point cloud and multiview images. The laser point cloud is reprojected to multiview images. The corresponding optimal level of the image pyramid is predicted by the distance distribution of projected pixels, which is used as the starting level for patch optimization during dense reconstruction. The laser point cloud is used as stable seed points for patch growth and expansion, and stored by the dynamic octree structure. Subsequently, the corresponding patches are optimized and expanded with the pyramid image to achieve multiscale and multiresolution dense reconstruction. In addition, the octree's spatial index structure facilitates parallel computing with highly efficiency. The experimental results show that the proposed method is superior to the traditional MVS technology in terms of model accuracy and completeness, and have broad application prospects in high-precision 3D modeling of large scenes.
作者机构:
[Gui, Ziyan; Liu, Changhui; Xiong, Li] Wuhan Institute of Technology, Wuhan, China;[Xie, Zuoquan] Central China Normal University, Wuhan, China;[Wu, Liang] Southwestern University of Finance and Economics, Chengdu, China
会议名称:
3rd International Conference on Big Data and Artificial Intelligence and Software Engineering, ICBASE 2022
作者机构:
[Zhang, H; Tong, Hang; Liu, Sanya; Li, Yaopeng; Zhang, Hao; Min, Yuandong] Cent China Normal Univ, Fac Artificial Intelligence Educ, Natl Engn Res Ctr Learning, Wuhan 430079, Peoples R China.;[Zhang, H; Tong, Hang; Liu, Sanya; Li, Yaopeng; Zhang, Hao; Min, Yuandong] Cent China Normal Univ, Fac Artificial Intelligence Educ, Natl Engn Lab Educ Big Data, Wuhan 430079, Peoples R China.
会议名称:
IEEE International Performance, Computing, and Communications Conference (IPCCC)
会议时间:
NOV 11-13, 2022
会议地点:
Austin, TX
会议主办单位:
[Zhang, Hao;Min, Yuandong;Liu, Sanya;Tong, Hang;Li, Yaopeng] Cent China Normal Univ, Fac Artificial Intelligence Educ, Natl Engn Res Ctr Learning, Wuhan 430079, Peoples R China.^[Zhang, Hao;Min, Yuandong;Liu, Sanya;Tong, Hang;Li, Yaopeng] Cent China Normal Univ, Fac Artificial Intelligence Educ, Natl Engn Lab Educ Big Data, Wuhan 430079, Peoples R China.
会议论文集名称:
IEEE International Performance Computing and Communications Conference (IPCCC)
摘要:
How to automatically obtain cross-features with different weight values is a significant issue in the research of recommendation models. Traditional recommendation models cannot automatically learn the deep-level features of users and items to obtain cross-features. The mixed processing of dense numerical features and sparse categorical features will result in more information loss during dimensionality reduction. Cross features occupy the same weight in the recommendation process, which will lead to the non-prominence of critical features and reduce the accuracy of model recommendations. This paper proposes a personalized recommendation model (MSRN) for self-attention perceptron with automatic feature correlation. The model first processes the numerical features and category features in double towers to reduce the loss of feature information. Numerical cross-feature matrix and category cross-feature matrix use multilayer perceptrons to automatically mine the hidden knowledge and relationships between features. The model uses the Hadamard product to process it to obtain the cross feature matrix and uses the self-attention mechanism to assign different weights to the extracted cross-features. The experimental results on the public data set show that the recommended evaluation indicators of this model, MAE, and RMSE, are better than the current advanced recommendation models and have better accuracy and stability.
摘要:
In this paper, we explore the capabilities of a number of deep neural network models in generating whole-brain 3T-like MR images from clinical 1.5T MRIs. The models include a fully convolutional network (FCN) method and three state-of-the-art super-resolution solutions, ESPCN [26], SRGAN [17] and PRSR [7]. The FCN solution, U-Convert-Net, carries out mapping of 1.5T-to-3T slices through a U-Net-like architecture, with 3D neighborhood information integrated through a multi-view ensemble. The pros and cons of the models, as well the associated evaluation metrics, are measured with experiments and discussed in depth. To the best of our knowledge, this study is the first work to evaluate multiple deep learning solutions for whole-brain MRI conversion, as well as the first attempt to utilize FCN/U-Net-like structure for this purpose.
作者机构:
[Zhou, Jie; Liu, Xuan; Cui, Yilin; Xiong, Xuqian] Cent China Normal Univ, Sch Urban & Environm Sci, Wuhan, Peoples R China.;[Zhou, Jie; Liu, Xuan; Cui, Yilin; Xiong, Xuqian] Key Lab Geog Proc Anal & Simulat Hubei Prov, Wuhan, Peoples R China.;[Jia, Li; Lu, Jing] Chinese Acad Sci, Aerosp Informat Res Inst, Beijing, Peoples R China.;[Zhou, Jie] Delft Univ Technol, Delft, Netherlands.
会议名称:
IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
会议时间:
JUL 17-22, 2022
会议地点:
Kuala Lumpur, MALAYSIA
会议主办单位:
[Zhou, Jie;Liu, Xuan;Xiong, Xuqian;Cui, Yilin] Cent China Normal Univ, Sch Urban & Environm Sci, Wuhan, Peoples R China.^[Zhou, Jie;Liu, Xuan;Xiong, Xuqian;Cui, Yilin] Key Lab Geog Proc Anal & Simulat Hubei Prov, Wuhan, Peoples R China.^[Jia, Li;Lu, Jing] Chinese Acad Sci, Aerosp Informat Res Inst, Beijing, Peoples R China.^[Zhou, Jie] Delft Univ Technol, Delft, Netherlands.
会议论文集名称:
IEEE International Symposium on Geoscience and Remote Sensing IGARSS
关键词:
vegetation anomalies;uncertainty;EO-based vegetation products;Vegetation Condition Index
摘要:
Satellite-based Earth Observation systems archived a variety of vegetation products during the last 50 years, which can reveal regional to global ecosystem dynamics across diverse spatiotemporal scales. The anomaly metrics such as Vegetation Condition Index (VCI) defined by comparing the current vegetation growth condition to historical average status based on long-term EO-based vegetation products were widely used to delineate abnormal vegetation variation exerted by either climatic or anthropogenic factors (e.g., droughts, wildfires). However, currently available long-term vegetation products may differ from each other in terms of sensors (observational platform or spectral bands), biophysical definitions (e.g., NDVI, EVI, LAI, and VOD), spatiotemporal resolution, as well as the time-spans, which results in inconsistency across these vegetation products. Taking the VCI as an example, this study evaluated the uncertainty of vegetation anomalies detected based on different vegetation products over the middle reach of the Yangtze River by explicitly considering the effect of sensors, biophysical definitions, and time-spans. The preliminary results showed that VCI derived from NDVI products from different sensors (AVHRR vs. MODIS) induced significant inconsistent anomalies over most landscapes. The differences resulting from products with different biophysical definitions (NDVI vs. EVI, LAI, and VOD) are much lower than those from different sensors but still significant over specific areas. As for the time-spans, the 20-year NDVI based VCI presented a considerable reduction in variance over the study area on average compared to VCI calculated based on 5-year NDVI. In summary, caution should be taken when applying EO-based vegetation products for vegetation anomalies mapping, especially for quantitative assessment.
作者机构:
[Chi, Maomao; Ma, Haiyan] China Univ Geosci, Sch Econ & Management, Wuhan, Peoples R China.;[Wang, Yunran] Cent China Normal Univ, Sch Informat Management, Wuhan, Peoples R China.
会议名称:
3rd International Conference on Design, Operation and Evaluation of Mobile Communications (MOBILE) Held as Part of 24th International Conference on Human-Computer Interaction (HCII)
会议时间:
JUN 26-JUL 01, 2022
会议地点:
ELECTR NETWORK
会议主办单位:
[Chi, Maomao;Ma, Haiyan] China Univ Geosci, Sch Econ & Management, Wuhan, Peoples R China.^[Wang, Yunran] Cent China Normal Univ, Sch Informat Management, Wuhan, Peoples R China.
会议论文集名称:
Lecture Notes in Computer Science
关键词:
Mobile games;Uses and gratifications theory;Stickiness
摘要:
Despite the huge growth potential that has been predicted for mobile game continuous usage intention, little is known about what motives users to be sticky under the mobile game context. Drawing on the Uses and Gratifications theory (UGT), this study aims to investigate the influencing effects of players' characteristics and the mobile game structures on players' mobile game behavior (e.g. stickiness). After surveying 439 samples, the research model is tested with Partial Least Squares Structural Equation Modeling (PLS-SEM). The results indicate that both individual gratifications and mobile game presence positively affect users' stickiness. Furthermore, we find that leisure boredom of individual situations and integration of mobile game governance positively affect users' stickiness. The results provide further insights into the design and governance strategies of mobile games.
作者机构:
[Zhang, Lei] Cent China Normal Univ, Sch Chinese Language & Literature, Wuhan, Peoples R China.;[Yang, Shanshan] Cent China Normal Univ, Sch Foreign Languages, Wuhan, Peoples R China.;[Dong, Sicong] Harbin Inst Technol, Sch Humanities & Social Sci, Shenzhen, Peoples R China.
会议名称:
22nd Chinese Lexical Semantics Workshop (CLSW)
会议时间:
MAY 15-16, 2021
会议地点:
Nanjing Normal Univ, Nanjing, PEOPLES R CHINA
会议主办单位:
Nanjing Normal Univ
会议论文集名称:
Lecture Notes in Artificial Intelligence
关键词:
Constructional innovation;"(sic)NP" [ni bixu zhidao de NP] (NP that you must know);Limitations
摘要:
The present study addresses the limitations of constructional innovation by looking into the case of "(sic)NP" [ni bixu zhidao de NP] (NP that you must know), an emerging construction popular in Chinese titles. Upon linguistic data collection and case analysis, it is found that, constructional innovation, while fulfilling the expected functions, is at the same time subject to the context of linguistic innovation. On one hand, new constructions with certain functional attributes have a better chance of rising from a specific context. The rise of the "(sic)NP" [ni bixu zhidao de NP] (NP that you must know) as a popular title option in the Chinese new media is believed to benefit from its functional attributes that "highlight high-value information", "express the author's stance", and "recruit readers' empathy". On the other hand, newly emerging constructions are restricted by the linguistic context as well. Therefore, the construction "(sic)NP" [ni bixu zhidao de NP] (NP that you must know) is distinctive in both its form and semantics.
摘要:
The scientific and reasonable evaluation indicators that can fully reflect the various dimensions of students' computational thinking (CT) skills is the basis and premise of accurately evaluating students' CT skills, which is of great significance to the cultivation of students' CT skills. However, the current research on how to construct the evaluation indicators is still inadequate, and most of the research is put forward by the subjective experience of researchers, lacking objectivity and the universality of ability. In the paper, we comprehensively reviewed the concepts of CT in the theoretical literature of CT, aiming to construct the comprehensive and effective evaluation indicators of CT for students by clustering the keywords of CT concepts and extracting indicators. The validity of indicators is verified by qualitative analysis, quantitative analysis and expert evaluation. The results show that the evaluation indicators of CT constructed by spectral clustering technology are a more scientific, more comprehensive reflection of the ability dimensions of CT. It has unique advantages in constructing objective and comprehensive evaluation indicators and provides an evaluation basis for the evaluation practice of CT skills.
摘要:
Event cameras asynchronously capture pixel-level intensity changes in scenes and output a stream of events. Compared with traditional frame-based cameras, they can offer competitive imaging characteristics: low latency, high dynamic range, and low power consumption. It means that event cameras are ideal for vision tasks in dynamic scenarios, such as human action recognition. The best-performing event-based algorithms convert events into frame-based representations and feed them into existing learning models. However, generating informative frames for long-duration event streams is still a challenge since event cameras work asynchronously without a fixed frame rate. In this work, we propose a novel frame-based representation named Compact Event Image (CEI) for action recognition. This representation is generated by a self-attention based module named Event Tubelet Compressor (EVTC) in a learnable way. The EVTC module adaptively summarizes the long-term dynamics and temporal patterns of events into a CEI frame set. We can combine EVTC with conventional video backbones for end-to-end event-based action recognition. We evaluate our approach on three benchmark datasets, and experimental results show it outperforms state-of-the-art methods by a large margin.
作者机构:
[Zhang, Wei] Central China Normal University, National Engineering Research Center for E-Learning, China;[Qu, Kaiyuan; Han, Yahui; Tan, Longan] Central China Normal University, China
会议名称:
6th International Conference on Innovation in Artificial Intelligence, ICIAI 2022
作者机构:
[Ren, Xiaotong] Cent China Normal Univ, Fac Artificial Intelligence Educ, Wuhan 430079, Hubei, Peoples R China.
会议名称:
13th International Conference on Graphics and Image Processing (ICGIP)
会议时间:
AUG 18-20, 2021
会议地点:
Yunnan Univ, Kunming, PEOPLES R CHINA
会议主办单位:
Yunnan Univ
会议论文集名称:
Proceedings of SPIE
关键词:
Virtual Reality Technology;Virtual Research Travel;Suzhou Shantang Street Research Travel
摘要:
Research travel have gradually been applied and studied by many schools in teaching practice, but under many interference factors, the vigorous implementation of research travel has not been carried out successfully. And virtual reality technology can effectively solve this problem, help students conduct practical learning, and improve students' inquiry ability. This research developed a virtual research program which is taking Suzhou Shantang Street as an example to explore the application of virtual reality technology in the middle school research travel course.
作者机构:
[Li, Wanxin; Wang, Wei; Jin, Lianghao; Xie, Wei] Cent China Normal Univ, Hubei Prov Key Lab Artificial Intelligence & Smar, Wuhan, Peoples R China.;[Li, Wanxin; Wang, Wei; Jin, Lianghao; Xie, Wei] Cent China Normal Univ, Sch Comp, Wuhan, Peoples R China.;[Tu, Zhigang] Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, Wuhan, Peoples R China.
会议名称:
IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) / IEEE World Congress on Computational Intelligence (IEEE WCCI) / International Joint Conference on Neural Networks (IJCNN) / IEEE Congress on Evolutionary Computation (IEEE CEC)
会议时间:
JUL 18-23, 2022
会议地点:
Padua, ITALY
会议主办单位:
[Li, Wanxin;Xie, Wei;Wang, Wei;Jin, Lianghao] Cent China Normal Univ, Hubei Prov Key Lab Artificial Intelligence & Smar, Wuhan, Peoples R China.^[Li, Wanxin;Xie, Wei;Wang, Wei;Jin, Lianghao] Cent China Normal Univ, Sch Comp, Wuhan, Peoples R China.^[Tu, Zhigang] Wuhan Univ, State Key Lab Informat Engn Surveying Mapping & R, Wuhan, Peoples R China.
会议论文集名称:
IEEE International Joint Conference on Neural Networks (IJCNN)
摘要:
Group activity recognition aims to identify group activities from the videos. Most of the previous methods focus on modeling between individuals (one-to- one), which ignores the fact that a single individual's behavior may be jointly determined by multiple individual behaviors (many-to-one). For this reason, we propose a Multi-Hyperedge Hypergraph (MHH) to capture high-order relationships between multiple people. Specifically, we build three different types of hyperedges on the hypergraph structure. Each hyperedge can accommodate the characteristics of multiple nodes to capture different types of high-order relationships between nodes. Then, we use the late fusion method to fuse the three features to further enhance the overall behavioral representation. Finally, we perform a series of experiments on two of the most widely used benchmarks in group activity recognition, which have proved the effectiveness of MHH. More importantly, as far as we know, this is the first case of using a hypergraph structure for group activity recognition.
期刊:
2022 2ND IEEE INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING AND ARTIFICIAL INTELLIGENCE (SEAI 2022),2022年:199-203
作者机构:
[Qiao, Xiaobin; Yongmin, Shuai] Wuhan Maritime Commun Res Inst, Wuhan, Peoples R China.;[Zhang, Yu; Liu, Fuhao] Cent China Normal Univ, Coll Phys Sci & Technol, Wuhan, Peoples R China.;[Zeng, Yong; Xiong, Yunfei] Wuhan Fiberhome Tech Serv Co Ltd, Wuhan, Peoples R China.
会议名称:
2nd IEEE International Conference on Software Engineering and Artificial Intelligence (SEAI) / 7th International Workshop on Pattern Recognition (IWPR)
会议时间:
JUN 10-12, 2022
会议地点:
Huaqiao Univ, Coll Comp Sci & Technol, Xiamen, PEOPLES R CHINA
会议主办单位:
Huaqiao Univ, Coll Comp Sci & Technol
关键词:
power grid;information network;transportation network;co-simulation system
摘要:
The three-network integration of power grid, information network and transportation network has become a global issue and trend. However, the current research on triple play is still in its infancy. Most of the researches define the concept of triple play, and lack of simulation research on the power grid-information network-transportation network coupling system. Therefore, this paper studies the key technologies of power grid-information network-transportation network co-simulation. The key technologies of simulation are data interaction method and time synchronization method. By building a simulation prototype system, it provides simulation support for the theoretical study of the power grid-information network-transportation network coupling system.
摘要:
The neuro-transfer function (neuro-TF) methods have been widely used in electromagnetic (EM) parametric modeling. This paper reviews the advanced neuro-TE techniques for EM parametric modeling in recent years, which includes neuro-TF using pole/residue as coefficients, neuro-TF using hybrid coefficients, and decomposition technique. An example of a fourth-order bandpass filter is given to verify the accuracy of the decomposition method.
作者:
Shu, Fengfang;Zhao, Chengling;Liu, Qingtang;Li, Hongxia;Huang, Yan
作者机构:
[Shu, Fengfang; Zhao, Chengling; Liu, Qingtang] Faculty of Artificial Intelligence in Education, Central China Normal University, Hubei, Wuhan;430079, China;Wuhan Open University, Wuhan Software Engineering Vocational College, Hubei, Wuhan;430030, China;[Li, Hongxia] School of Computer Science, Si Chuan Normal University, Sichuan, Chengdu
会议名称:
6th International Conference on Education and Multimedia Technology, ICEMT 2022
作者机构:
[Zhang, Kui; Dai, Zhicheng; Wang, Chunran; Chen, Rongjin; Zhu, Fuming] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.
会议名称:
10th International Conference on Information and Education Technology (ICIET)
会议时间:
APR 09-11, 2022
会议地点:
Matsue, JAPAN
会议主办单位:
[Dai, Zhicheng;Zhang, Kui;Wang, Chunran;Chen, Rongjin;Zhu, Fuming] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.
摘要:
It is an important issue to effectively perceive learners' emotional state in the field of smart education, which helps to enhance the interaction between teaching groups and stimulate learners' enthusiasm for learning. Taking "emotion perception" as the theme, this paper retrieved 533 relevant core literature from the CNKI (China National Knowledge Infrastructure) database and used econometric methods and visualization software CiteSpace to analyze the number of literature, authors, institutions, and keywords. The results show that the number of literature published on learners' emotion perception has increased year by year in the past 30 years and is in the mature stage of development; The authors and institutions are relatively scattered, and the core research system of emotion perception has not been formed. Building a multimodal perception model using techniques such as expression recognition, posture recognition, and physiological parameter detection is research hotspots in the field of emotion perception. The research trends in this field are to collect and fuse multimodal emotional data, and deeply analyze the change rule of learners' emotions based on deep learning and data mining.