Search | Engineering

Subscribe Submit

Home Journals Focus Achievement Fronts About Us 中文版

Resource Type

Journal Article 134

Year

2023 14

2022 15

2021 13

2020 11

2019 9

2018 9

2017 9

2016 4

2015 2

2014 4

2013 1

2011 3

2009 2

2007 2

2006 6

2005 4

2004 4

2003 5

2002 5

2001 5

open ︾

Keywords

Computer vision 6

Deep learning 6

Artificial intelligence 4

Knowledge distillation 3

Knowledge graph 2

Knowledge push 2

Machine learning 2

Product design 2

Simultaneous localization and mapping (SLAM) 2

Visual tracking 2

design 2

design science 2

knowledge 2

knowledge acquirement 2

knowledge economy 2

knowledge management 2

3D parametric model 1

3D visual knowledge 1

ACE2 1

open ︾

Search scope:

排序： Display mode:

Miniaturized five fundamental issues about visual knowledge Perspectives

Yun-he Pan,panyh@zju.edu.cn

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 5, Pages 615-766 doi: 10.1631/FITEE.2040000

Abstract: 认知心理学早已指出，人类知识记忆中的重要部分是视觉知识，被用来进行形象思维。因此，基于视觉的人工智能（AI）是AI绕不开的课题，且具有重要意义。本文继《论视觉知识》一文，讨论与之相关的5个基本问题：（1）视觉知识表达；（2）视觉识别；（3）视觉形象思维模拟；（4）视觉知识的学习；（5）多重知识表达。视觉知识的独特优点是具有形象的综合生成能力，时空演化能力和形象显示能力。这些正是字符知识和深度神经网络所缺乏的。AI与计算机辅助设计/图形学/视觉的技术联合将在创造、预测和人机融合等方面对AI新发展提供重要的基础动力。视觉知识和多重知识表达的研究是发展新的视觉智能的关键，也是促进AI 2.0取得重要突破的关键理论与技术。这是一块荒芜、寒湿而肥沃的“北大荒”，也是一块充满希望值得多学科合作勇探的“无人区”。

Keywords：视觉知识表达；视觉识别；视觉形象思维模拟；视觉知识学习；多重知识表达

HTML PDF Collect

Visual knowledge: an attempt to explore machine creativity Perspectives

Yueting Zhuang, Siliang Tang,yzhuang@zju.edu.cn,siliang@zju.edu.cn

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 5, Pages 615-766 doi: 10.1631/FITEE.2100116

Abstract: 长期以来困扰人工智能领域的一个问题是：人工智能是否具有创造力，或者说，算法的推理过程是否可以具有创造性。本文从思维科学的角度探讨人工智能创造力的问题。首先，列举形象思维推理的相关研究；然后，重点介绍一种特殊的视觉知识表示形式，即视觉场景图；最后，详细介绍视觉场景图构造问题与潜在应用。所有证据表明，视觉知识和视觉思维不仅可以改善当前人工智能任务的性能，而且可以用于机器创造力的实践。

Keywords：思维科学；形象思维推理；视觉知识表达；视觉场景图

HTML PDF Collect

Multiple Knowledge Representation of Artificial Intelligence

Yunhe Pan

Engineering 2020, Volume 6, Issue 3, Pages 216-217 doi: 10.1016/j.eng.2019.12.011

HTML PDF Collect

On visual knowledge Perspective

Yun-he PAN

Frontiers of Information Technology & Electronic Engineering 2019, Volume 20, Issue 8, Pages 1021-1025 doi: 10.1631/FITEE.1910001

Abstract: 提出“视觉知识”概念。视觉知识是知识表达的一种新形式. 它与迄今为止人工智能（AI）所用知识表达方法不同. 其中视觉概念具有典型（prototype）与范畴结构、层次结构与动作结构等要素. 视觉概念能构成视觉命题，包括场景结构与动态结构，视觉命题能构成视觉叙事。指出重构计算机图形学成果可实现视觉知识表达及其推理与操作，重构计算机视觉成果可实现视觉知识学习。实现视觉知识表达、推理、学习和应用技术将是AI 2.0取得突破的重要方向之一。

Keywords： None

HTML PDF Collect

Three-dimensional shape space learning for visual concept construction: challenges and research progress Perspective

Xin TONG

Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 9, Pages 1290-1297 doi: 10.1631/FITEE.2200318

Abstract: Human beings can easily categorize three-dimensional (3D) objects with similar shapes and functions into a set of “visual concepts” and learn “visual knowledge” of the surrounding 3D real world (). Developing efficient methods to learn the computational representation of the visual concept and the visual knowledge is a critical task in artificial intelligence (). A crucial step to this end is to learn the shape space spanned by all 3D objects that belong to one visual concept. In this paper, we present the key technical challenges and recent research progress in 3D shape space learning and discuss the open problems and research opportunities in this area.

Keywords：视觉概念；视觉知识；三维几何学习；三维形状空间；三维结构

HTML PDF Collect

Multiple knowledge representation for big data artificial intelligence: framework, applications, and case studies Perspective

Yi Yang, Yueting Zhuang, Yunhe Pan,yangyics@zju.edu.cn,yzhuang@zju.edu.cn,panyh@zju.edu.cn

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 12, Pages 1551-1684 doi: 10.1631/FITEE.2100463

Abstract: In this paper, we present a multiple knowledge representation (MKR) framework and discuss its potential for developing big data artificial intelligence (AI) techniques with possible broader impacts across different AI areas. Typically, canonical knowledge representations and modern representations each emphasize a particular aspect of transforming inputs into symbolic encoding or vectors. For example, knowledge graphs focus on depicting semantic connections among concepts, whereas deep neural networks (DNNs) are more of a tool to perceive raw signal inputs. MKR is an advanced AI representation framework for more complete intelligent functions, such as raw signal perception, feature extraction and vectorization, knowledge symbolization, and logical reasoning. MKR has two benefits: (1) it makes the current AI techniques (dominated by deep learning) more explainable and generalizable, and (2) it expands current AI techniques by integrating MKR to facilitate the mutual benefits of the complementary capacity of each representation, e.g., raw signal perception and symbolic encoding. We expect that MKR research and its applications will drive the evolution of AI 2.0 and beyond.

Keywords：多重知识表达；人工智能；大数据

HTML PDF Collect

Visual recognition of cardiac pathology based on 3D parametric model reconstruction Research Article

Jinxiao XIAO, Yansong LI, Yun TIAN, Dongrong XU, Penghui LI, Shifeng ZHAO, Yunhe PAN

Frontiers of Information Technology & Electronic Engineering 2022, Volume 23, Issue 9, Pages 1324-1337 doi: 10.1631/FITEE.2200102

Abstract: Visual recognition of cardiac images is important for and treatment. Due to the limited availability of annotated datasets, traditional methods usually extract features directly from two-dimensional slices of three-dimensional (3D) heart images, followed by pathological classification. This process may not ensure the overall anatomical consistency in 3D heart. A new method for classification of cardiac pathology is therefore proposed based on reconstruction. First, 3D heart models are reconstructed based on multiple 3D volumes of cardiac imaging data at the end-systole (ES) and end-diastole (ED) phases. Next, based on these reconstructed 3D hearts, s are constructed through the statistical shape model (SSM), and then the heart data are augmented via the variation in shape parameters of one with visual knowledge constraints. Finally, shape and motion features of 3D heart models across two phases are extracted to classify cardiac pathology. Comprehensive experiments on the automated cardiac diagnosis challenge (ACDC) dataset of the Statistical Atlases and Computational Modelling of the Heart (STACOM) workshop confirm the superior performance and efficiency of this proposed approach.

Keywords： 3D visual knowledge 3D parametric model Cardiac pathology diagnosis Data augmentation

HTML PDF Collect

Unsupervised object detection with scene-adaptive concept learning Research Articles

Shiliang Pu, Wei Zhao, Weijie Chen, Shicai Yang, Di Xie, Yunhe Pan,xiedi@hikvision.com

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 5, Pages 615-766 doi: 10.1631/FITEE.2000567

Abstract: Object detection is one of the hottest research directions in computer vision, has already made impressive progress in academia, and has many valuable applications in the industry. However, the mainstream detection methods still have two shortcomings: (1) even a model that is well trained using large amounts of data still cannot generally be used across different kinds of scenes; (2) once a model is deployed, it cannot autonomously evolve along with the accumulated unlabeled scene data. To address these problems, and inspired by theory, we propose a novel scene-adaptive evolution algorithm that can decrease the impact of scene changes through the concept of object groups. We first extract a large number of object proposals from unlabeled data through a pre-trained detection model. Second, we build the dictionary of object concepts by clustering the proposals, in which each cluster center represents an object prototype. Third, we look into the relations between different clusters and the object information of different groups, and propose a graph-based group information propagation strategy to determine the category of an object concept, which can effectively distinguish positive and negative proposals. With these pseudo labels, we can easily fine-tune the pre-trained model. The effectiveness of the proposed method is verified by performing different experiments, and the significant improvements are achieved.

Keywords：视觉知识；无监督视频目标检测；场景自适应学习

HTML PDF Collect

A quantitative attribute-based benchmark methodology for single-target visual tracking Article

Wen-jing KANG, Chang LIU, Gong-liang LIU

Frontiers of Information Technology & Electronic Engineering 2020, Volume 21, Issue 3, Pages 405-421 doi: 10.1631/FITEE.1900245

Abstract: In the past several years, various visual object tracking benchmarks have been proposed, and some of them have been used widely in numerous recently proposed trackers. However, most of the discussions focus on the overall performance, and cannot describe the strengths and weaknesses of the trackers in detail. Meanwhile, several benchmark measures that are often used in tests lack convincing interpretation. In this paper, 12 frame-wise visual attributes that reflect different aspects of the characteristics of image sequences are collated, and a normalized quantitative formulaic definition has been given to each of them for the first time. Based on these definitions, we propose two novel test methodologies, a correlation-based test and a weight-based test, which can provide a more intuitive and easier demonstration of the trackers’ performance for each aspect. Then these methods have been applied to the raw results from one of the most famous tracking challenges, the Video Object Tracking (VOT) Challenge 2017. From the tests, most trackers did not perform well when the size of the target changed rapidly or intensely, and even the advanced deep learning based trackers did not perfectly solve the problem. The scale of the targets was not considered in the calculation of the center location error; however, in a practical test, the center location error is still sensitive to the targets’ changes in size.

Keywords： Visual tracking Performance evaluation Visual attributes Computer vision

HTML PDF Collect

A Framework of Knowledge Theory： Toward a Unified Theory of Information, Knowledge and Intelligence

Zhong Yixin

Strategic Study of CAE 2000, Volume 2, Issue 9, Pages 50-64

Abstract:

Knowledge has been very important wealth to the mankind but there has not a knowledge theory existed yet till the present time. An attempt is thus made in the paper to present a framework of knowledge theory that includes two parts: fundamentals and the main body of knowledge theory. The first part is to deal with a series of basic issues such as the related concepts and definitions, the methods of representation, the measurements, the reasoning and decision rules. The second part is to explore the mechanism of knowledge formation based on information processing and the mechanism of intelligence formation based on the activation of knowledge. It is believed that the establishment of the knowledge theory will lay a solid foundation to the unified theory of information, knowledge, and intelligence and will greatly facilitate the effective utilization of information and knowledge, leading to the growth of the research in the field of intelligent machines.

Keywords： knowledge amount of knowledge knowledge formation knowledge activation unified theory of information-knowledge-intelligence

HTML PDF Collect

Visual commonsense reasoning with directional visual connections Research Articles

Yahong Han, Aming Wu, Linchao Zhu, Yi Yang,yahong@tju.edu.cn

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 5, Pages 615-766 doi: 10.1631/FITEE.2000722

Abstract: To boost research into cognition-level visual understanding, i.e., making an accurate inference based on a thorough understanding of visual details, (VCR) has been proposed. Compared with traditional visual question answering which requires models to select correct answers, VCR requires models to select not only the correct answers, but also the correct rationales. Recent research into human cognition has indicated that brain function or cognition can be considered as a global and dynamic integration of local neuron connectivity, which is helpful in solving specific cognition tasks. Inspired by this idea, we propose a to achieve VCR by dynamically reorganizing the that is contextualized using the meaning of questions and answers and leveraging the directional information to enhance the reasoning ability. Specifically, we first develop a GraphVLAD module to capture to fully model visual content correlations. Then, a contextualization process is proposed to fuse sentence representations with visual neuron representations. Finally, based on the output of , we propose to infer answers and rationales, which includes a ReasonVLAD module. Experimental results on the VCR dataset and visualization analysis demonstrate the effectiveness of our method.

Keywords：视觉常识推理；有向连接网络；视觉神经元连接；情景化连接；有向连接

HTML PDF Collect

Visual Inspection Technology and its Application

Ye Shenghua,Zhu Jigui,Wang Zhong,Yang Xueyou

Strategic Study of CAE 1999, Volume 1, Issue 1, Pages 49-52

Abstract:

Visual inspection, especially, the active visual inspection and passive visual inspection based on triangulation method has advantages of non-contact, rapid speed, flexibility, etc. Visual inspection is a advanced inspection technology, satisfies modern manufacturing demands. This paper discusses the principle of visual inspection, studies several developed applied visual inspection systems, these systems demostrate wide application foreground of visual inspection from different points of view.

Keywords： active visual inspection passive visual inspection inspection system modern manufacturing

HTML PDF Collect

The application and deepening of knowledge management system

Li Hua

Strategic Study of CAE 2011, Volume 13, Issue 8, Pages 87-93

Abstract:

In the knowledge economy era, enterprises begin to realize that the most valuable property is knowledge. Knowledge is not only the key element of production, but also an important means for enterprises to maintain a sustainable competitive advantage. Effectively implementing the knowledge management system should be guided by the correct principles. It is necessary to establish proper organizational structure and business culture for knowledge sharing; meanwhile, during the understanding and implementation of knowledge management, 5 principles of accumulation, trust, sharing, communication and learning must be adhered to. The goal of knowledge management for the organization is to achieve the overall development strategy, hence the knowledge sharing process must make the realization of organizational strategic objective as the prerequisite. The selection of sharing knowledge, building knowledge sharing platform and storage management unit, leading knowledge exchange and implementing incentive policies should be emphasized.

Keywords： knowledge management knowledge sharing knowledge forum

HTML PDF Collect

Development and Prospect of Big Data Knowledge Engineering

Zheng Qinghua, Liu Huan, Gong Tieliang, Zhang Lingling, Liu Jun

Strategic Study of CAE 2023, Volume 25, Issue 2, Pages 208-220 doi: 10.15302/J-SSCAE-2023.02.018

Abstract:

Big Data Knowledge Engineering is the infrastructure of artificial intelligence, a common requirement faced by various industries and fields, and the inevitable path for the digitalization to intelligence. In this paper, we firstly elaborate on the background and connotation of big data knowledge engineering and propose a research framework of “data knowledgeization, knowledge systematization, and knowledge reasoning”. Secondly, we sort out the key technologies of knowledge acquisition and fusion, knowledge representation, and knowledge reasoning and introduce engineering applications in typical scenarios such as smart education, tax risk control, and smart healthcare. Thirdly, we summary the challenges faced by big data knowledge engineering and predict the future research directions including complex big data knowledge acquisition, knowledge+data hybrid learning, and brain-inspired knowledge coding and memorizing. Finally, several suggestions are given by the research: guiding interdisciplinary integration and establishing major and key R&D projects to promote the basic theory and technological breakthroughs of big data knowledge engineering; strengthening communication and cooperation between enterprises and research institutions as well as promoting cutting-edge research results to form application demonstrations, so as to establish an industry-standard system for big data knowledge engineering; exploring school-enterprise cooperation in line with market demands, orienting towards major application needs, and accelerating the landing application of big data knowledge engineering technology in the country's important industries.

Keywords： Big Data Knowledge Engineering Knowledge Acquisition Knowledge Fusion Knowledge Representation Knowledge Reasoning

HTML PDF Collect

Establishing a New Discipline ： Knowledge Systems Engineering

Wang Zhongtuo

Strategic Study of CAE 2006, Volume 8, Issue 12, Pages 1-9

Abstract:

In this paper, the establishment of a new discipline, knowledge systems engineering, and the mission and contents of this new discipline are described. The architectures of the knowledge systems are suggested and the working processes are analyzed. Some new concepts about the creation of new knowledge are put forward.

Keywords： knowledge management systems engineering knowledge systems engineering innovation knowledge integration