Article
Computer Science, Artificial Intelligence
Shervin Minaee, Yuri Y. Boykov, Fatih Porikli, Antonio J. Plaza, Nasser Kehtarnavaz, Demetri Terzopoulos
Summary: This article provides a comprehensive review of recent literature on the importance of image segmentation in computer vision and image processing, and the methods of utilizing deep learning models for image segmentation. It introduces various DL-based segmentation models and their relationships, strengths, and challenges, and discusses research directions.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Mang Ye, Jianbing Shen, Gaojie Lin, Tao Xiang, Ling Shao, Steven C. H. Hoi
Summary: Person re-identification (Re-ID) has gained significant interest in the computer vision community, with the advancement of deep neural networks. It is categorized into closed-world and open-world settings. While closed-world setting has achieved inspiring success, the research focus has shifted to the more challenging open-world setting. We summarize the open-world Re-ID in five different aspects and introduce a new evaluation metric. This metric provides an additional criteria for evaluating Re-ID systems in real applications.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Jiankang Deng, Jia Guo, Jing Yang, Niannan Xue, Irene Kotsia, Stefanos Zafeiriou
Summary: In this paper, the authors propose an Additive Angular Margin Loss (ArcFace) to enhance the discriminative power in face recognition. They also introduce the sub-center ArcFace method to address label noise. Additionally, they explore the inverse problem of mapping feature vectors to face images.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Shaoxiong Ji, Shirui Pan, Erik Cambria, Pekka Marttinen, Philip S. Yu
Summary: This survey provides a comprehensive review of knowledge graphs, covering topics such as knowledge graph representation learning, knowledge acquisition and completion, temporal knowledge graphs, and knowledge-aware applications. The study proposes a categorization and taxonomies on these topics, as well as explores emerging themes like metarelational learning, commonsense reasoning, and temporal knowledge graphs. Additionally, the research offers curated data sets and open-source libraries to facilitate future research in the field of knowledge graphs.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Laith Abualigah, Mohamed Abd Elaziz, Putra Sumari, Zong Woo Geem, Amir H. Gandomi
Summary: The paper introduces a novel nature-inspired meta-heuristic optimizer, RSA, based on the hunting behavior of crocodiles. Through implementing two main steps of crocodile behavior, RSA shows unique search methods compared to existing algorithms, and achieves better results in various test functions and engineering problems.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Guillermo Gallego, Tobi Delbruck, Garrick Michael Orchard, Chiara Bartolozzi, Brian Taba, Andrea Censi, Stefan Leutenegger, Andrew Davison, Jorg Conradt, Kostas Daniilidis, Davide Scaramuzza
Summary: This paper provides a comprehensive overview of event-based vision, focusing on the applications and algorithms developed for event cameras. Event cameras differ from traditional cameras in their asynchronous measurement of per-pixel brightness changes, offering high temporal resolution, very high dynamic range, low power consumption, and high pixel bandwidth. The paper discusses techniques for processing events, including learning-based methods and specialized processors. It also highlights the remaining challenges and opportunities in the field of bio-inspired perception and interaction for machines.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Han Xu, Jiayi Ma, Junjun Jiang, Xiaojie Guo, Haibin Ling
Summary: This study proposes a novel unified and unsupervised end-to-end image fusion network, U2Fusion, which can solve different fusion problems. By training the model with adaptive information preservation, the network avoids the requirements of previous image fusion methods and has broad applicability. Moreover, a new dataset RoadScene is released for evaluation and comparison.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Geochemistry & Geophysics
Danfeng Hong, Zhu Han, Jing Yao, Lianru Gao, Bing Zhang, Antonio Plaza, Jocelyn Chanussot
Summary: The article introduces a novel HS image classification network called SpectralFormer, which utilizes the transformers framework to learn spectral sequence information, achieving better classification performance than traditional methods and exhibiting high flexibility.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Engineering, Electrical & Electronic
Zhengxia Zou, Keyan Chen, Zhenwei Shi, Yuhong Guo, Jieping Ye
Summary: Object detection, a fundamental problem in computer vision, has received significant attention in recent years. This article reviews the rapid technological evolution of object detection over the past two decades and its impact on the entire computer vision field. It covers various topics such as milestone detectors, datasets, metrics, fundamental building blocks, speedup techniques, and state-of-the-art methods.
PROCEEDINGS OF THE IEEE
(2023)
Article
Computer Science, Artificial Intelligence
Zewen Li, Fan Liu, Wenjie Yang, Shouheng Peng, Jun Zhou
Summary: This review provides insights into the development history of CNN, a overview of various convolutions, introduction to classic and advanced CNN models, conclusions drawn from experimental analysis, rules of thumb for function and hyperparameter selection, and applications of 1-D, 2-D, and multidimensional convolutions. Moreover, it also discusses open issues and promising directions for CNN as guidelines for future work.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Matthias De Lange, Rahaf Aljundi, Marc Masana, Sarah Parisot, Xu Jia, Ales Leonardis, Greg Slabaugh, Tinne Tuytelaars
Summary: This article introduces the application of artificial neural networks in continual learning, focusing on task incremental classification. It proposes a new framework for continually evaluating the stability-plasticity trade-off of the network and performs experimental comparisons of 11 state-of-the-art continual learning methods, evaluating their strengths and weaknesses by considering different benchmark datasets.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Timothy Hospedales, Antreas Antoniou, Paul Micaelli, Amos Storkey
Summary: The field of meta-learning, or learning-to-learn, has gained significant interest in recent years. Unlike conventional approaches to AI, meta-learning aims to improve the learning algorithm itself by utilizing multiple learning experiences. This provides an opportunity to address challenges in deep learning, including data and computation limitations, as well as generalization.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Yongming Li, Yanjun Liu, Shaocheng Tong
Summary: This article presents an adaptive neural network output feedback optimized control design for strict-feedback nonlinear systems with unknown internal dynamics. By constructing optimal cost functions for subsystems and using the actor-critic architecture, virtual and actual optimal controllers are developed to ensure the boundedness of all closed-loop signals. The proposed strategy also guarantees that system states are always confined within some preselected compact sets.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Engineering, Civil
B. Ravi Kiran, Ibrahim Sobh, Victor Talpaert, Patrick Mannion, Ahmad A. Al Sallab, Senthil Yogamani, Patrick Perez
Summary: This paper summarizes deep reinforcement learning algorithms, provides a taxonomy of automated driving tasks, discusses key computational challenges in real world deployment of autonomous driving agents, and explores adjacent domains as well as the role of simulators in training agents.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Hongyang Gao, Shuiwang Ji
Summary: This research focuses on representation learning for graph data. A graph U-Net model is proposed, and novel graph pooling and unpooling operations are introduced to address the challenges of applying encoder-decoder architectures on graph data. Experimental results demonstrate that the proposed methods achieve better performance in node classification and graph classification tasks, and the integration of attention mechanisms further enhances the capability of the methods.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Kai Han, Yunhe Wang, Hanting Chen, Xinghao Chen, Jianyuan Guo, Zhenhua Liu, Yehui Tang, An Xiao, Chunjing Xu, Yixing Xu, Zhaohui Yang, Yiman Zhang, Dacheng Tao
Summary: Transformer, a deep neural network with a self-attention mechanism, has been initially used in natural language processing and is now gaining attention in computer vision tasks. Transformer-based models perform as well as or even better than convolutional and recurrent neural networks in various visual benchmarks. This paper reviews vision transformer models, categorizes them based on different tasks, and analyzes their advantages and disadvantages. The discussed categories include backbone network, high/mid-level vision, low-level vision, and video processing. Efficient methods for applying transformer in real device-based applications are also explored. The challenges and further research directions for vision transformers are discussed as well.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Jing Li, Aixin Sun, Jianglei Han, Chenliang Li
Summary: This paper provides a comprehensive review of existing deep learning techniques for named entity recognition (NER), including NER resources, categorization methods, and recent applied techniques. The paper introduces the basics of NER systems and outlines future research directions and challenges in the field.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)
Article
Computer Science, Artificial Intelligence
Xiao Liu, Fanjin Zhang, Zhenyu Hou, Li Mian, Zhaoyu Wang, Jing Zhang, Jie Tang
Summary: Deep supervised learning has been successful, but it is limited by manual labels and vulnerable to attacks. In contrast, self-supervised learning utilizes input data as supervision, showing promising performance on representation learning. This survey comprehensively reviews self-supervised learning methods in computer vision, natural language processing, and graph learning.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Jun Yu, Min Tan, Hongyuan Zhang, Dacheng Tao, Yong Rui
Summary: This paper proposes a method to predict the click feature of an image from visual features by integrating sparse constraints and an improved RELU operator. The method learns from an auxiliary image dataset containing click information to discover the hierarchy of word semantics. Experimental results show that the method achieves higher recognition accuracy, larger compression ratio, and good one-shot learning ability and scalability to unseen categories.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Yu Zhang, Qiang Yang
Summary: This paper provides a survey of Multi-Task Learning (MTL) from the perspective of algorithmic modeling, applications, and theoretical analyses. It discusses different MTL algorithms and their characteristics, as well as the combination of MTL with other learning paradigms. The paper also reviews MTL models for large-scale tasks or high-dimensional data, as well as dimensionality reduction and feature hashing. Real-world applications of MTL are examined, and theoretical analyses and future directions are discussed.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)