相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article
Computer Science, Hardware & Architecture
Peining Zhen et al.
Summary: This study proposes a compact and fast neural network-based action recognition accelerator for high-performance action recognition on mobile devices. By compressing and optimizing the LSTM model, the system achieves comparable classification accuracy to other methods on multiple datasets.
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS
(2023)
Review
Computer Science, Hardware & Architecture
Xiankai Huang et al.
Summary: This paper summarizes and analyzes existing video action recognition methods based on 3D convolution to help new researchers understand this field. Firstly, it introduces the classical methods and points out the problems. Then, it summarizes the existing improved methods and compares the experimental results on benchmarks, discussing current challenges and future trends.
COMPUTERS & ELECTRICAL ENGINEERING
(2023)
Review
Automation & Control Systems
Pranjal Kumar et al.
Summary: The use of artificial intelligence in medicine is revolutionizing current procedures in healthcare. However, there are concerns about trust, ethics, and integration of this technology. This paper aims to provide researchers with a comprehensive understanding of AI and its medical applications, as well as the challenges associated with its large-scale integration.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Automation & Control Systems
Yassine Himeur et al.
Summary: Developing automated video surveillance systems (VSSs) is crucial for ensuring population security, especially in events involving large crowds. Deep transfer learning (DTL) and deep domain adaptation (DDA) are promising solutions to improve the performance of machine learning (ML) and deep learning (DL) models in VSSs by transferring knowledge and overcoming data scarcity problems.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Engineering, Electrical & Electronic
Hanbo Wu et al.
Summary: This paper proposes a novel multi-level channel attention excitation (MCAE) module to model temporal-related channel attention at both frame and video levels, enhancing the performance of video-based human action recognition task.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2023)
Article
Computer Science, Artificial Intelligence
Ming Zong et al.
Summary: This paper proposes a four-stream network based on spatial and temporal saliency, including appearance stream, motion stream, spatial saliency stream, and temporal saliency stream. Multi-task learning based LSTM is adopted to capture long-term dependency relationships between consecutive frames. Experimental results demonstrate that the proposed network outperforms state-of-the-art methods on three popular action recognition datasets.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Roshan Singh et al.
Summary: This paper discusses the progress and approaches in human action identification from videos, focusing on both hand-crafted feature based approach and automatic feature extraction approach. By analyzing various methods based on methodology, accuracy, classifier, and datasets, this paper provides different levels and options for activity detection.
COGNITIVE SYSTEMS RESEARCH
(2023)
Article
Engineering, Electrical & Electronic
Jincan Deng et al.
Summary: In this paper, a syntax-guided hierarchical attention network (SHAN) is proposed to generate video captions by integrating visual and sentence-context features. Experimental results demonstrate that the proposed method achieves comparable performance with current methods.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Information Systems
Linchao Zhu et al.
Summary: In this paper, a novel method called Temporal Cross-Layer Correlation (TCLC) framework is proposed for action recognition. The framework explores temporal correlations among neighboring frames, assists cross-layer spatio-temporal feature learning, and integrates features with contextual knowledge using cross-layer attention and center-guided attention mechanism.
IEEE TRANSACTIONS ON MULTIMEDIA
(2022)
Article
Computer Science, Artificial Intelligence
Sravani Yenduri et al.
Summary: The study presents a dynamic kernel-based approach for effective recognition of fine-grained actions by extracting local spatio-temporal features and analyzing them using a Gaussian mixture model. Kernels are built to find the similarity between fine-grained actions by mapping the statistics to the kernel feature space, and the effectiveness of the proposed method is demonstrated through experiments.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Artificial Intelligence
Zhouning Du et al.
Summary: This paper discusses human action recognition using a dual-stream architecture and linear dynamical systems approach. The proposed method is competitive and efficient, as validated through experiments on different datasets.
APPLIED INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Yu Kong et al.
Summary: This paper surveys the state-of-the-art techniques in action recognition and prediction, covering existing models, popular algorithms, technical difficulties, popular action databases, evaluation protocols, and promising future directions.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2022)
Article
Computer Science, Artificial Intelligence
Kok Seang Tan et al.
Summary: Long Short-Term Memory networks play a significant role in human action recognition. This study proposes a method called Bidirectional Long Short-Term Memory with Temporal Dense Sampling and Fusion Network to address the challenges in existing human action recognition. Experimental results show that this method outperforms state-of-the-art methods on two datasets.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Automation & Control Systems
Xuelong Li et al.
Summary: The precise location information of road and lane lines is crucial for autonomous and assisted driving, but detection inaccuracies are common. To address this, an attention-based spatial segmentation network has been proposed to improve network understanding of spatial information, effectively enhancing the performance of traffic scene understanding.
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Computer Science, Information Systems
Pengpeng Hu et al.
Summary: This paper proposes a deep learning algorithm called 3DBodyNet for rapidly reconstructing the 3D shape of human bodies using a single commodity depth camera. The algorithm is easy to use and only requires two depth images, while being insensitive to pose variations.
IEEE TRANSACTIONS ON MULTIMEDIA
(2022)
Article
Computer Science, Artificial Intelligence
Preksha Pareek et al.
Summary: This paper discusses various machine learning and deep learning techniques used for Human Action Recognition (HAR) from 2011 to 2019, investigates the characteristics of public datasets, and introduces various action recognition techniques and their applications.
ARTIFICIAL INTELLIGENCE REVIEW
(2021)
Article
Computer Science, Artificial Intelligence
Amin Ullah et al.
Summary: This paper proposes a lightweight deep learning-assisted framework for activity recognition, which detects and tracks humans in surveillance videos using CNN models, and learns temporal changes in frame sequences for activity recognition using DS-GRU. Experimental results demonstrate the efficiency of this technique for real-time surveillance applications.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Theory & Methods
Khan Muhammad et al.
Summary: This study introduces a novel approach combining BiLSTM and DCNN with an attention mechanism to effectively recognize different human actions in videos, improving the performance of video-based action classification.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2021)
Article
Computer Science, Artificial Intelligence
Farhat Afza et al.
Summary: This article proposes an action recognition technique based on features fusion and best feature selection, achieving high recognition rates on multiple famous datasets. The experimental results demonstrate the superior performance of the proposed scheme compared to listed methods.
IMAGE AND VISION COMPUTING
(2021)
Article
Computer Science, Information Systems
Ramna Maqsood et al.
Summary: This study provides an effective framework for recognizing different real-world anomalies from videos by training 3D ConvNets on the UCF Crime video dataset. The findings suggest that 3D ConvNets can improve generalizing competencies and achieve better results by learning frame-level information and applying spatial augmentation. The proposed approach outperforms state-of-the-art methods in terms of accuracy on anomalous activity recognition, achieving an 82% AUC.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Li Zhang et al.
Summary: The research proposes an ensemble model of evolving deep networks comprising Convolutional Neural Networks (CNNs) and bidirectional Long Short-Term Memory (BLSTM) networks using a swarm intelligence (SI) algorithm to determine optimal hyper-parameters for accurate representation of temporal dynamics of human actions. The SI algorithm incorporates hybrid crossover operators and a versatile search process to overcome stagnation, showing superiority over other methods for solving high-dimensional optimization functions.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Robotics
Md Mofijul Islam et al.
Summary: This study presents a multimodal graphical attention-based human activity recognition approach, Multi-GAT, which hierarchically learns complementary multimodal features and outperforms other HAR algorithms, especially in noisy environments.
IEEE ROBOTICS AND AUTOMATION LETTERS
(2021)
Article
Computer Science, Artificial Intelligence
Jun-Yan He et al.
Summary: A novel deep learning model is proposed in this paper to capture spatial and temporal patterns of human actions from videos, utilizing methods such as sample representation learner, Densely-connected Bi-directional LSTM network, and fusion of appearance and motion modalities. These techniques improve the effectiveness and robustness of long-range action recognition, leading to promising performance surpassing existing approaches in benchmark datasets UCF101 and HMDB51.
Article
Computer Science, Artificial Intelligence
Hayat Ullah et al.
Summary: This study introduces a lightweight convolutional neural network, LD-Net, for reconstructing hazy images and proposes a color visibility restoration method to overcome weather challenges. Extensive experiments validate the superiority of the proposed method in image dehazing techniques and object detection tasks.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Computer Science, Information Systems
Salah Al-Obaidi et al.
Summary: In this paper, a method based on handcrafted features is proposed to analyze neuromorphic vision sensor data streams for human action recognition. The method outperformed existing methods in terms of accuracy rates for different datasets.
Article
Computer Science, Artificial Intelligence
Mahshid Majd et al.
Article
Computer Science, Artificial Intelligence
Cheng Dai et al.
APPLIED SOFT COMPUTING
(2020)
Article
Computer Science, Information Systems
Imad Rida et al.
MULTIMEDIA TOOLS AND APPLICATIONS
(2020)
Article
Computer Science, Artificial Intelligence
Zufan Zhang et al.
Article
Computer Science, Information Systems
Sheng Yu et al.
Article
Computer Science, Artificial Intelligence
Limin Wang et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2019)
Article
Computer Science, Artificial Intelligence
Haodong Yang et al.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2019)
Article
Computer Science, Theory & Methods
Amin Ullah et al.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2019)
Article
Engineering, Electrical & Electronic
Chih-Yao Ma et al.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2019)
Article
Automation & Control Systems
Amin Ullah et al.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2019)
Article
Computer Science, Artificial Intelligence
Sijie Song et al.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2018)
Article
Computer Science, Information Systems
Yu-Gang Jiang et al.
IEEE TRANSACTIONS ON MULTIMEDIA
(2018)
Article
Computer Science, Information Systems
Xuanhan Wang et al.
IEEE TRANSACTIONS ON MULTIMEDIA
(2018)
Article
Computer Science, Information Systems
Wenhui Li et al.
Article
Computer Science, Artificial Intelligence
An-An Liu et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2017)
Article
Computer Science, Artificial Intelligence
M. S. Ryoo et al.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2016)
Article
Computer Science, Artificial Intelligence
Kishore K. Reddy et al.
MACHINE VISION AND APPLICATIONS
(2013)