Article
Computer Science, Artificial Intelligence
Qing Gao, Jinguo Liu, Zhaojie Ju
Summary: In this paper, a method based on multimodal data fusion and multiscale parallel convolutional neural network is proposed to improve the accuracy and reliability of hand gesture recognition. Experiments on a self-made database verified the effectiveness and superiority of the method, which was also successfully applied to a seven-degree-of-freedom bionic manipulator for robotic manipulation using hand gestures.
Article
Computer Science, Artificial Intelligence
Yair A. Andrade-Ambriz, Sergio Ledesma, Mario-Alberto Ibarra-Manzano, Marvella Oros-Flores, Dora-Luz Almanza-Ojeda
Summary: A temporal convolutional neural network method is proposed for analyzing and recognizing human activities using spatio-temporal features, achieving improved accuracy in classification results through optimal use of computational resources, and providing real-time classification results.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Dazhuo Wang, Jianfei Yang, Wei Cui, Lihua Xie, Sumei Sun
Summary: The article proposes a multimodal channel state information-based activity recognition system, which uses generative adversarial networks and semi-supervised learning to address performance degradation in WiFi human recognition systems due to environmental dynamics. Experimental results demonstrate that the system performs well in multiple experimental settings, overcoming environmental dynamics and outperforming existing HAR systems.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Artificial Intelligence
Chhavi Dixit, Shashank Mouli Satapathy
Summary: This project aims to develop an efficient real-time multimodal emotion recognition model for analyzing emotion expression in human oration videos. Different models were trained for text, audio, images, and multimodal analysis using separate datasets. The models were tested and combined on the CMU-MOSEI dataset to find the most effective architecture. The proposed architecture achieved high accuracy and F1-score on the CMU-MOSEI dataset.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Information Systems
Yasin Kaya, Elif Kevser Topuz
Summary: Smart devices with sensors enable continuous measurement of daily activities, leading to various experiments in human activity recognition (HAR) to convert data into physical activity types. HAR has wide applications in research areas like health assessment, living systems, sports, and security. This study focuses on sensor-based activity recognition and presents a new 1D-CNN deep learning approach. The model was evaluated on three datasets, achieving high accuracy rates ranging from 94.8% to 98%.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Bruce X. B. Yu, Yan Liu, Xiang Zhang, Sheng-hua Zhong, Keith C. C. Chan
Summary: This article proposes a model-based multimodal network (MMNet) that fuses skeleton and RGB modalities in order to improve ensemble recognition accuracy by effectively applying mutually complementary information from different data modalities. Experimental results show that the proposed MMNet outperforms state-of-the-art approaches on five benchmark datasets, effectively capturing mutually complementary features in different RGB-D video modalities and providing more discriminative features for human action recognition.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Yang Xing, Stuart Golodetz, Aluna Everitt, Andrew Markham, Niki Trigoni
Summary: This study proposes a two-stream multiscale human activity recognition and anticipation network, which is optimized using multitask learning and temporal-channel attention fusion approach to enhance the model's representation ability for both temporal and spatial features.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Automation & Control Systems
Jamie Roche, Varuna De-Silva, Joosep Hook, Mirco Moencks, Ahmet Kondoz
Summary: The task of detecting and recognizing human actions has increasingly been delegated to neural network processing camera or wearable sensor data. To overcome limitations of single modality data, researchers have explored ways to apply convolutional neural networks to 3-D data and proposed a framework to tackle human activity recognition using sensor fusion and multimodal machine learning. The proposed method, evaluated on a custom captured multimodal dataset, demonstrated highly accurate human activity classification (90%).
IEEE TRANSACTIONS ON CYBERNETICS
(2022)
Article
Engineering, Electrical & Electronic
Tanvir Mahmud, A. Q. M. Sazzad Sayyed, Shaikh Anowarul Fattah, Sun-Yuan Kung
Summary: The article introduces a novel multi-stage training approach to enhance diversity in feature extraction process for accurate action recognition. This method utilizes various transformations on time series data to obtain diversified feature representations, achieving outstanding performance on publicly available datasets.
IEEE SENSORS JOURNAL
(2021)
Article
Environmental Sciences
Mingjie Qian, Song Sun, Xianju Li
Summary: The study proposed a 3M-CNN model for fine land cover classification in complex landscapes using multimodal remote sensing data and multiscale kernel-based approach. Experimental results showed that the model achieved excellent overall accuracies on different satellite images and outperformed other comparative models, particularly in visual performance. Overall, the proposed process benefited the fine land cover classification of complex landscape areas.
Article
Computer Science, Artificial Intelligence
Diego Teran-Pineda, Karl Thurnhofer-Hemsi, Enrique Dominguez
Summary: Human activity recognition is a machine learning application that aims to identify activities based on activity raw data collected by different sensors. In medicine, doctors often analyze human gait to detect abnormalities and determine possible treatments. This research proposes a novel methodology that improves human activity classification based on accelerometer data and reduces the complexity of feature extraction from multimodal sensors.
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS
(2023)
Article
Computer Science, Software Engineering
Hend Basly, Wael Ouarda, Fatma Ezahra Sayadi, Bouraoui Ouni, Adel M. Alimi
Summary: This paper introduces a deep temporal residual system for enhancing human activity recognition performance, combining a deep residual convolutional neural network with long short-term memory neural network for improved spatiotemporal feature representation.
Article
Engineering, Electrical & Electronic
Ying Li, Junsheng Wu, Weigang Li, Aiqing Fang, Wei Dong
Summary: The sensor-based human activity recognition (SHAR) task aims to recognize signals collected by sensors in intelligent devices to assist people in their daily lives. Deep learning is being studied for combining with SHAR. To address the challenge of maintaining efficiency, an effective sensor signal representation method, called the temporal-spatial dynamic convolutional network, is presented. Extensive experiments demonstrate the superiority of this method over deep learning baselines and existing SHAR works on benchmark SHAR datasets.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Computer Science, Artificial Intelligence
Dimitrios Koutrintzes, Evaggelos Spyrou, Eirini Mathe, Phivos Mylonas
Summary: In this paper, a multimodal approach for video-based human activity recognition (HAR) is proposed. It involves transforming 3D visual data into six different 2D image representations and extracting visual features using convolutional neural networks. The extracted features are then used for classification using a support vector machine. The proposed approach outperforms other state-of-the-art methods in most experiments.
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Ehab Essa, Islam R. Abdelmaksoud
Summary: This paper proposes two novel architectures, CSNet and TCCSNet, for classifying sequences of human activity data from different sensors. The proposed models outperform other modern approaches, such as Transformers and LSTM based models.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Carlos Caetano, Sandra Avila, William Robson Schwartz, Silvio Jamil F. Guimaraes, Arnaldo de A. Araujo
Article
Computer Science, Artificial Intelligence
Luciana dos Santos Belo, Carlos Antonio Caetano, Zenilton Kleber Goncalves do Patrocinio, Silvio Jamil Ferzoli Guimaraes
Article
Engineering, Electrical & Electronic
Rensso Victor Hugo Mora Colque, Carlos Caetano, Matheus Toledo Lustosa de Andrade, William Robson Schwartz
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2017)
Article
Computer Science, Information Systems
Carlos Caetano, Victor H. C. de Melo, Francois Bremond, Jefersson A. dos Santos, William Robson Schwartz
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Gabriel R. Goncalves, Jessica Sena, William Robson Schwartz, Carlos Antonio Caetano
Summary: Object detection is a widely studied topic in computer vision research and is essential for systems involving visual scene understanding. As technology advances, more challenging issues in object detection, such as class-agnostic object detection, have emerged. This paper addresses the task of class-agnostic object detection using a convolutional network and texture graylevel quantization. The results show a significant improvement compared to the baseline in detecting objects without determining their classes.
2022 35TH SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Carlos Caetano, Francois Bremond, William Robson Schwartz
2019 32ND SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Victor H. C. Melo, Jesimon B. Santos, Carlos Caetano, Jessica Sena, Otavio A. B. Penatti, William Robson Schwartz
PROCEEDINGS 2018 31ST SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Carlos Caetano, Victor H. C. de Melo, Jefersson A. dos Santos, William Robson Schwartz
2017 30TH SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Rensso Victor Hugo Mora Colque, Carlos Antonio Caetano Junior, William Robson Schwartz
2015 28TH SIBGRAPI CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES
(2015)
Proceedings Paper
Computer Science, Artificial Intelligence
Luciana Belo, Carlos Caetano, Zenilton Patrocinio, Silvio Guimaraes
2014 IEEE 26TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI)
(2014)
Proceedings Paper
Engineering, Electrical & Electronic
Carlos Caetano, Sandra Avila, Silvio Guimaraes, Arnaldo de A. Araujo
2014 PROCEEDINGS OF THE 22ND EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO)
(2014)
Article
Computer Science, Artificial Intelligence
Rui Lv, Dingheng Wang, Jiangbin Zheng, Zhao-Xu Yang
Summary: In this paper, the authors investigate tensor decomposition for neural network compression. They analyze the convergence and precision of tensor mapping theory, validate the rationality of tensor mapping and its superiority over traditional tensor approximation based on the Lottery Ticket Hypothesis. They propose an efficient method called 3D-KCPNet to compress 3D convolutional neural networks using the Kronecker canonical polyadic (KCP) tensor decomposition. Experimental results show that 3D-KCPNet achieves higher accuracy compared to the original baseline model and the corresponding tensor approximation model.
Article
Computer Science, Artificial Intelligence
Xiangkun He, Zhongxu Hu, Haohan Yang, Chen Lv
Summary: In this paper, a novel constrained multi-objective reinforcement learning algorithm is proposed for personalized end-to-end robotic control with continuous actions. The approach trains a single model using constraint design and a comprehensive index to achieve optimal policies based on user-specified preferences.
Article
Computer Science, Artificial Intelligence
Zhijian Zhuo, Bilian Chen, Shenbao Yu, Langcai Cao
Summary: In this paper, a novel method called Expansion with Contraction Method for Overlapping Community Detection (ECOCD) is proposed, which utilizes non-negative matrix factorization to obtain disjoint communities and applies expansion and contraction processes to adjust the degree of overlap. ECOCD is applicable to various networks with different properties and achieves high-quality overlapping community detection.
Article
Computer Science, Artificial Intelligence
Yizhe Zhu, Chunhui Zhang, Jialin Gao, Xin Sun, Zihan Rui, Xi Zhou
Summary: In this work, the authors propose a Contrastive Spatio-Temporal Distilling (CSTD) approach to improve the detection of high-compressed deepfake videos. The approach leverages spatial-frequency cues and temporal-contrastive alignment to fully exploit spatiotemporal inconsistency information.
Review
Computer Science, Artificial Intelligence
Laijin Meng, Xinghao Jiang, Tanfeng Sun
Summary: This paper provides a review of coverless steganographic algorithms, including the development process, known contributions, and general issues in image and video algorithms. It also discusses the security of coverless steganography from theoretical analysis to actual investigation for the first time.
Article
Computer Science, Artificial Intelligence
Yajie Bao, Tianwei Xing, Xun Chen
Summary: Visual question answering requires processing multi-modal information and effective reasoning. Neural-symbolic learning is a promising method, but current approaches lack uncertainty handling and can only provide a single answer. To address this, we propose a confidence based neural-symbolic approach that evaluates NN inferences and conducts reasoning based on confidence.
Article
Computer Science, Artificial Intelligence
Anh H. Vo, Bao T. Nguyen
Summary: Interior style classification is an interesting problem with potential applications in both commercial and academic domains. This project proposes a method named ISC-DeIT, which combines data-efficient image transformer architectures and knowledge distillation, to address the interior style classification problem. Experimental results demonstrate a significant improvement in predictive accuracy compared to other state-of-the-art methods.
Article
Computer Science, Artificial Intelligence
Shashank Kotyan, Danilo Vasconcellos Vargas
Summary: This article introduces a novel augmentation technique called Dynamic Scanning Augmentation to improve the accuracy and robustness of Vision Transformer (ViT). The technique leverages dynamic input sequences to adaptively focus on different patches, resulting in significant changes in ViT's attention mechanism. Experimental results demonstrate that Dynamic Scanning Augmentation outperforms ViT in terms of both robustness to adversarial attacks and accuracy against natural images.
Article
Computer Science, Artificial Intelligence
Hiba Alqasir, Damien Muselet, Christophe Ducottet
Summary: The article proposes a solution to improve the learning process of a classification network by providing shape priors, reducing the need for annotated data. The solution is tested on cross-domain digit classification tasks and a video surveillance application.
Article
Computer Science, Artificial Intelligence
Dexiu Ma, Mei Liu, Mingsheng Shang
Summary: This paper proposes a method using neural dynamics solvers to solve infinity-norm optimization problems. Two improved solvers are constructed and their effectiveness and superiority are demonstrated through theoretical analysis and simulation experiments.
Article
Computer Science, Artificial Intelligence
Francesco Gregoretti, Giovanni Pezzulo, Domenico Maisto
Summary: Active Inference is a computational framework that uses probabilistic inference and variational free energy minimization to describe perception, planning, and action. cpp-AIF is a header-only C++ library that provides a powerful tool for implementing Active Inference for Partially Observable Markov Decision Processes through multi-core computing. It is cross-platform and improves performance, memory management, and usability compared to existing software.
Article
Computer Science, Artificial Intelligence
Zelin Ying, Dawei Cheng, Cen Chen, Xiang Li, Peng Zhu, Yifeng Luo, Yuqi Liang
Summary: This paper proposes a novel stock market trends prediction framework called SMART, which includes a self-supervised stock technical data sequence embedding model S3E. By training with multiple self-supervised auxiliary tasks, the model encodes stock technical data sequences into embeddings and uses the learned sequence embeddings for predicting stock market trends. Extensive experiments on China A-Shares market and NASDAQ market prove the high effectiveness of our model in stock market trends prediction, and its effectiveness is further validated in real-world applications in a leading financial service provider in China.
Article
Computer Science, Artificial Intelligence
Hao Li, Hao Jiang, Dongsheng Ye, Qiang Wang, Liang Du, Yuanyuan Zeng, Liu Yuan, Yingxue Wang, C. Chen
Summary: DHGAT1, a dynamic hyperbolic graph attention network, utilizes hyperbolic metric properties to embed dynamic graphs. It employs a spatiotemporal self-attention mechanism and weighted node representations, resulting in excellent performance in link prediction tasks.
Article
Computer Science, Artificial Intelligence
Jiehui Huang, Zhenchao Tang, Xuedong He, Jun Zhou, Defeng Zhou, Calvin Yu-Chian Chen
Summary: This study proposes a progressive learning multi-scale feature blending model for image deraining tasks. The model utilizes detail dilation and texture extraction to improve the restoration of rainy images. Experimental results show that the model achieves near state-of-the-art performance in rain removal tasks and exhibits better rain removal realism.
Article
Computer Science, Artificial Intelligence
Lizhi Liu, Zilin Gao, Yinhe Wang, Yongfu Li
Summary: This paper proposes a novel discrete-time interconnected model for depicting complex dynamical networks. The model consists of nodes and edges subsystems, which consider the dynamic characteristic of both nodes and edges. By designing control strategies and coupling modes, the stabilization and synchronization of the network are achieved. Simulation results demonstrate the effectiveness of the proposed methods.