Article
Computer Science, Information Systems
Muhammad Kamran Afzal, Jibril Muhammad Adam, H. M. Rehan Afzal, Yu Zang, Saifullahi Aminu Bello, Cheng Wang, Jonathan Li
Summary: Feature normalization is crucial in CNNs, and this paper proposes a revised softmax loss function based on scaled cosine similarity, which shows significant improvements on several datasets.
INFORMATION SCIENCES
(2022)
Article
Engineering, Electrical & Electronic
Haonan Zhang, Longjun Liu, Hengyi Zhou, Liang Si, Hongbin Sun, Nanning Zheng
Summary: This paper proposes a three-phase hierarchical pruning framework (FCHP) that utilizes discriminative features in FMs and feature correlation between two adjacent layers for efficient network pruning. The experiments show that FCHP achieves superior compression performance compared to other methods on different benchmarks and architectures.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Information Systems
Shi Luo, Xiongfei Li, Xiaoli Zhang
Summary: The goal of this research is to improve face detection performance by extending the sampling range of face aspect ratio. We propose a Wide Aspect Ratio Matching (WARM) strategy and a feature enhancement module called Receptive Field Diversity (RFD) to capture more representative features of extreme aspect ratio faces. Extensive experiments show the effectiveness of our method on various benchmarks.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Tao Lu, Qiang Zhou, Wenhua Fang, Yanduo Zhang
Summary: The CASNN algorithm is a context-aware Siamese neural network designed to enhance the discriminative feature representation ability in face verification tasks. By utilizing a context-aware module and center-classification loss, CASNN effectively compresses intra-class features and enhances inter-class features.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Yuxiang Zhou, Lejian Liao, Yang Gao, Heyan Huang
Summary: This paper investigates the capability of convolutional neural networks in text analysis and proposes two modules to enhance the discriminative power and feature extraction ability of vanilla CNN models. Validation tests on benchmark datasets show competitive performance, and visualization on upgrade filters and pooling features confirms the effectiveness of the proposed model.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
Tobias Schlagenhauf, Yiwen Lin, Benjamin Noack
Summary: This work proposes a novel method that forces a set of base models to learn different features for a classification task, which can improve the classification accuracy. Experimental results demonstrate the effectiveness of this method.
MACHINE VISION AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Yi-Xiang Luo, Jiann-Liang Chen
Summary: This study introduces a Dual Attention Forgery Detection Network that embeds two attention mechanisms to identify traces of tampering in fake videos. The proposed DAFDN outperforms other methods in two benchmark datasets, DFDC and FaceForensics++.
Article
Computer Science, Artificial Intelligence
Lu Ding, Yong Wang, Robert Laganiere, Dan Huang, Xinbin Luo, Huanlong Zhang
Summary: This paper proposes a dynamic selection scheme to adaptively adjust receptive field size in multispectral pedestrian detection, showing superior performance than existing methods through empirical evaluations.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Engineering, Electrical & Electronic
Lisha Cui, Xiaoheng Jiang, Mingliang Xu, Wanqing Li, Pei Lv, Bing Zhou
Summary: SDDNet addresses the challenges in surface defect detection, such as large texture variation and small defect size, by introducing a feature retaining block and skip densely connected module. Extensive experiments have demonstrated the effectiveness of SDDNet for real-time industrial applications.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Computer Science, Artificial Intelligence
Wei Liu, Irtiza Hasan, Shengcai Liao
Summary: Traditional object detection methods require tedious bounding box configurations. This paper proposes a novel approach that treats object detection as a high-level semantic feature detection task, simplifying it to a center and scale prediction task. The proposed method considerably reduces the difficulty in training and configuration, and achieves competitive accuracy in benchmark tests.
PATTERN RECOGNITION
(2023)
Article
Computer Science, Artificial Intelligence
Cian Ryan, Brian O'Sullivan, Amr Elrasad, Aisling Cahill, Joe Lemley, Paul Kielty, Christoph Posch, Etienne Perot
Summary: Event cameras are neuromorphic vision sensors that capture local-light intensity changes, offering advantages such as low energy consumption and high temporal resolution. This paper introduces a novel method for driver monitoring using event cameras, featuring a unique network architecture and a synthetic dataset called Neuromorphic-HELEN.
Article
Computer Science, Artificial Intelligence
Xiangwei Zheng, Xiaomei Yu, Yongqiang Yin, Tiantian Li, Xiaoyan Yan
Summary: The paper proposes an emotion recognition method based on three-dimensional feature maps and CNNs, which improves the accuracy of emotion recognition through steps such as calibration, segmentation, feature extraction, and CNN design. Experimental results demonstrate that the proposed method has better classification accuracy than state-of-the-art methods.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Biao Cai, Mingyue Wang, Yongkeng Chen, Yanmei Hu, Mingzhe Liu
Summary: Community detection is important in complex networks, and MFF-Net is a novel multi-feature fusion network that improves the performance of community detection by using comprehensive feature representations.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Agriculture, Multidisciplinary
Zhi Weng, Fansheng Meng, Shaoqing Liu, Yong Zhang, Zhiqiang Zheng, Caili Gong
Summary: A cattle face recognition model based on a two-branch convolutional neural network is proposed in this paper, which achieves high recognition accuracy of cattle faces through image inputs from different angles, feature fusion, and the use of global average pooling layer.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2022)
Article
Engineering, Electrical & Electronic
Feng Li, QingGang Xi
Summary: This article introduces a new defect detection network, DefectNet, which combines a shared weight binary classification network and a detection network to solve the problem of defect data detection. Experimental results confirm its effectiveness in improving detection speed and performance of CNN-based object detection networks.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
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.