Article
Computer Science, Information Systems
Guanchen Ding, Daiqin Yang, Tao Wang, Sihan Wang, Yunfei Zhang
Summary: This paper proposes a cross-domain learning network to address domain gaps between different data sets. The network consists of MFD, DFA, and CVB modules to process features effectively and improve network performance.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)
Article
Computer Science, Artificial Intelligence
He Li, Junge Zhang, Weihang Kong, Jienan Shen, Yuguang Shao
Summary: This paper explores the aggregated multi-scale context in both the modality-specific and modality-shared feature extraction, and designs SCAA and SCFA modules for feature extraction and fusion, achieving state-of-the-art RGB-T counting performance.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Weihong Ren, Xinchao Wang, Jiandong Tian, Yandong Tang, Antoni B. Chan
Summary: The paper proposes a new MOT paradigm tailored for crowded scenes, simultaneously finding global optimal detections and trajectories of multiple targets over the whole video, yielding promising results on public benchmarks in various domains.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2021)
Article
Computer Science, Information Systems
Bo Li, Yong Zhang, Chengyang Zhang, Xinglin Piao, Baocai Yin
Summary: Weakly supervised crowd counting faces two primary challenges: the large variation of head size and uneven distribution of crowd density. To address these issues, we propose a novel Hypergraph Association Crowd Counting (HACC) framework. Our approach includes a new multi-scale dilated pyramid module to handle head size variation and a novel hypergraph association module to solve the problem of uneven crowd density distribution.
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Chenfeng Xu, Dingkang Liang, Yongchao Xu, Song Bai, Wei Zhan, Xiang Bai, Masayoshi Tomizuka
Summary: This paper introduces a new method for addressing the issue in density maps, and proposes a Learning to Scale (L2S) module to normalize dense regions, improving pattern shifts and long-tailed distribution of density values. Additionally, it explores a novel localization method and optimized cross-entropy loss for localization-based crowd counting. Experimental results demonstrate that the proposed framework achieves competitive performance across various benchmarks.
INTERNATIONAL JOURNAL OF COMPUTER VISION
(2022)
Article
Computer Science, Information Systems
Li Yang, Yanqun Guo, Jun Sang, Weiqun Wu, Zhongyuan Wu, Qi Liu, Xiaofeng Xia
Summary: This paper proposes an improved crowd counting method by combining a small network as a new component with the existing CSRNet, which significantly improves the counting performance. The effectiveness of the method is demonstrated through experiments on multiple datasets. The future work will explore applying this method to other networks.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Hardware & Architecture
Lixian Yuan, Yandong Chen, Hefeng Wu, Wentao Wan, Pei Chen
Summary: The growing demands for crowd security and commercial applications have brought attention to crowd counting, a computer vision task aiming to count persons in an image. Existing crowd counting methods face challenges in complex scenarios. To address this, the Localization Guided Transformer (LGT) framework is proposed, leveraging knowledge from localization-based methods to improve density map estimation for accurate crowd counting. Experimental results demonstrate the effectiveness of the proposed framework.
COMPUTERS & ELECTRICAL ENGINEERING
(2022)
Article
Engineering, Electrical & Electronic
Anran Zhang, Jun Xu, Xiaoyan Luo, Xianbin Cao, Xiantong Zhen
Summary: This paper proposes a Cross-Domain Attention Network (CDANet) for solving the complex crowd counting problem in real-world datasets. By introducing the Cross-Domain Attention Module (CDAM) and consistency penalty, the method achieves competitive results in unsupervised synthetic-to-realistic and realistic-to-realistic UDACC tasks.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2022)
Article
Computer Science, Information Systems
Xiaoheng Jiang, Li Zhang, Tianzhu Zhang, Pei Lv, Bing Zhou, Yanwei Pang, Mingliang Xu, Changsheng Xu
Summary: In this study, a novel density-aware convolutional neural network (DensityCNN) method is proposed to perform crowd counting by learning density-level classification and density map estimation. Extensive experiments demonstrate the high effectiveness of the proposed method across multiple datasets.
IEEE TRANSACTIONS ON MULTIMEDIA
(2021)
Article
Computer Science, Artificial Intelligence
Shihui Zhang, Wei Wang, Weibo Zhao, Lei Wang, Qunpeng Li
Summary: This paper proposes a cross-modal crowd counting method that effectively fuses information between different modalities using CNN and a novel cross-modal transformer, improving the accuracy and robustness of crowd counting in unconstrained scenes.
IMAGE AND VISION COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Joey Tianyi Zhou, Le Zhang, Du Jiawei, Xi Peng, Zhiwen Fang, Zhe Xiao, Hongyuan Zhu
Summary: This paper proposes a method to address the issue of imbalanced data distribution in crowd counting datasets by introducing locality-aware data partition and augmentation. The proposed method demonstrates its effectiveness and superiority through extensive experiments.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Li Dong, Haijun Zhang, Jianghong Ma, Xiaofei Xu, Yimin Yang, Q. M. Jonathan Wu
Summary: In this article, a new network model called CLRNet is proposed for generating high-quality crowd density maps in videos for crowd counting. By introducing a cross locality relation module and a scene consistency attention map, this model can better model the local dependencies between pixels and enhance the features, resulting in improved accuracy.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Interdisciplinary Applications
Xiangyu Guo, Mingliang Gao, Wenzhe Zhai, Jianrun Shang, Qilei Li
Summary: This article presents a spatial-frequency attention network (SFANet) for crowd counting. By utilizing a bottleneck spatial attention module and a multispectral channel attention module, SFANet achieves state-of-the-art performance in crowd counting tasks.
Article
Computer Science, Information Systems
Jiyeoup Jeong, Jongwon Choi, Dae Ung Jo, Jin Young Choi
Summary: This paper proposes a novel congestion-aware Bayesian loss method that considers both the person-scale and crowd-sparsity, which greatly improves the accuracy of crowd density estimation. The estimated person-scale and crowd-sparsity are utilized to enhance the supervising representation of the point annotations, achieving state-of-the-art performance in various experiments.
Article
Computer Science, Artificial Intelligence
Shihui Zhang, He Li, Weihang Kong
Summary: This paper presents a novel cross-modal fusion based approach for RGB-D crowd counting, achieving superior performance compared to state-of-the-art methods in crowd counting and density estimation. By modeling global and local contexts and utilizing cross-modal interactions, the proposed approach learns more abundant deep representations for various scenes, especially congested ones, showing comparable performance in RGB crowd counting task.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Xin Zeng, Yunpeng Wu, Shizhe Hu, Ruobin Wang, Yangdong Ye
EXPERT SYSTEMS WITH APPLICATIONS
(2020)
Article
Computer Science, Artificial Intelligence
Gaoyi Zhu, Xin Zeng, Xiangjie Jin, Jun Zhang
Summary: In this study, a novel method called DT-CNN is proposed for metro passenger counting and density estimation. By combining a feature extraction module and a feature recovery module, high-quality density maps are generated to accurately estimate passenger counts in highly congested metro scenes. Extensive experiments show that the proposed method achieves superior performance compared to other state-of-the-art methods.
KNOWLEDGE AND INFORMATION SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Xin Zeng, Qiang Guo, Haoran Duan, Yunpeng Wu
Summary: The proposed approach introduces a multi-level features extraction network with a gating mechanism to adaptively extract features in different levels and fully aggregate features via multi-level fusion, achieving state-of-the-art counting performance against other methods.
IET IMAGE PROCESSING
(2021)
Article
Computer Science, Artificial Intelligence
Youwei Wang, Chengying Zhu, Qiang Guo, Yangdong Ye
Summary: The identification of railway safety risk is crucial for continuous and stable railway operations. Current works often overlook the important relation between detected objects and suffer from poor domain semantics, leading to degraded performance in understanding railway text. To address these challenges, this study proposes a Domain Semantics-Enhanced Relation Extraction (DSERE) model that utilizes triple knowledge from a knowledge graph to model railway safety risk and introduces domain semantics-enhanced transformer and piece-wise convolution neural networks to improve the understanding and classification of domain text. Experimental results on a real-world dataset of China Railway south zone demonstrate the superiority of the DSERE model, achieving an AUC of 81.84% and F1 score of 76.00%.
COMPLEX & INTELLIGENT SYSTEMS
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Yiqiao Mao, Xiaoqiang Yan, Qiang Guo, Yangdong Ye
Summary: A novel deep mutual information maximin (DMIM) method is proposed for cross-modal clustering, aiming to preserve shared information of multiple modalities while eliminating superfluous information of individual modalities. Extensive experimental results demonstrate its superiority over state-of-the-art methods on various datasets.
THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE
(2021)
Article
Computer Science, Artificial Intelligence
Hao Yang, Min Wang, Zhengfei Yu, Hang Zhang, Jinshen Jiang, Yun Zhou
Summary: In this paper, a novel method called CSTTA is proposed for test time adaptation (TTA), which utilizes confidence-based optimization and sample reweighting to better utilize sample information. Extensive experiments demonstrate the effectiveness of the proposed method.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Jin Liu, Ju-Sheng Mi, Dong-Yun Niu
Summary: This article focuses on a novel method for generating a canonical basis for decision implications based on object-induced operators (OE operators). The logic of decision implication based on OE operators is described, and a method for obtaining the canonical basis for decision implications is given. The completeness, nonredundancy, and optimality of the canonical basis are proven. Additionally, a method for generating true premises based on OE operators is proposed.
KNOWLEDGE-BASED SYSTEMS
(2024)
Review
Computer Science, Artificial Intelligence
Kun Bu, Yuanchao Liu, Xiaolong Ju
Summary: This paper discusses the importance of sentiment analysis and pre-trained models in natural language processing, and explores the application of prompt learning. The research shows that prompt learning is more suitable for sentiment analysis tasks and can achieve good performance.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Xiangjun Cai, Dagang Li
Summary: This paper presents a new decomposition mechanism based on learned decomposition mapping. By using a neural network to learn the relationship between original time series and decomposed results, the repetitive computation overhead during rolling decomposition is relieved. Additionally, extended mapping and partial decomposition methods are proposed to alleviate boundary effects on prediction performance. Comparative studies demonstrate that the proposed method outperforms existing RDEMs in terms of operation speed and prediction accuracy.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Xu Wu, Yang Liu, Jie Tian, Yuanpeng Li
Summary: This paper proposes a blockchain-based privacy-preserving trust management architecture, which adopts federated learning to train task-specific trust models and utilizes differential privacy to protect device privacy. In addition, a game theory-based incentive mechanism and a parallel consensus protocol are proposed to improve the accuracy of trust computing and the efficiency of consensus.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Zaiyang Yu, Prayag Tiwari, Luyang Hou, Lusi Li, Weijun Li, Limin Jiang, Xin Ning
Summary: This study introduces a 3D view-based approach that effectively handles occlusions and leverages the geometric information of 3D objects. The proposed method achieves state-of-the-art results on occluded ReID tasks and exhibits competitive performance on holistic ReID tasks.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Yongliang Shi, Runyi Yang, Zirui Wu, Pengfei Li, Caiyun Liu, Hao Zhao, Guyue Zhou
Summary: Neural implicit representations have gained attention due to their expressive, continuous, and compact properties. However, there is still a lack of research on city-scale continual implicit dense mapping based on sparse LiDAR input. In this study, a city-scale continual neural mapping system with a panoptic representation is developed, incorporating environment-level and instance-level modeling. A tailored three-layer sampling strategy and category-specific prior are proposed to address the challenges of representing geometric information in city-scale space and achieving high fidelity mapping of instances under incomplete observation.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Ruihan Hu, Zhi-Ri Tang, Rui Yang, Zhongjie Wang
Summary: Mesh data is crucial for 3D computer vision applications worldwide, but traditional deep learning frameworks have struggled with handling meshes. This paper proposes MDSSN, a simple mesh computation framework that models triangle meshes and represents their shape using face-based and edge-based Riemannian graphs. The framework incorporates end-to-end operators inspired by traditional deep learning frameworks, and includes dedicated modules for addressing challenges in mesh classification and segmentation tasks. Experimental results demonstrate that MDSSN outperforms other state-of-the-art approaches.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Buliao Huang, Yunhui Zhu, Muhammad Usman, Huanhuan Chen
Summary: This paper proposes a novel semi-supervised conditional normalizing flow (SSCFlow) algorithm that combines unsupervised imputation and supervised classification. By estimating the conditional distribution of incomplete instances, SSCFlow facilitates imputation and classification simultaneously, addressing the issue of separated tasks ignoring data distribution and label information in traditional methods.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Deeksha Varshney, Asif Ekbal, Erik Cambria
Summary: This paper focuses on the neural-based interactive dialogue system that aims to engage and retain humans in long-lasting conversations. It proposes a new neural generative model that combines step-wise co-attention, self-attention-based transformer network, and an emotion classifier to control emotion and knowledge transfer during response generation. The results from quantitative, qualitative, and human evaluation show that the proposed models can generate natural and coherent sentences, capturing essential facts with significant improvement over emotional content.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Junchen Ye, Weimiao Li, Zhixin Zhang, Tongyu Zhu, Leilei Sun, Bowen Du
Summary: Modeling multivariate time series has long been a topic of interest for scholars in various fields. This paper introduces MvTS, an open library based on Pytorch, which provides a unified framework for implementing and evaluating these models. Extensive experiments on public datasets demonstrate the effectiveness and universality of the models reproduced by MvTS.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Reham R. Mostafa, Ahmed M. Khedr, Zaher Al Aghbari, Imad Afyouni, Ibrahim Kamel, Naveed Ahmed
Summary: Feature selection is crucial in classification procedures, but it faces challenges in high-dimensional datasets. To overcome these challenges, this study proposes an Adaptive Hybrid-Mutated Differential Evolution method that incorporates the mechanics of the Spider Wasp Optimization algorithm and the concept of Enhanced Solution Quality. Experimental results demonstrate the effectiveness of the method in terms of accuracy and convergence speed, and it outperforms contemporary cutting-edge algorithms.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Ti Xiang, Pin Lv, Liguo Sun, Yipu Yang, Jiuwu Hao
Summary: This paper introduces a Track Classification Model (TCM) based on marine radar, which can effectively recognize and classify shipping tracks. By using a feature extraction network with multi-feature fusion and a dataset production method to address missing labels, the classification accuracy is improved, resulting in successful engineering application in real scenarios.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Zhihao Zhang, Yuan Zuo, Chenghua Lin, Junjie Wu
Summary: This paper proposes a novel unsupervised context-aware quality phrase mining framework called LMPhrase, which is built upon large pre-trained language models. The framework mines quality phrases as silver labels using a parameter-free probing technique on the pre-trained language model BERT, and formalizes the phrase tagging task as a sequence generation problem by fine-tuning on the Sequence to-Sequence pre-trained language model BART. The results of extensive experiments show that LMPhrase consistently outperforms existing competitors in two different granularity phrase mining tasks.
KNOWLEDGE-BASED SYSTEMS
(2024)
Article
Computer Science, Artificial Intelligence
Kemal Buyukkaya, M. Ozan Karsavuran, Cevdet Aykanat
Summary: The study aims to investigate the hybrid parallelization of the Stochastic Gradient Descent (SGD) algorithm for solving the matrix completion problem on a high-performance computing platform. A hybrid parallel decentralized SGD framework with asynchronous inter-process communication and a novel flexible partitioning scheme is proposed to achieve scalability up to hundreds of processors. Experimental results on real-world benchmark datasets show that the proposed algorithm achieves 6x higher throughput on sparse datasets compared to the state-of-the-art, while achieving comparable throughput on relatively dense datasets.
KNOWLEDGE-BASED SYSTEMS
(2024)
