CAAI International Conference on Artificial Intelligence最新文献

Concealed Object Segmentation with Hierarchical Coherence Modeling 利用层次一致性建模进行隐蔽物体分割

CAAI International Conference on Artificial Intelligence Pub Date : 2024-01-22 DOI: 10.48550/arXiv.2401.11767

Fengyang Xiao, Pan Zhang, Chunming He, Runze Hu, Yutao Liu

引用次数: 2

Physical Logic Enhanced Network for Small-Sample Bi-Layer Metallic Tubes Bending Springback Prediction 小样本双层金属管弯曲回弹预测的物理逻辑增强网络

CAAI International Conference on Artificial Intelligence Pub Date : 2022-09-20 DOI: 10.48550/arXiv.2209.09870

Chang Sun, Zili Wang, Shuyou Zhang, Le Wang, Jianrong Tan

{"title":"Physical Logic Enhanced Network for Small-Sample Bi-Layer Metallic Tubes Bending Springback Prediction","authors":"Chang Sun, Zili Wang, Shuyou Zhang, Le Wang, Jianrong Tan","doi":"10.48550/arXiv.2209.09870","DOIUrl":"https://doi.org/10.48550/arXiv.2209.09870","url":null,"abstract":"Bi-layer metallic tube (BMT) plays an extremely crucial role in engineering applications, with rotary draw bending (RDB) the high-precision bending processing can be achieved, however, the product will further springback. Due to the complex structure of BMT and the high cost of dataset acquisition, the existing methods based on mechanism research and machine learning cannot meet the engineering requirements of springback prediction. Based on the preliminary mechanism analysis, a physical logic enhanced network (PE-NET) is proposed. The architecture includes ES-NET which equivalent the BMT to the single-layer tube, and SP-NET for the final prediction of springback with sufficient singlelayer tube samples. Specifically, in the first stage, with the theory-driven preexploration and the data-driven pretraining, the ES-NET and SP-NET are constructed, respectively. In the second stage, under the physical logic, the PE-NET is assembled by ES-NET and SP-NET and then fine-tuned with the small sample BMT dataset and composite loss function. The validity and stability of the proposed method are verified by the FE simulation dataset, the small-sample dataset BMT springback angle prediction is achieved, and the method potential in interpretability and engineering applications are demonstrated.","PeriodicalId":155654,"journal":{"name":"CAAI International Conference on Artificial Intelligence","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132698702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Scene Text Recognition with Single-Point Decoding Network 场景文本识别与单点解码网络

CAAI International Conference on Artificial Intelligence Pub Date : 2022-09-05 DOI: 10.48550/arXiv.2209.01914

Lei Chen, Haibo Qin, Shi-Xue Zhang, Chun Yang, Xucheng Yin

{"title":"Scene Text Recognition with Single-Point Decoding Network","authors":"Lei Chen, Haibo Qin, Shi-Xue Zhang, Chun Yang, Xucheng Yin","doi":"10.48550/arXiv.2209.01914","DOIUrl":"https://doi.org/10.48550/arXiv.2209.01914","url":null,"abstract":", Abstract. In recent years, attention-based scene text recognition methods have been very popular and attracted the interest of many researchers. Attention-based methods can adaptively focus attention on a small area or even single point during decoding, in which the attention matrix is nearly one-hot distribution. Furthermore, the whole feature maps will be weighted and summed by all attention matrices during inference, caus-ing huge redundant computations. In this paper, we propose an eﬃcient attention-free Single-Point Decoding Network (dubbed SPDN) for scene text recognition, which can replace the traditional attention-based decoding network. Speciﬁcally, we propose Single-Point Sampling Module (SPSM) to eﬃciently sample one key point on the feature map for decoding one character. In this way, our method can not only precisely locate the key point of each character but also remove redundant computations. Based on SPSM, we design an eﬃcient and novel single-point decoding network to replace the attention-based decoding network. Extensive experiments on publicly available benchmarks verify that our SPDN can greatly improve decoding eﬃciency without sacriﬁcing performance.","PeriodicalId":155654,"journal":{"name":"CAAI International Conference on Artificial Intelligence","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132240387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Cross-Camera Deep Colorization 跨相机深着色

CAAI International Conference on Artificial Intelligence Pub Date : 2022-08-26 DOI: 10.48550/arXiv.2209.01211

Yaping Zhao, Haitian Zheng, Mengqi Ji, Ruqi Huang

引用次数: 3

Chinese Word Sense Embedding with SememeWSD and Synonym Set 基于SememeWSD和同义词集的汉语词义嵌入

CAAI International Conference on Artificial Intelligence Pub Date : 2022-06-29 DOI: 10.48550/arXiv.2206.14388

Yangxi Zhou, Junping Du, Zhe Xue, Ang Li, Zeli Guan

引用次数: 3

PHN: Parallel heterogeneous network with soft gating for CTR prediction PHN:用于CTR预测的软门控并行异构网络

CAAI International Conference on Artificial Intelligence Pub Date : 2022-06-18 DOI: 10.48550/arXiv.2206.09184

Ri-Qi Su, Alphonse Houssou Hounye, Cong Cao, Muzhou Hou

{"title":"PHN: Parallel heterogeneous network with soft gating for CTR prediction","authors":"Ri-Qi Su, Alphonse Houssou Hounye, Cong Cao, Muzhou Hou","doi":"10.48550/arXiv.2206.09184","DOIUrl":"https://doi.org/10.48550/arXiv.2206.09184","url":null,"abstract":"The Click-though Rate (CTR) prediction task is a basic task in recommendation system. Most of the previous researches of CTR models built based on Wide &deep structure and gradually evolved into parallel structures with different modules. However, the simple accumulation of parallel structures can lead to higher structural complexity and longer training time. Based on the Sigmoid activation function of output layer, the linear addition activation value of parallel structures in the training process is easy to make the samples fall into the weak gradient interval, resulting in the phenomenon of weak gradient, and reducing the effectiveness of training. To this end, this paper proposes a Parallel Heterogeneous Network (PHN) model, which constructs a network with parallel structure through three different interaction analysis methods, and uses Soft Selection Gating (SSG) to feature heterogeneous data with different structure. Finally, residual link with trainable parameters are used in the network to mitigate the influence of weak gradient phenomenon. Furthermore, we demonstrate the effectiveness of PHN in a large number of comparative experiments, and visualize the performance of the model in training process and structure.","PeriodicalId":155654,"journal":{"name":"CAAI International Conference on Artificial Intelligence","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114865372","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Dual Windows Are Significant: Learning from Mediastinal Window and Focusing on Lung Window 双窗意义重大:从纵隔窗学，从肺窗学

CAAI International Conference on Artificial Intelligence Pub Date : 2022-06-08 DOI: 10.48550/arXiv.2206.03803

Qiuli Wang, Xin Tan, Chen Liu

{"title":"Dual Windows Are Significant: Learning from Mediastinal Window and Focusing on Lung Window","authors":"Qiuli Wang, Xin Tan, Chen Liu","doi":"10.48550/arXiv.2206.03803","DOIUrl":"https://doi.org/10.48550/arXiv.2206.03803","url":null,"abstract":"Since the pandemic of COVID-19, several deep learning methods were proposed to analyze the chest Computed Tomography (CT) for diagnosis. In the current situation, the disease course classification is significant for medical personnel to decide the treatment. Most previous deep-learning-based methods extract features observed from the lung window. However, it has been proved that some appearances related to diagnosis can be observed better from the mediastinal window rather than the lung window, e.g., the pulmonary consolidation happens more in severe symptoms. In this paper, we propose a novel Dual Window RCNN Network (DWRNet), which mainly learns the distinctive features from the successive mediastinal window. Regarding the features extracted from the lung window, we introduce the Lung Window Attention Block (LWA Block) to pay additional attention to them for enhancing the mediastinal-window features. Moreover, instead of picking up specific slices from the whole CT slices, we use a Recurrent CNN and analyze successive slices as videos. Experimental results show that the fused and representative features improve the predictions of disease course by reaching the accuracy of 90.57%, against the baseline with an accuracy of 84.86%. Ablation studies demonstrate that combined dual window features are more efficient than lung-window features alone, while paying attention to lung-window features can improve the model's stability. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.","PeriodicalId":155654,"journal":{"name":"CAAI International Conference on Artificial Intelligence","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123010298","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Transformer-based Network for Deformable Medical Image Registration 变形医学图像配准的一种基于变压器的网络

CAAI International Conference on Artificial Intelligence Pub Date : 2022-02-24 DOI: 10.1007/978-3-031-20497-5_41

Yibo Wang, W. Qian, Xuming Zhang

引用次数: 7

Dynamic Clustering Federated Learning for Non-IID Data 非iid数据的动态聚类联邦学习

CAAI International Conference on Artificial Intelligence Pub Date : 2022-01-01 DOI: 10.1007/978-3-031-20503-3_10

Ming Chen, Jinze Wu, Yu Yin, Zhenya Huang, Qi Liu, Enhong Chen

引用次数: 0

Cross-domain Trajectory Prediction with CTP-Net 基于CTP-Net的跨域轨迹预测

CAAI International Conference on Artificial Intelligence Pub Date : 2021-10-22 DOI: 10.1007/978-3-031-20497-5_7

Pingxuan Huang, Zhenhua Cui, Jing Li, Shenghua Gao, Bo Hu, Yanyan Fang

引用次数: 2