標(biāo)題: Titlebook: Artificial Intelligence; Third CAAI Internati Lu Fang,Jian Pei,Ruiping Wang Conference proceedings 2024 The Editor(s) (if applicable) and T [打印本頁(yè)] 作者: Garfield 時(shí)間: 2025-3-21 18:09
書目名稱Artificial Intelligence影響因子(影響力)
作者: intention 時(shí)間: 2025-3-21 21:49
Blind Adversarial Training: Towards Comprehensively Robust Models Against Blind Adversarial Attacksning. Most existing AT approaches can be grouped into restricted and unrestricted approaches. Restricted AT requires a prescribed uniform budget for AEs during training, with the obtained results showing high sensitivity to the budget. In contrast, unrestricted AT uses unconstrained AEs, and these o作者: 咽下 時(shí)間: 2025-3-22 02:58
TOAC: Try-On Aligning Conformer for?Image-Based Virtual Try-On Alignmentof portraits. Image-based virtual try-on generally consists of two steps: Image-based Virtual Try-on Alignment and Image-based Virtual Try-on Generation. In this paper, we focus on Image-based Virtual Try-on Alignment (IVTA), which plays a pivotal role in virtual try-on and aligns the target garment作者: 專心 時(shí)間: 2025-3-22 07:24
GIST: Transforming Overwhelming Information into Structured Knowledge with Large Language Models language models to analyze and organize the information, generating structured results, including summaries, key points, and questions and answers. The system also utilizes a multimodal information processing approach to enhance comprehension of the content. As the user’s knowledge base grows, GIST作者: GROG 時(shí)間: 2025-3-22 10:36
AIGCIQA2023: A Large-Scale Image Quality Assessment Database for?AI Generated Images: From the?Perspniques, AI-based image generation has been applied to various fields. However, AI Generated Images (AIGIs) may have some unique distortions compared to natural images, thus many generated images are not qualified for real-world applications. Consequently, it is important and significant to study sub作者: 共同給與 時(shí)間: 2025-3-22 16:14
TST: Time-Sparse Transducer for?Automatic Speech Recognitiones a great memory footprint and computing time when processing a long decoding sequence. To solve this problem, we propose a model named time-sparse transducer, which introduces a time-sparse mechanism into transducer. In this mechanism, we obtain the intermediate representations by reducing the tim作者: jabber 時(shí)間: 2025-3-22 17:14
Enhancing Daily Life Through an?Interactive Desktop Robotics Systemlarge language models and performing a variety of desktop-related tasks. The robot’s capabilities include organizing cluttered objects on tables, such as dining tables or office desks, placing them into storage cabinets, as well as retrieving specific items from drawers upon request. This paper prov作者: Foreknowledge 時(shí)間: 2025-3-22 21:36 作者: 閃光你我 時(shí)間: 2025-3-23 01:58
A Weakly Supervised Learning Method for Recognizing Childhood Tic Disordersy. In this work, we focus on weakly supervised learning methods for recognizing childhood tic disorders. In situations with limited data availability, we design a relative probability metric based on the characteristics of the data and a multi-phase learning algorithm is proposed based on relative p作者: 裁決 時(shí)間: 2025-3-23 07:23
Detecting Software Vulnerabilities Based on?Hierarchical Graph Attention Networkcation or regression models from the source code to detect vulnerabilities, which require lots of high-quality labeled vulnerabilities. However, high-quality labeled vulnerabilities are not easy to be obtained in practical applications. To alleviate this problem, we present an effective and unsuperv作者: lethal 時(shí)間: 2025-3-23 11:28 作者: Abduct 時(shí)間: 2025-3-23 15:11
Ensemble Learning with?Time Accumulative Effect for?Early Diagnosis of?Alzheimer’s Diseaseession. The existing early diagnosis algorithms for AD ignore the distinct time accumulative effect seen in chronic diseases and do not address the problem of adaptation of multi-source heterogeneous data to a single learner. We use the idea of ensemble learning to train multi-source heterogeneous d作者: Costume 時(shí)間: 2025-3-23 18:19 作者: altruism 時(shí)間: 2025-3-23 23:58
A Novel Online Multi-label Feature Selection Approach for?Multi-dimensional Streaming Datacan efficiently deal with the single-dimensional variation of a multi-label information system. However, multi-dimensional variations often occur in real-time streaming applications. Based on the improved Fisher score model for multi-label learning and feature redundancy analysis using symmetric unc作者: Factorable 時(shí)間: 2025-3-24 03:17 作者: 不法行為 時(shí)間: 2025-3-24 08:32
R. Gerlach,J. Hannappel,B. Heinrichs,M. Grawducer is close to RNN-T and the real-time factor is 50.00% of the original. By adjusting the time resolution, the time-sparse transducer can also reduce the real-time factor to 16.54% of the original at the expense of a 4.94% loss of precision.作者: 千篇一律 時(shí)間: 2025-3-24 14:22
presentation based on hierarchical graph attention network. Finally, we obtain vulnerabilities by applying an outlier detection algorithm on the low-dimensional representation. We carry out extensive experiments on six datasets and the effectiveness of our proposed method is demonstrated by the experimental results.作者: 迅速成長(zhǎng) 時(shí)間: 2025-3-24 17:19
TST: Time-Sparse Transducer for?Automatic Speech Recognitionducer is close to RNN-T and the real-time factor is 50.00% of the original. By adjusting the time resolution, the time-sparse transducer can also reduce the real-time factor to 16.54% of the original at the expense of a 4.94% loss of precision.作者: 小母馬 時(shí)間: 2025-3-24 20:30
Detecting Software Vulnerabilities Based on?Hierarchical Graph Attention Networkpresentation based on hierarchical graph attention network. Finally, we obtain vulnerabilities by applying an outlier detection algorithm on the low-dimensional representation. We carry out extensive experiments on six datasets and the effectiveness of our proposed method is demonstrated by the experimental results.作者: 火海 時(shí)間: 2025-3-25 02:20 作者: Carcinoma 時(shí)間: 2025-3-25 04:38 作者: 誹謗 時(shí)間: 2025-3-25 08:59 作者: 節(jié)省 時(shí)間: 2025-3-25 12:30 作者: Inflamed 時(shí)間: 2025-3-25 17:50 作者: 分離 時(shí)間: 2025-3-25 23:08 作者: Tremor 時(shí)間: 2025-3-26 02:21 作者: ATRIA 時(shí)間: 2025-3-26 06:18
Immunologische Aktivit?t der Lymphozytenn combined using the decision fusion approach. Experimental results demonstrate that our algorithmic framework attains an average accuracy of 75.75% and the time accumulative effect also benefits our model.作者: MORPH 時(shí)間: 2025-3-26 10:05
Enhancing Daily Life Through an?Interactive Desktop Robotics Systemrithms, and manipulation techniques. Through real-world experiments and user evaluations, we demonstrate the effectiveness and practicality of our robotic companion in assisting individuals with everyday desktop tasks.作者: HALO 時(shí)間: 2025-3-26 16:03 作者: 精致 時(shí)間: 2025-3-26 20:52 作者: outer-ear 時(shí)間: 2025-3-26 22:24
Conference proceedings 2024 China, in July 2023.?CICAI is a summit forum in the field of artificial intelligence and the 2023 forum was hosted by Chinese Association for Artificial Intelligence (CAAI). The 100 papers were thoroughly reviewed and selected from 376 submissions.?CICAI 2023 conference covers a wide range of of AI作者: bromide 時(shí)間: 2025-3-27 04:04
Hans van Haut,Heinrich Stratmanncausal structures. Leveraging the perspective of SCM, we propose a framework called FairDR, which utilizes the Hirschfeld-Gebelein-Rényi (HGR) correlation to accurately recover the distribution of both fairly and unfairly treated data. FairDR can serve as a pre-processing method for other fair machi作者: collateral 時(shí)間: 2025-3-27 09:22
estimate a nonuniform budget to modify the AEs used in training, ensuring that the strengths of the AEs are dynamically located in a reasonable range and ultimately improving the comprehensive robustness of the AT model. We include a theoretical investigation on a toy classification problem to guar作者: 惡名聲 時(shí)間: 2025-3-27 10:48
Fluoranreicherung in Pflanzenorganen, comprehensively extract both global patterns and local details. Secondly, we propose a robust learned perceptual loss between generative reconstructed garment images and the ground truth to alleviate the overlap problem. Extensive experiments demonstrate the superiority of our proposed model compar作者: plasma-cells 時(shí)間: 2025-3-27 13:57
H.-W. Radeke,N. Jaeger,J. Vogel,L. Weissbachassess the human visual preferences for each image from three perspectives including ., . and .. Finally, based on this large-scale database, we conduct a benchmark experiment to evaluate the performance of several state-of-the-art IQA metrics on our constructed database. The AIGCIQA2023 database an作者: FLING 時(shí)間: 2025-3-27 20:01 作者: febrile 時(shí)間: 2025-3-27 23:13 作者: 不怕任性 時(shí)間: 2025-3-28 06:02
Antik?rper-vermittelte überempfindlichkeitres are used to enhance the feature map of each scale. Finally, we fuse the upsampled results of all scales on UNet to improve the performance of segmentation. Our method achieves 0.9432, 0.8948, 0.9348 for mDice, mIoU and mACC on the ISIC2016 dataset, and 0.9058, 0.8138, 0.8968 on the ISIC2018 data作者: Buttress 時(shí)間: 2025-3-28 10:05 作者: 保存 時(shí)間: 2025-3-28 14:05 作者: 原來(lái) 時(shí)間: 2025-3-28 16:44 作者: Interferons 時(shí)間: 2025-3-28 22:03
FairDR: Ensuring Fairness in?Mixed Data of?Fairly and?Unfairly Treated Instancescausal structures. Leveraging the perspective of SCM, we propose a framework called FairDR, which utilizes the Hirschfeld-Gebelein-Rényi (HGR) correlation to accurately recover the distribution of both fairly and unfairly treated data. FairDR can serve as a pre-processing method for other fair machi作者: 啞劇 時(shí)間: 2025-3-29 01:04
Blind Adversarial Training: Towards Comprehensively Robust Models Against Blind Adversarial Attacks estimate a nonuniform budget to modify the AEs used in training, ensuring that the strengths of the AEs are dynamically located in a reasonable range and ultimately improving the comprehensive robustness of the AT model. We include a theoretical investigation on a toy classification problem to guar作者: 清唱?jiǎng)?nbsp; 時(shí)間: 2025-3-29 04:26 作者: atrophy 時(shí)間: 2025-3-29 10:50
AIGCIQA2023: A Large-Scale Image Quality Assessment Database for?AI Generated Images: From the?Perspassess the human visual preferences for each image from three perspectives including ., . and .. Finally, based on this large-scale database, we conduct a benchmark experiment to evaluate the performance of several state-of-the-art IQA metrics on our constructed database. The AIGCIQA2023 database an作者: BOAST 時(shí)間: 2025-3-29 13:27 作者: Pulmonary-Veins 時(shí)間: 2025-3-29 19:12
Domain Specific Pre-training Methods for?Traditional Chinese Medicine Prescription Recommendationnd multi-grained negative sampling methods and training objectives. To verify the effectiveness of the proposed method, we conduct extensive experiments on the symptom-prescription dataset. The experiment results show that our proposed method can accurately recommend suitable prescriptions with more作者: 背書 時(shí)間: 2025-3-29 20:48
LTUNet: A Lightweight Transformer-Based UNet with?Multi-scale Mechanism for?Skin Lesion Segmentationres are used to enhance the feature map of each scale. Finally, we fuse the upsampled results of all scales on UNet to improve the performance of segmentation. Our method achieves 0.9432, 0.8948, 0.9348 for mDice, mIoU and mACC on the ISIC2016 dataset, and 0.9058, 0.8138, 0.8968 on the ISIC2018 data作者: 免費(fèi) 時(shí)間: 2025-3-30 01:53
A Novel Online Multi-label Feature Selection Approach for?Multi-dimensional Streaming Data we recalculates the weights of all current labels and updates the total Fisher score to update the current feature rank list. In the experiments, we compare the performance of our approach with four representative online feature selection algorithms for streaming features and labels, respectively. 作者: 錯(cuò)事 時(shí)間: 2025-3-30 06:19
M,Sim: A Long-Term Interactive Driving Simulatorediction model M2I, forming a new simulator named M.Sim. Notably, M.Sim can effectively address the OOD problem of long-term simulation by enforcing a flexible regularization that admits the replayed data, while still enjoying the diversity of data-driven predictions. We demonstrate the superiority 作者: Anticlimax 時(shí)間: 2025-3-30 08:58
Lecture Notes in Computer Sciencehttp://image.papertrans.cn/b/image/162061.jpg作者: 不出名 時(shí)間: 2025-3-30 15:18
Hans van Haut,Heinrich Stratmannto recognize that not all samples are treated unfairly, resulting in data heterogeneity in fair machine learning. Existing fair models primarily focus on achieving fairness across all heterogeneous data, yet they often fall short in ensuring fairness within specific subgroups, such as fairly treated作者: chuckle 時(shí)間: 2025-3-30 20:25 作者: Missile 時(shí)間: 2025-3-31 00:13 作者: 輕率的你 時(shí)間: 2025-3-31 03:24 作者: Debility 時(shí)間: 2025-3-31 05:20
H.-W. Radeke,N. Jaeger,J. Vogel,L. Weissbachniques, AI-based image generation has been applied to various fields. However, AI Generated Images (AIGIs) may have some unique distortions compared to natural images, thus many generated images are not qualified for real-world applications. Consequently, it is important and significant to study sub作者: Glucocorticoids 時(shí)間: 2025-3-31 09:19
R. Gerlach,J. Hannappel,B. Heinrichs,M. Grawes a great memory footprint and computing time when processing a long decoding sequence. To solve this problem, we propose a model named time-sparse transducer, which introduces a time-sparse mechanism into transducer. In this mechanism, we obtain the intermediate representations by reducing the tim作者: 正面 時(shí)間: 2025-3-31 15:39
