检索结果-内蒙古大学图书馆

9th International Conference on Intelligent Computing and Signal processing, ICSP 2024

作者： Song, Yuan Yu, Luo College of Computer Science and Technology Wuhan University of Science and Technology Wuhan430065 China Hubei Provincial Key Laboratory of Intelligent Information Processing and Real-time Industrial Systems Wuhan430065 China

ISBN: (纸本)9798350376548

Translation efforts from natural language to code generation have achieved great success with large pre-trained language models. However, selecting the correct code output for the problem posed by the generated set of candidate codes is still challenging. In this paper, we address this problem by proposing an outcome-based quality-aware reordering method for code selection. This method scores each code by whether the set of candidate codes passes the test cases or not as a reference to select the top k best code outputs. In addition, this method depends on the quality and number of test cases. However, it is impractical to manually create a large number of test cases for each problem, so this paper adopts an automated approach that utilizes the current model to generate test cases for each problem. The experimental results show that the approach proposed in this paper obtains a significant improvement in the pass@k benchmark for each model, and the correctness and quality of test cases generated automatically using the model are discussed experimentally. Summarizing the experimental results and discussions, the result-based quality-aware reordering method proposed in this paper achieves a significant improvement in solving the problem of selecting the correct output from natural language to code generation, effectively improves the accuracy of evaluation by automating the generation of test cases, and provides an effective solution to improving the correctness of code generation. © 2024 IEEE.

关键词： code generation natural language processing (NLP) pre-trained large models quality estimation reranking test case generation

来源：评论

学校读者我要写书评

暂无评论

MAML MOT: Multiple Object Tracking Based on Meta-Learning

MAML MOT: Multiple Object Tracking Based on Meta-Learning

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Chen, Jiayi Deng, Chunhua School of Computer Science and Technology Wuhan University of Science and Technology Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan430065 China

ISBN: (纸本)9781665410205

With the advancement of video analysis technology, the multi-object tracking (MOT) problem in complex scenes involving pedestrians is gaining increasing importance. This challenge primarily involves two key tasks: pedestrian detection and re-identification. While significant progress has been achieved in pedestrian detection tasks in recent years, enhancing the effectiveness of re-identification tasks remains a persistent challenge. This difficulty arises from the large total number of pedestrian samples in multi-object tracking datasets and the scarcity of individual instance samples. Motivated by recent rapid advancements in meta-learning techniques, we introduce MAML MOT, a meta-learning-based training approach for multi-object tracking. This approach leverages the rapid learning capability of meta-learning to tackle the issue of sample scarcity in pedestrian re-identification tasks, aiming to improve the model's generalization performance and robustness. Experimental results demonstrate that the proposed method achieves high accuracy on mainstream datasets in the MOT Challenge. This offers new perspectives and solutions for research in the field of pedestrian multi-object tracking. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Transformer-Based Deep Hashing Method for Multi-Scale Feature Fusion 48

Transformer-Based Deep Hashing Method for Multi-Scale Featur...

引用

48th IEEE International Conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： He, Chao Wei, Hongxi Inner Mongolia University School of Computer Science Hohhot China Provincial Key Laboratory of Mongolian Information Processing Technology Hohhot China National and Local Joint Engineering Research Center of Mongolian Information Processing Technology Hohhot China

ISBN: (纸本)9781728163277

The deep image hashing aims to map the input image into simply binary hash codes via deep neural networks. Motivated by the recent advancements of Vision Transformers (ViT), many deep hashing methods based on ViT have been proposed. Nevertheless, the ViT has enormous number of model parameters and high computational complexity. Moreover, the last layer of the ViT outputs only the classification tokens as image feature vectors, while the rest of the vectors are discarded. This results in the inefficiency of the model computation and the neglect of useful image information. Therefore, this paper proposes a Transformer-based deep hashing method for multi-scale feature fusion (TDH). Specifically, we use a hierarchical Transformer backbone to capture both global and local features of images. The hierarchical Transformer utilizes a local self-attention mechanism to process image blocks in parallel, which reduces computational complexity and promotes computational efficiency. Multi-scale feature fusion module captures all image feature vectors of the hierarchical Transformer output to obtain more enriched image feature information. We perform comprehensive experiments on three widely-studied datasets: CIFAR-10, NUS-WIDE and IMAGENET. The experimental results demonstrate that the proposed method in this paper indicates superior results compared to the existing state-of-the-art work. Source code is available https://***/shuaichaochao/TDH. © 2023 IEEE.

关键词： deep hashing hash code image retrieval multi-scale feature fusion Transformer

来源：评论

学校读者我要写书评

暂无评论

Dual-Path Spectrogram Refinement Network for Robust Speaker Verification

引用

Journal of Shanghai Jiaotong University (Science) 2025年 1-9页

作者： Wang, Zonghui Fang, Zhihua He, Liang School of Computer Science and Technology Xinjiang University Urumqi830017 China School of Intelligence Science and Technology Xinjiang University Urumqi830017 China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi830017 China Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China

The accuracy and reliability of automatic speaker verification (ASV) face significant challenges in noisy environments. In recent years, joint training of speech enhancement front-end and ASV back-end has been widely applied to improve the robustness of ASV systems. Traditional joint training directly uses the enhanced speech features as the input of the back-end. However, the diversity of noise types and noise intensities will excessively suppress the enhanced features, resulting in speech distortion or residual noise. To alleviate this problem, we propose a dual-path spectrogram refinement network that enables the enhanced features to learn supplementary information from the separated noise features. In addition, we incorporate coordinate attention into the overall joint architecture to capture more comprehensive frequency and temporal information of the speaker from different spatial positions. We conduct extensive experiments on the VoxCeleb1 test set, the out-of-domain noise test set, and the VOiCES corpus. The experimental results demonstrate that our proposed method significantly improves the accuracy and robustness of speaker verification systems in both clean and noisy environments. (Figure presented.) © Shanghai Jiao Tong University 2025.

关键词： Spectrographs

来源：评论

学校读者我要写书评

暂无评论

Multiband Kick Drum Separation with Genre-Guided Optimization 10th

Multiband Kick Drum Separation with Genre-Guided Optimizati...

引用

10th Conference on Sound and Music technology, CSMT 2023

作者： Li, Si Jiang, Yuanfeng Wang, Zhaowen Qian, Jiale Li, Wei School of Computer Science and Technology Fudan University Shanghai200438 China Department of Music AI and Information Technology Central Conservatory of Music Beijing100091 China Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai200433 China

ISBN: (纸本)9789819779611

Kick drum plays an important role in electronic music. When hearing an excellent kick drum sound from a reference music track, music production beginners always feel confused about how it will sound if we solo the kick track and why it sounds perfect in a specific song. Reproducing the kick of a music track is not easy even for professional producers and arrangers. To investigate the ability of artificial intelligence in separating kick-drum sounds, in this paper we propose an end-to-end system which is capable of separating multi-genre high-quality electronic kick drum clips from mixed song tracks. Unlike most of the previous music source separation tasks, we only focus on the electronic kick drum rather than the whole percussion track. First, we design a multiband data representation approach for non-pitched percussions such as kick drums, then adopt a multi-discriminator module trained on a multi-genre kick drum corpus to further optimize the separated kick sound. To the authors’ knowledge, this study marks the first attempt at kick drum separation with stylistic optimization. Objective and subjective evaluations demonstrate that joint multiband representation and genre-guided optimisation can form a high-performance framework, showing a promising solution to the kick drum separation task. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Source separation

来源：评论

学校读者我要写书评

暂无评论

NEAT-Net: An Unsupervised Cross-View Prior Inpainting Network for CBCT Metal Artifact Reduction 46

NEAT-Net: An Unsupervised Cross-View Prior Inpainting Networ...

引用

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2024

作者： Yang, Yang Tong, Zhan Zhong, Xinyun Shi, Yijie Xi, Yan Yu, Wenxue Wu, Zhan Chen, Yang First-Imaging Tech Shanghai China Southeast University Laboratory of Image Science and Technology The School of Computer Science and Engineering Nanjing China Southeast University Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing The Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Nanjing China

ISBN: (纸本)9798350371499

Intraoperative Cone-Beam Computed Tomography (CBCT) facilitates intraoperative navigation for Minimally Invasive Spine Surgery (MISS). However, high-attenuation metal implants used in MISS often cause metal artifacts in the reconstructed CBCT images. Current algorithms do not consider the cross-view information in the projection-domain for metal artifact reduction (MAR). Inaccurate projection-domain inpainting results in CBCT MAR lead to tissue blurring and secondary artifacts, significantly compromising the accuracy of CBCT-guided MISS and increasing surgical risks. To address the above challenge, in this paper, we propose a novel unsupervised cross-view prior inpainting network for CBCT Metal Artifact Reduction named NEAT-Net. Firstly, a cross-view prior multi-scale inpainting module is constructed to learn the inter-view complementary information. Secondly, a hybrid feature attention module is proposed to adaptively fuse cross-view features. In addition, an unsupervised training approach is proposed to directly learn from metal-affected data. Extensive experiments are conducted to verify the effectiveness of our algorithm on a real clinical dataset. © 2024 IEEE.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Enhanced YOLOv7-Based Construction Site Environmental Detection Method 4

Enhanced YOLOv7-Based Construction Site Environmental Detect...

引用

4th International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering, ICBAIE 2023

作者： Liang, Siheng Huang, Wenming Xiao, Yannan Guilin University of Electronic Technology School of Computer and Information Security Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China Guilin University of Electronic Technology School of Computer and Information Security Guilin China

ISBN: (纸本)9798350343618

This paper proposes an enhanced approach utilizing the YOLOv7 model for automated construction site environment detection and management. The method leverages high-resolution surveillance cameras and computer vision techniques to achieve this goal. The proposed method starts with data collection of the construction site environment. Then produce accurate bounding boxes. These bounding boxes serve as input to an improved YOLOv7 network model, enabling feature extraction and generating high-scoring feature maps with associated weights. Utilizing these weights, image segmentation is performed to obtain the desired detection heads. Experimental results demonstrate the effectiveness of the method in identifying and annotating various environmental features within the construction site, leading to significant improvements in detection accuracy. Compared to similar techniques, this method offers faster detection speed, higher accuracy, and reduced error rates. The proposed construction site environment detection method provides an efficient and automated solution for on-site management in the construction industry, with practical applications and value. © 2023 IEEE.

关键词： Construction industry

来源：评论

学校读者我要写书评

暂无评论

引用

4th International Conference on information Science, Parallel and Distributed Systems, ISPDS 2023

作者： Zhou, Ya Zhao, Ning Huang, Guimin Deng, Nanxiao Guo, Qingkai School of Computer Science and Information Security Guilin University of Electronic Technology Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China

ISBN: (纸本)9798350337181

In sentence similarity research methods, sentence similarity is often calculated from semantic aspects, however, the influence of other features is ignored. For example, the influence of sentence syntactic structure and word order on sentence similarity is not considered. Therefore, This paper proposes a method to measure the degree of similarity between sentences based on a multi-feature fusion of semantics, syntactic similarity and word order similarity, respectively. For the aspect of semantic similarity, in this paper, we first preprocess the sentence and obtain the word vectors, and then obtains sentence vector features through neural networks, so as to calculate the sentence semantic similarity;Finally, for the aspect of word order similarity, word order is considered as the auxiliary feature information to calculate sentence similarity since word order has a smaller effect on sentence similarity compared to the above information. The experimental results show that the proposed model has an accuracy of 77.4 % and an F1 value of 84.3% on the MRPC dataset. © 2023 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Faster and More Robust Low-Resource Nearest Neighbor Machine Translation 12th

Faster and More Robust Low-Resource Nearest Neighbor Machin...

引用

12th National CCF Conference on Natural Language processing and Chinese Computing, NLPCC 2023

作者： Sun, Shuo Hou, Hongxu Yang, Zongheng Wang, Yisong College of Computer Science Inner Mongolia University National and Local Joint Engineering Research Center of Intelligent Information Hohhot China Processing Technology for Mongolian Inner Mongolia Key Laboratory of Mongolian Information Processing Technology Hohhot China

ISBN: (纸本)9783031446955

Transformer-based neural machine translation (NMT) models have achieved performance close to human-level on some languages, but still suffer from poor interpretability and scalability of the models. Many advanced studies enhance the model’s translation ability by building external memory modules and utilizing retrieval operations, however, it suffers from poor robustness and low decoding efficiency while improving the model performance, especially for low-resource translation tasks. In this paper, we propose a confidence-based gating mechanism to optimize the decoding efficiency by building a sub-network to determine the confidence of the model’s own translation capability and then decide whether the current translation needs to be retrieved from the memory module. By reducing the number of retrievals to improve the model’s translation speed without degrading the translation quality as much as possible. In addition, we use a nonparametric dynamic Monte Carlo-based algorithm to fuse retrieval probabilities and model predictions to improve the generalization and robustness of the model. Extensive experiments on different datasets demonstrate the effectiveness of our method. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Multi-Perspective Frame Element Representation for Machine Reading Comprehension 8th

Multi-Perspective Frame Element Representation for Machine ...

引用

8th China Conference on Knowledge Graph and Semantic Computing, CCKS 2023

作者： Guo, Shaoru Guan, Yong Li, Ru School of Computer and Information Technology Shanxi University Taiyuan China Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University Taiyuan China

ISBN: (纸本)9789819972234

Semantics understanding is a critical aspect of Machine Reading Comprehension (MRC). In recent years, researchers have started leveraging the semantic knowledge provided by FrameNet to enhance the performance of MRC systems. While significant efforts have been dedicated to Frame representation, there is a noticeable lack of research on Frame Element (FE) representation, which is equally crucial for MRC. We propose a groundbreaking approach called the Multi-Perspective Frame Elements Representation (MPFER) method. It aims to comprehensively model FEs from three distinct perspectives: FE definition, Frame (semantic scenario), and FE relation. By considering these multiple perspectives, our proposed model significantly improves the representation and understanding of FEs in MRC tasks. To validate the effectiveness of the MPFER method, we conducted extensive experiments. The results clearly demonstrate that our proposed model outperforms existing state-of-the-art methods. The superiority of our approach highlights its potential for advancing the field of MRC and showcasing the importance of properly modeling FEs for better semantic understanding. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：