检索结果-内蒙古大学图书馆

44th ACM/IEEE International Conference on software Engineering, ICSE 2024

作者： Liu, Bohan Zhang, He Ma, Weigang Kuang, Hongyu Yang, Yi Xu, Jinwei Gao, Shan Gao, Jian Software Institute Nanjing University State Key Laboratory of Novel Software Technology Jiangsu Nanjing China Huawei Technologies Co. Ltd. China

ISBN: (纸本)9798400702174

Trustworthy Open Source software (OSS) development processes are the basis that secures the long-term trustworthiness of soft-ware projects and products. With the aim to investigate the trust-worthiness of the Pull Request (PR) process, the common model of collaborative development in OSS community, we exploit process mining to identify and analyze the normal and anomalous patterns of PR processes, and propose our approach to identifying anomalies from both control-flow and semantic aspects, and then to analyze and synthesize the root causes of the identified anomalies. We analyze 17531 PRs of 18 OSS projects on GitHub, extracting 26 root causes of control-flow anomalies and 19 root causes of semantic anomalies. We find that most PRs can hardly contain both semantic anomalies and control-flow anomalies, and the internal custom rules in projects may be the key causes for the identified anomalous PRs. We further discover and analyze the patterns of normal PR processes. We find that PRs in the non-fork model (42%) are far more likely than the fork model (5%) to bypass the review process, indicating a higher potential risk. Besides, we analyzed nine poisoned projects whose PR practices were indeed worse. Given the complex and diverse PR processes in OSS community, the proposed approach can help identify and understand not only anomalous PRs but also normal PRs, which offers early risk indications of suspicious incidents (such as poisoning) to OSS supply chain. © 2024 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

SpikingMiniLM: energy-efficient spiking transformer for natural language understanding

引用

science China(Information sciences) 2024年第10期67卷 115-128页

作者： Jiayu ZHANG Jiangrong SHEN Zeke WANG Qinghai GUO Rui YAN Gang PAN Huajin TANG College of Computer Science and Technology Zhejiang University The State Key Lab of Brain-Machine Intelligence Zhejiang University Collaborative Innovation Center of Artificial Intelligence Zhejiang University Advanced Computing and Storage Laboratory Huawei Technologies Co. Ltd. College of Computer Science and Technology Zhejiang University of Technology MOE Frontier Science Center for Brain Science and Brain-Machine Integration Zhejiang University

In the era of large-scale pretrained models, artificial neural networks（ANNs） have excelled in natural language understanding（NLU） tasks. However, their success often necessitates substantial computational resources and energy consumption. To address this, we explore the potential of spiking neural networks（SNNs） in NLU——a promising avenue with demonstrated advantages, including reduced power consumption and improved efficiency due to their event-driven characteristics. We propose the SpikingMiniLM,a novel spiking Transformer model tailored for natural language understanding. We first introduce a multi-step encoding method to convert text embeddings into spike trains. Subsequently, we redesign the attention mechanism and residual connections to make our model operate on the pure spike-based paradigm without any normalization technique. To facilitate stable and fast convergence, we propose a general parameter initialization method grounded in the stable firing rate principle. Furthermore, we apply an ANN-to-SNN knowledge distillation to overcome the challenges of pretraining SNNs. Our approach achieves a macro-average score of 75.5 on the dev sets of the GLUE benchmark, retaining 98% of the performance exhibited by the teacher model MiniLMv2. Our smaller model also achieves similar performance to BERTMINIwith fewer parameters and much lower energy consumption, underscoring its competitiveness and resource efficiency in NLU tasks.

关键词： spiking neural networks natural language understanding spiking Transformer spike-based attention multi-step encoding ANN-to-SNN distillation

来源：评论

学校读者我要写书评

暂无评论

Fix the Tests: Augmenting LLMs to Repair Test Cases with Static Collector and Neural Reranker 35

Fix the Tests: Augmenting LLMs to Repair Test Cases with Sta...

引用

35th IEEE International Symposium on software Reliability Engineering, ISSRE 2024

作者： Liu, Jun Yan, Jiwei Xie, Yuanyuan Yan, Jun Zhang, Jian State Key Laboratory of Computer Science Institute of Software China Chinese Academy of Sciences Technology Center of Software Engineering Institute of Software China China UCAS School of Intelligent Science and Technology Hangzhou Institute for Advanced Study China

ISBN: (纸本)9798350353884

During software evolution, it is advocated that test code should co-evolve with production code. In real development scenarios, test updating may lag behind production code changing, which may cause compilation failure or bring other troubles. Existing techniques based on pre-trained language models can be directly adopted to repair obsolete tests caused by such unsynchronized code changes, especially syntactic-related ones. However, the lack of task-oriented contextual information affects the repair accuracy on large-scale projects. Starting from an obsolete test, the key challenging task is precisely identifying and constructing Test-Repair-Oriented Contexts (TROCtxs) from the whole repository within a limited token *** this paper, we propose Synter (SYNtactic-breaking- changes-induced TEst Repair), a novel approach based on LLMs to automatically repair obsolete test cases via precise and concise TROCtxs construction. Inspired by developers' programming practices, we design three types of TROCtx: class context, usage context, and environment context. Given an obsolete test case to repair, Synter firstly collects the related code information for each type of TROCtx through static analysis techniques automatically. Then, it generates reranking queries to identify the most relevant TROCtxs, which will be taken as the repair-required key contexts and be input to the large language model for the final test *** evaluate the effectiveness of Synter, we construct a benchmark dataset that contains a set of obsolete tests caused by syntactic breaking changes. The experimental results show that Synter outperforms baseline approaches both on textual- and intent-matching metrics. With the augmentation of constructed TROCtxs, hallucinations are reduced by 57.1%. © 2024 IEEE.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

SACM: spatial attributes of complex movements in multi-object tracking

引用

Multimedia Tools and Applications 2025年 1-20页

作者： Li, Hongjun Li, Jiaxin Sun, Xiaohu School of Information Science and Technology Nantong University Jiangsu Nantong226019 China State Key Lab. for Novel Software Technology Nanjing University Jiangsu Nantong210023 China Nantong Research Institute for Advanced Communication Technologies Jiangsu Nantong226019 China

Multi-object tracking is a crucial task in computer vision, but it faces significant challenges due to complex scenes and interactions between tracked objects. To address these challenges, we propose a complex movement-based spatial attribute tracking model (SACM). First, to enhance target detection, the model extracts both global and local features from the input feature maps to capture detailed spatial location information between different targets. Second, to strengthen the positional association of the same target across consecutive frames, position information from the previous frame is incorporated into the current frame, improving occlusion handling. Finally, a new target matching method is developed within the tracker, leveraging spatial relationships among targets to achieve precise matching of overlapping objects. Experimental results show that, compared to FairMOT, SACM achieves a 3.7% improvement in HOTA and a 4.8% improvement in IDF1 on the DanceTrack dataset. On the MOT17 dataset, SACM also improves HOTA by 3.7% and IDF1 by 4.8%. Furthermore, SACM achieves a processing speed of 30.5 FPS on a single GPU, resulting in improved tracking performance. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Robust Activity Recognition Based on Human Skeleton for Video Surveillance 9

Robust Activity Recognition Based on Human Skeleton for Vide...

引用

9th IEEE Smart World Congress, SWC 2023

作者： Zhang, Xiang Xie, Lei Bu, Yanling Lin, Zhenjie Wang, Liming Nanjing University State Key Laboratory for Novel Software Technology China Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology China China Southern Power Grid Digital Platform Technology Company China

ISBN: (纸本)9798350319804

Activity recognition is an important task in video analysis, which can be used in accident monitoring and other daily applications. Traditional activity recognition methods are mainly based on the pixel-level analysis of 2D images. However, they achieve poor robustness in various complex environments, and are vulnerable to the perspective distortion caused by the fixed camera view. To address these challenges, we propose a robust skeleton-based human activity recognition method using a fixed monocular surveillance camera. We encode human skeleton with more critical motion information like pairwise distances between keypoints to capture high-level motion modality. Besides, we normalize skeleton data to eliminate the defects of 2D frames, such as the impact of distance on skeleton scale. Furthermore, we propose a skeleton calibration method based on perspective transformation to adapt our method to the deployment environment of surveillance cameras, especially different downward pitch angles. Experimental results show the recognition accuracy of our system reaches 91 percent with a frame rate of 10 FPS. © 2023 IEEE.

关键词： Activity recognition Human skeleton Surveillance video

来源：评论

学校读者我要写书评

暂无评论

Nearly Optimal Regret for Decentralized Online Convex Optimization 37

Nearly Optimal Regret for Decentralized Online Convex Optimi...

引用

37th Annual Conference on Learning Theory, COLT 2024

作者： Wan, Yuanyu Wei, Tong Song, Mingli Zhang, Lijun The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China School of Software Technology Zhejiang University Ningbo China Institute of Blockchain and Data Security Hangzhou China School of Computer Science and Engineering Southeast University Nanjing China National Key Laboratory for Novel Software Technology Nanjing University Nanjing China

We investigate decentralized online convex optimization (D-OCO), in which a set of local learners are required to minimize a sequence of global loss functions using_only local computations and communications. Previous studies have established O(n5/4ρ-1/2 √T) and O(n3/2ρ-1 log T) regret bounds for convex and strongly convex functions respectively, where n is the number of local learners, ρ -1/4 √T) and Õ(nρ-1/2 log T). The primary technique is to design an online accelerated gossip strategy that enjoys a faster average consensus among local learners. Furthermore, by carefully exploiting the spectral properties of a specific network topology, we enhance the lower bounds for convex and strongly convex functions to Ω(nρ-14 √T) and Ω(nρ-1/2), respectively. These lower bounds suggest that our algorithms are nearly optimal in terms of T, n, and ρ. © 2024 Y. Wan, T. Wei, M. Song & L. Zhang.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Leveraging Separated World Model for Exploration in Visually Distracted Environments 38

Leveraging Separated World Model for Exploration in Visually...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Huang, Kaichen Wan, Shenghua Shao, Minghao Sun, Hai-Hang Gan, Le Feng, Shuai Zhan, De-Chuan School of Artificial Intelligence Nanjing University China National Key Laboratory for Novel Software Technology Nanjing University China School of Cyberspace Science and Technology Beijing Institute of Technology China

Model-based unsupervised reinforcement learning (URL) has gained prominence for reducing environment interactions and learning general skills using intrinsic rewards. However, distractors in observations can severely affect intrinsic reward estimation, leading to a biased exploration process, especially in environments with visual inputs like images or videos. To address this challenge, we propose a bi-level optimization framework named Separation-assisted eXplorer (SeeX). In the inner optimization, SeeX trains a separated world model to extract exogenous and endogenous information, minimizing uncertainty to ensure task relevance. In the outer optimization, it learns a policy on imaginary trajectories generated within the endogenous state space to maximize task-relevant uncertainty. Evaluations on multiple locomotion and manipulation tasks demonstrate SeeX's effectiveness. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Audio2AB:Audio-driven collaborative generation of virtual character animation

引用

虚拟现实与智能硬件（中英文） 2024年第1期6卷 56-70页

作者： Lichao NIU Wenjun XIE Dong WANG Zhongrui CAO Xiaoping LIU School of Computer Science and Information Engineering Hefei University of TechnologyHeifei 230009China School of Software Hefei University of TechnologyHeifei 230009China Anhui Province Key Laboratory of Industry Safety and Emergency Technology Hefei University of TechnologyHefei 230601China

Background Considerable research has been conducted in the areas of audio-driven virtual character gestures and facial animation with some degree of ***,few methods exist for generating full-body animations,and the portability of virtual character gestures and facial animations has not received sufficient *** Therefore,we propose a deep-learning-based audio-to-animation-and-blendshape(Audio2AB)network that generates gesture animations and ARK it's 52 facial expression parameter blendshape weights based on audio,audio-corresponding text,emotion labels,and semantic relevance labels to generate parametric data for full-body *** parameterization method can be used to drive full-body animations of virtual characters and improve their *** the experiment,we first downsampled the gesture and facial data to achieve the same temporal resolution for the input,output,and facial *** Audio2AB network then encoded the audio,audio-corresponding text,emotion labels,and semantic relevance labels,and then fused the text,emotion labels,and semantic relevance labels into the audio to obtain better audio ***,we established links between the body,gestures,and facial decoders and generated the corresponding animation sequences through our proposed GAN-GF loss *** By using audio,audio-corresponding text,and emotional and semantic relevance labels as input,the trained Audio2AB network could generate gesture animation data containing blendshape ***,different 3D virtual character animations could be created through *** The experimental results showed that the proposed method could generate significant gestures and facial animations.

关键词： Audio-driven Virtual character Full-body animation Audio2AB Blendshape GAN-GF

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Music Recommendation Model Based on Personalized Measurement and Game Theory

引用

Chinese Journal of Electronics 2023年第6期32卷 1319-1328页

作者： WU Yun LIN Jian MA Yanlong The State Key Laboratory of Public Big Data Guizhou University College of Computer Science and Technology Guizhou University

Music recommendation algorithms, from the perspective of real-time, can be classified into two categories: offline recommendation algorithms and online recommendation algorithms. To improve music recommendation accuracy, especially for the new music(users have no historic listening records on it), and real-time recommendation ability, and solve the interest drift problem simultaneously, we propose a hybrid music recommendation model based on personalized measurement and game theory. This model can be separated into two parts: an offline recommendation part(OFFLRP) and an online recommendation part(ONLRP). In the offline part, we emphasize users personalization. We introduce two metrics named user pursue-novelty degree(UPND) and music popularity(MP) to improve the traditional items-based collaborative filtering algorithm. In the online part, we try to solve the interest drift problem, which is a thorny problem in the offline part. We propose a novel online recommendation algorithm based on game theory. Experiments verify that the hybrid music recommendation model has higher new music recommendation accuracy, decent dynamical personalized recommendation ability, and real-time recommendation capability, and can substantially mitigate the problem of interest drift.

关键词： Measurement Collaborative filtering Heuristic algorithms Market research Real-time systems Data models Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

FedTC:A Personalized Federated LearningMethod with Two Classifiers

引用

computers, Materials & Continua 2023年第9期76卷 3013-3027页

作者： Yang Liu Jiabo Wang Qinbo Liu Mehdi Gheisari Wanyin Xu Zoe L.Jiang Jiajia Zhang School of Computer Science and Technology Harbin Institute of TechnologyShenzhen518055China Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Shenzhen518055China Research Center for Cyberspace Security Peng Cheng LaboratoryShenzhen518055China

Centralized training of deep learning models poses privacy risks that hinder their *** learning(FL)has emerged as a solution to address these risks,allowing multiple clients to train deep learning models collaborativelywithout sharing ***,FL is vulnerable to the impact of heterogeneous distributed data,which weakens convergence stability and suboptimal performance of the trained model on local *** is due to the discarding of the old local model at each round of training,which results in the loss of personalized information in the model critical for maintaining model accuracy and ensuring *** this paper,we propose FedTC,a personalized federated learning method with two classifiers that can retain personalized information in the local model and improve the model’s performance on local *** divides the model into two parts,namely,the extractor and the classifier,where the classifier is the last layer of the model,and the extractor consists of other *** classifier in the local model is always retained to ensure that the personalized information is not *** receiving the global model,the local extractor is overwritten by the globalmodel’s extractor,and the classifier of the globalmodel serves as anadditional classifier of the localmodel toguide local *** FedTCintroduces a two-classifier training strategy to coordinate the two classifiers for local model *** results on Cifar10 and Cifar100 datasets demonstrate that FedTC performs better on heterogeneous data than current studies,such as FedAvg,FedPer,and local training,achieving a maximum improvement of 27.95%in model classification test accuracy compared to FedAvg.

关键词： Distributed machine learning federated learning data hetero-geneity non-independent identically distributed

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：