检索结果-内蒙古大学图书馆

11th ACM SIGCHI Annual Symposium on computer-Human Interaction in Play, CHI-PLAY Companion 2024

作者： Lu, Yingtong Li, Zhuying Ding, Ding Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China

ISBN: (纸本)9798400706929

In this paper, we explore the design of interpersonal bodily intertwinement through a VR social game, "Light Up Fireflies". Inspired by works of virtual co-embodiment, our game lets two players embody a single avatar, where each player controls half of the body. The gameplay involves walking in a virtual forest and collaboratively interacting with floating fireflies. While moving, poor coordination can lead to unbalanced movements, causing the avatar to lose its center of mass and fall. Such a design might blur the body boundary between players, providing an intriguing bodily experience of interpersonal bodily intertwinement. We hope our work offers novel insights into bodily play where players experience interconnected physical presence within the digital space. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Enhancing Parameter-Efficient Transformers with Contrastive Syntax and Regularized Dropout for Neural Machine Translation 21st

Enhancing Parameter-Efficient Transformers with Contrastive...

引用

21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024

作者： Fan, Yunlong Yang, Zhiheng Li, Baixuan Gao, Zhiqiang School of Computer Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education Nanjing China

ISBN: (纸本)9789819601219

Transformers have significantly improved Neural Machine Translation (NMT) models, accompanied by the inherent space complexity of O(n2). While recent approaches aim to be parameter-efficient, they often exhibit limited generalization capabilities with fewer parameters and decreased performances in longer sentences. To this end, we propose two methods, Syntax-enhanced Contrastive Learning (Syn-CL) and JS divergence-based Regularized Dropout (JSR-Drop) for the cross-layer parameter-sharing Transformer (baseline) in NMT. In Syn-CL, we add the corresponding target-to-source instances for the same batch in an extra bidirectional training phase, and minimize the distances of syntax-enhanced representation between the bilingual sentence-pair while maximizing the ones among others. In JSR-Drop, we refine the regularized dropout strategy with JS divergence, and improve generalization capabilities by reducing Transformers’ inconsistencies between training and inference introduced by dropout. Extensive experiments on six NMT tasks, IWSLT2014 (German↔English) and IWSLT2017 (English↔French and English↔Romanian), show an average BLEU score of 37.55, surpassing the vanilla Transformer and the baseline up to 1.75 BLEU, and outperforming models with 1.5×, 2.0× parameters in translating long sentences. Our code is available at https://***/Anon1214/EnPeNMT. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

YOLOv8-GR: Gesture Recognition by Improving of YOLOv8 Algorithm 12

YOLOv8-GR: Gesture Recognition by Improving of YOLOv8 Algori...

引用

12th International Conference on Advanced Cloud and Big Data, CBD 2024

作者： Ding, Yi Guo, Naixuan Meng, Haitao School of Information Engineering Yancheng Institute of Technology Yancheng China Southeast University Ministry of Education Key Laboratory of Computer Network and Information Integration China

ISBN: (纸本)9798331511074

Gesture recognition has been widely used in many situations, such as human-computer interaction, virtual reality and smart home. To meet the current demands for accuracy and speed in gesture recognition, this paper proposes an improved algorithm based on YOLOv8, referred to as YOLOv8-GR. By replacing the original YOLOv8 detection head with a Dynamic Head, we integrate scale-aware, spatial-aware, and task-aware attention mechanisms within a unified framework. To enhance context information capture, the SPPF (Spatial Pyramid Pooling - Fast) module is optimized to a modified SPPF-LSKA (Large Separable Kernel Attention) module. In addition, we employ the EIoU loss function for more accurate evaluation of object detection results. To evaluate our algorithm, we integrate a gesture dataset in complex and diverse scenarios through network and field shooting annotations. Compared to the original YOLOv8, the proposed YOLOv8-GR achieves a 22.5% improvement in mAP50 and a 10.0% improvement in mAP50-95 on our dataset. We also compare YOLOv8-GR with the MobileNetv2-based SSD, which is a kind of one-stage object detection algorithm. While maintaining similar recognition accuracy, the computational cost of YOLOv8-GR is 9.9 GFLOPs, which is 15.8% of SSD, and our algorithm can be deployed on Raspberry Pi 4B. © 2024 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

DP-GenFL: a local differentially private federated learning system through generative data

引用

Science China(information Sciences) 2023年第8期66卷 275-276页

作者： Jun LI Kang WEI Chuan MA Feng SHU School of Electronic and Optical Engineering Nanjing University of Science and Technology Zhejiang Lab Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education School of Information and Communication Engineering Hainan University

With the rapid development of the Internet of Things(Io T),the amount of data from intelligent devices is propagating at unprecedented scales. Meanwhile, machine learning(ML),which relies heavily on such data, is revolutionizing many aspects of our lives [1]. However, conventional centralized ML offers little scalability for efficiently processing this huge amount of data.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

SEAVER: Attention Reallocation for Mitigating Distractions in Language Models for Conditional Semantic Textual Similarity Measurement

SEAVER: Attention Reallocation for Mitigating Distractions i...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Li, Baixuan Fan, Yunlong Gao, Zhiqiang School of Computer Science and Engineering Southeast University Nanjing211189 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China

ISBN: (纸本)9798891761681

Conditional Semantic Textual Similarity (C-STS) introduces specific limiting conditions to the traditional Semantic Textual Similarity (STS) task, posing challenges for STS models. Language models employing cross-encoding demonstrate satisfactory performance in STS, yet their effectiveness significantly diminishes in C-STS. In this work, we argue that the failure is due to the fact that the redundant information in the text distracts language models from the required condition-relevant information. To alleviate this, we propose SElf-Augmentation Via SElf-Reweighting (SEAVER), which, based solely on models' internal attention and without the need for external auxiliary information, adaptively reallocates the model's attention weights by emphasizing the importance of condition-relevant tokens. On the C-STS-2023 test set, SEAVER consistently improves performance of all million-scale fine-tuning baseline models (up to around 3 points), and even surpasses performance of billion-scale few-shot prompted large language models (such as GPT-4). Our code is available at https://***/BaixuanLi/SEAVER. © 2024 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Multi-Label Open Set Recognition 38

Multi-Label Open Set Recognition

引用

38th Conference on Neural information Processing Systems, NeurIPS 2024

作者： Wang, Yi-Bo Hang, Jun-Yi Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China

In multi-label learning, each training instance is associated with multiple labels simultaneously. Traditional multi-label learning studies primarily focus on closed set scenario, i.e. the class label set of test data is identical to those used in training phase. Nevertheless, in numerous real-world scenarios, the environment is open and dynamic where unknown labels may emerge gradually during testing. In this paper, the problem of multi-label open set recognition (MLOSR) is investigated, which poses significant challenges in classifying and recognizing instances with unknown labels in multi-label setting. To enable open set multi-label prediction, a novel approach named SLAN is proposed by leveraging sub-labeling information enriched by structural information in the feature space. Accordingly, unknown labels are recognized by differentiating the sub-labeling information from holistic supervision. Experimental results on various datasets validate the effectiveness of the proposed approach in dealing with the MLOSR problem. © 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

Binary Decomposition: A Problem Transformation Perspective for Open-Set Semi-Supervised Learning 41

Binary Decomposition: A Problem Transformation Perspective f...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Hang, Jun-Yi Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China

Semi-supervised learning (SSL) is a classical machine learning paradigm dealing with labeled and unlabeled data. However, it often suffers performance degradation in real-world open-set scenarios, where unlabeled data contains outliers from novel categories that do not appear in labeled data. Existing studies commonly tackle this challenging open-set SSL problem with detect-and-filter strategy, which attempts to purify unlabeled data by detecting and filtering outliers. In this paper, we propose a novel binary decomposition strategy, which refrains from error-prone procedure of outlier detection by directly transforming the original open-set SSL problem into a number of standard binary SSL problems. Accordingly, a concise yet effective approach named BDMatch is presented. BDMatch confronts two attendant issues brought by binary decomposition, i.e. class-imbalance and representation-compromise, with adaptive logit adjustment and label-specific feature learning respectively. Comprehensive experiments on diversified benchmarks clearly validate the superiority of BDMatch as well as the effectiveness of our binary decomposition strategy. Copyright 2024 by the author(s)

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Prompting Large Language Models with Knowledge-Injection for Knowledge-Based Visual Question Answering

引用

Big Data Mining and Analytics 2024年第3期7卷 843-857页

作者： Zhongjian Hu Peng Yang Fengyuan Liu Yuan Meng Xingyu Liu School of Computer Science and Engineering Southeast University the Key Laboratory of Computer Network and Information Integration(Southeast University) Ministry of Education of the People’s Republic of ChinaNanjing 211189China Southeast University-Monash University Joint Graduate School(Suzhou) Southeast UniversitySuzhou 215125China

Previous works employ the Large Language Model(LLM)like GPT-3 for knowledge-based Visual Question Answering(VQA).We argue that the inferential capacity of LLM can be enhanced through knowledge *** methods that utilize knowledge graphs to enhance LLM have been explored in various tasks,they may have some limitations,such as the possibility of not being able to retrieve the required *** this paper,we introduce a novel framework for knowledge-based VQA titled“Prompting Large Language Models with Knowledge-Injection”(PLLMKI).We use vanilla VQA model to inspire the LLM and further enhance the LLM with knowledge *** earlier approaches,we adopt the LLM for knowledge enhancement instead of relying on knowledge ***,we leverage open LLMs,incurring no additional *** comparison to existing baselines,our approach exhibits the accuracy improvement of over 1.3 and 1.7 on two knowledge-based VQA datasets,namely OK-VQA and A-OKVQA,respectively.

关键词： visual question answering knowledge-based visual question answering large language model knowledge injection

来源：评论

学校读者我要写书评

暂无评论

Integrating Syntactic and Semantic Knowledge in AMR Parsing with Heterogeneous Graph Attention network 48

Integrating Syntactic and Semantic Knowledge in AMR Parsing ...

引用

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

作者： Sataer, Yikemaiti Shi, Chuanqi Gao, Miao Fan, Yunlong Li, Bin Gao, Zhiqiang Southeast University School of Computer Science and Engineering Nanjing China Ministry of Education Key Laboratory of Computer Network and Information Integration Nanjing China

ISBN: (纸本)9781728163277

Meaning Representation (AMR) parsing is the task of translating a sentence to an AMR semantic graph which captures the basic meaning of the sentence, and is empowered by pre-trained Transformer models recently. These models encode the syntactic and semantic knowledge implicitly through self-supervised pre-trained tasks. We argue that encoding the syntactic and semantic knowledge explicitly is beneficial to AMR parsing and can improve data efficiency. Specifically, syntactic dependency and semantic role labeling (SRL) have similar sub-structures with AMR. In this work, we propose a novel linguistic knowledge-enhanced AMR parsing model, which augments the pre-trained Transformer with syntactic dependency and semantic role labeling structures of sentences. By applying a heterogeneous graph attention network, we can obtain syntactically and semantically augmented word representation, which can be integrated using an attentive integration layer and gating mechanism. Experimental results show that our model achieves state-of-the-art performance on different benchmarks, especially in out-of-domain and low-resource scenarios. © 2023 IEEE.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

On accuracy rate of community detection and pairing in mobile social network 19

On accuracy rate of community detection and pairing in mobil...

引用

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and Computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable Computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy Computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Tu, Jinbin Li, Qing Wang, Yun Southeast University Key Lab of Computer Network and Information Integration School of Computer Science and Engineering Moe Nanjing China

ISBN: (纸本)9798350346558

Mobile Social network(MSN) is an opportunity network that considers the social attributes of nodes, and also uses the 'store-carry-forward' model to carry out data transfer between nodes. The community nature of nodes is an important reference in MSN to select messaging path. In this paper, a new community cluster problem based on our observed pickup strategies for car-hailing is proposed, which is involving community detection and community pairing. Then we formulate it by using T-Sorokin mobility model. The Cluster-First algorithm and Pair-First algorithm are proposed based on the defined community dependency metric to maximize the accuracy rate. Simulation experimental results show that both CFA and PFA can effectively solve this problem with an accuracy rate of over 70%. And it is concluded that cluster-first is superior to pair-first for this considered problem. © 2022 IEEE.

关键词： Data transfer

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：