检索结果-内蒙古大学图书馆

8th International Conference on computer science and Computational Intelligence, ICCSCI 2023

作者： Dominic, Nicholas Cenggoro, Tjeng Wawan Pardamean, Bens Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta11480 Indonesia

Predicting the best-quality of rice phenotypes is the priority among agricultural researchers to fulfill worldwide food security. Trend development of predictive models from statistics to machine learning is the subject of this review. Gathered from the Google Scholar database, 14 appropriate papers (2016-2020) related to the rice phenotypes prediction were selected through title and abstract content filtering. The outputs show that Support Vector Machine, Multi-layer Perceptron, and regression are the most used models, while yield is the priority prediction point besides tiller, panicle, and 1000-grain weight of rice. However, finding the accurate predictor is invariably challenging due to distinct rice varieties in the world and high confounding factors. Thus, developing an advanced deep learning model that accommodates these needs is worth considering further. © 2023 The Authors. Published by Elsevier B.V.

关键词： machine learning rice phenotypes prediction statistics

来源：评论

学校读者我要写书评

暂无评论

Implementing Vision Transformer to Model Emotions Recognition from Facial Expressions 4

Implementing Vision Transformer to Model Emotions Recognitio...

引用

4th International Conference on Artificial Intelligence and data sciences, AiDAS 2023

作者： Chowanda, Andry Nadia Diana School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Cyber Security Program Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350318432

Emotions are essential to social interaction between interlocutors. It provides essential meaning to social interaction. It is important to recognise emotions along with verbal cues to fully understand the true meaning of a conversation in a social interaction setting. Several techniques can be applied to recognise emotions in the social interaction setting automatically. Emotions can be recognised and interpreted from the interlocutor's facial cues (e.g., facial expression recognition task) by using a sensor such as a camera. Recognising emotions from facial cues has several problems to be solved. This research aims to model robust emotion recognition from facial cues to recognise emotions (particularly from Asian people), as there is only limited research done in this area. This research aims to propose an emotion recognition model from facial cues by implementing Vision Transformers architecture. The dataset implemented in this research was explicitly performed by local (i.e., Indonesian) actors (The Indonesian Mixed Emotion dataset-IMED). The results show that the proposed model can achieve the best testing accuracy of 100% with the best training loss of 0.0001, with 0.53 hours of training times for 50 epochs. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

CollageNoter: Real-Time and Adaptive Collage Layout Design for Screenshot-Based E-Note-Taking 39

CollageNoter: Real-Time and Adaptive Collage Layout Design f...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Qiuyun Guo, Bin Yao, Lina Qiao, Xiaotian Zhang, Ying Yu, Zhiwen School of Computer Science Northwestern Polytechnical University China CSIRO’s Data61 Australia School of Computer Science and Technology Xidian University China Guangzhou Institute of Technology Xidian University China College of Computer Science and Technology Harbin Engineering University China

ISBN: (纸本)157735897X

To enhance the processing of complex multi-modal documents (e.g. e-books, long web pages, etc.), it is an efficient way for users to take digital screenshots of key parts and reorganize them into a new collage E-Note. Existing methods for assisting collage layout design primarily employ a semantic relevance-first strategy, with arranging related contents together. Though capable, it can not ensure the visual readability of screenshots and may conflict with human natural reading patterns. In this paper, we introduce CollageNoter for real-time collage layout design that adapts to various devices (e.g. laptop, tablet, phone, etc.), offering users visually and cognitively well-organized screenshot-based E-Notes. Specifically, we construct a novel two-stage pipeline for collage design, including 1) readability-first layout generation and 2) cognitive-driven layout adjustment. In addition, to achieve real-time response and adaptive model training, we propose a cascade transformer-based layout generator named CollageFormer and a size-aware collage layout builder for automatic dataset construction. Extensive experimental results have confirmed the effectiveness of our CollageNoter. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Exploration of Real-Time 3-D View Reconstruction Methods

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 5915-5927页

作者： Agrawal, Arya Sharma, Teena Verma, Nishchal K. Vellore Institute of Technology School of Computer Science and Engineering Vellore632014 India Indian Institute of Technology Mehta Family School of Data Science and Artificial Intelligence Guwahati781039 India Indian Institute of Technology Kanpur Department of Electrical Engineering 208016 India

Real-time 3-D view reconstruction in an unfamiliar environment poses complexity for various applications due to varying conditions such as occlusion, latency, precision, etc. This article thoroughly examines and tests contemporary methodologies addressing challenges in 3-D view reconstruction. The methods being explored in this article are categorized into volumetric and mesh, generative adversarial network based, and open source library based methods. The exploration of these methods undergoes detailed discussions, encompassing methods, advantages, limitations, and empirical results. The real-time testing of each method is done on benchmarked datasets, including ShapeNet, Pascal 3D+, Pix3D, etc. The narrative highlights the crucial role of 3-D view reconstruction in domains such as robotics, virtual and augmented reality, medical imaging, cultural heritage preservation, etc. The article also anticipates future scopes by exploring generative models, unsupervised learning, and advanced sensor fusion to increase the robustness of the algorithms. © 2020 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

SG-NeRF:Sparse-Input Generalized Neural Radiance Fields for Novel View Synthesis

引用

Journal of computer science & Technology 2024年第4期39卷 785-797页

作者： Kuo Xu Jie Li Zhen-Qiang Li Yang-Jie Cao School of Cyber Science and Engineering Zhengzhou UniversityZhengzhou 450002China Intelligent Big Data System(iBDSys)Lab Shanghai Jiao Tong UniversityShanghai 200240China School of Computer and Artificial Intelligence Zhengzhou UniversityZhengzhou 450001China

Traditional neural radiance fields for rendering novel views require intensive input images and pre-scene optimization,which limits their practical *** propose a generalization method to infer scenes from input images and perform high-quality rendering without pre-scene optimization named SG-NeRF(Sparse-Input Generalized Neural Radiance Fields).Firstly,we construct an improved multi-view stereo structure based on the convolutional attention and multi-level fusion mechanism to obtain the geometric features and appearance features of the scene from the sparse input images,and then these features are aggregated by multi-head attention as the input of the neural radiance *** strategy of utilizing neural radiance fields to decode scene features instead of mapping positions and orientations enables our method to perform cross-scene training as well as inference,thus enabling neural radiance fields to generalize for novel view synthesis on unseen *** tested the generalization ability on DTU dataset,and our PSNR(peak signal-to-noise ratio)improved by 3.14 compared with the baseline method under the same input *** addition,if the scene has dense input views available,the average PSNR can be improved by 1.04 through further refinement training in a short time,and a higher quality rendering effect can be obtained.

关键词： Neural Radiance Fields(NeRF) multi-view stereo(MVS) new view synthesis(NVS)

来源：评论

学校读者我要写书评

暂无评论

Intention Analysis Makes LLMs A Good Jailbreak Defender 31

Intention Analysis Makes LLMs A Good Jailbreak Defender

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Zhang, Yuqi Ding, Liang Zhang, Lefei Tao, Dacheng School of Computer Science Wuhan University China The University of Sydney Australia College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore

ISBN: (纸本)9798891761964

Aligning large language models (LLMs) with human values, particularly when facing complex and stealthy jailbreak attacks, presents a formidable challenge. Unfortunately, existing methods often overlook this intrinsic nature of jailbreaks, which limits their effectiveness in such complex scenarios. In this study, we present a simple yet highly effective defense strategy, i.e., Intention Analysis (IA). IA works by triggering LLMs' inherent self-correct and improve ability through a two-stage process: 1) analyzing the essential intention of the user input, and 2) providing final policy-aligned responses based on the first round conversation. Notably, IA is an inference-only method, thus could enhance LLM safety without compromising their helpfulness. Extensive experiments on varying jailbreak benchmarks across a wide range of LLMs show that IA could consistently and significantly reduce the harmfulness in responses (averagely -48.2% attack success rate). Encouragingly, with our IA, Vicuna-7B even outperforms GPT-3.5 regarding attack success rate. We empirically demonstrate that, to some extent, IA is robust to errors in generated intentions. Further analyses reveal the underlying principle of IA: suppressing LLM's tendency to follow jailbreak prompts, thereby enhancing safety. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Recognition of Facial Expressions and Emotions on the Face using the YOLOv5 Algorithm

Recognition of Facial Expressions and Emotions on the Face u...

引用

2023 International Workshop on Artificial Intelligence and Image Processing, IWAIIP 2023

作者： Gunawan, Alexander A. S. Kusnadi, Maximilianus Raymond Joseph, James Tristan Josan, William Edbert, Ivan Sebastian Bina Nusantara University School of Computer Science Computer Science Department Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Cyber Security Program Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350382914

This study examines the significant influence of emotional states on individuals, recognizing that people are often confronted with numerous challenges and problems in their lives. Such challenges can give rise to feelings of despair and tension, especially in those who struggle to manage them effectively. Depression, which is not just limited to adults, can also have a significant impact on children who may not fully grasp their socio-economic conditions. One of the serious consequences of unresolved emotional distress, particularly depression, is an elevated risk of suicide. Within this framework, facial recognition technology presents itself as a powerful instrument for identifying human emotions. The purpose of this study is to assess the efficacy of facial recognition systems in detecting indicators of depression. Using the YOLOv5 algorithm and comparing it with its precursors, YOLOv4 and YOLOv7, the research conducts a simulation experiment to examine the ability of the system to precisely interpret a range of emotional states, including happiness, sadness, and anger. The research findings suggest that the YOLO algorithm, particularly in its most recent versions, displays exceptional precision in identifying and classifying intricate facial expressions, thus showcasing its potential as a beneficial device in mental health evaluations. © 2023 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Attributive Reasoning for Hallucination Diagnosis of Large Language Models 39

Attributive Reasoning for Hallucination Diagnosis of Large L...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Chen, Yuyan Li, Zehao You, Shuangjie Chen, Zhengyu Chang, Jingwen Zhang, Yi Dai, Weinan Guo, Qingpei Xiao, Yanghua Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China School of Data Science and Engineering East China Normal University China Georgia Institute of Technology United States Zhejiang University China Southern University of Science and Technology China Ant Group China

ISBN: (纸本)157735897X

In recent years, large language models (LLMs) have demonstrated outstanding capabilities in various tasks. However, LLMs also have various drawbacks, especially hallucination. Hallucination refers to the generation of content that does not align with the user input, contradicts previously generated content or world knowledge. Current research on hallucination mainly include knowledge retrieval, prompt engineering, training data improvement, reinforcement learning, etc. However, these methods do not involve different categories of hallucinations which is important on hallucination analysis, and make detailed investigation for the internal state of LLMs which indicates the direction on hallucination occurrence. Therefore, in our research, we introduce an attribution framework to trace the origins of hallucinations based on the internal signals of LLMs. To support this framework, we develop a new benchmark named RelQA-Cate, which includes eight categories of hallucinations for the answers generated by LLMs. After that, we present a novel Differential Penalty Decoding (DPD) strategy for reducing hallucinations through adjusting post-probabilities of each answer. We conduct a series of experiments and the performance on answer reliability has significant improvement, achieving 28.25% at most, which demonstrates the effectiveness of our proposed DPD and its generalization in mitigating hallucination in LLMs. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Imagery contents descriptions for People with visual impairments 22

Imagery contents descriptions for People with visual impairm...

引用

22nd Brazilian Symposium on Human Factorsin Computing Systems, IHC 2023

作者： Jandrey, Alessandra Helena Ruiz, Duncan Dubugras Alcoba Silveira, Milene Selbach School of Technology Graduate Program in Computer Science - PUCRS Brazil

ISBN: (纸本)9798400717154

Image descriptions are crucial in assisting individuals without eyesight by providing verbal representations of visual content. While manual and Artificial Intelligence (AI)-generated descriptions exist, automatic description generators have not fully met the needs of visually impaired People. In this study, we have examined the problems related to image descriptions reported in existing literature using the Snowballing technique. Through this method, we have identified thirteen issues, including ethical concerns surrounding physical appearance, gender and identity, race, and disability. Furthermore, we have identified five reasons why sighted Individuals often fail to provide descriptions for visual content, highlighting the necessity for accessibility campaigns that raise awareness about the social significance of descriptive sentences. We conducted interviews with eight low-vision volunteers, in which we analyzed the characteristics of descriptive sentences for 25 indoor images and gathered participants' expectations regarding image descriptions. As a result, we propose a set of Good Practices for writing descriptive sentences aimed to assist automatic tools and sighted Individuals in generating more satisfactory and high-quality image descriptions. We hope our results will emphasize the societal importance of imagery descriptions and inspire the community to pursue further interdisciplinary research to address the issues identified in our study. © 2023 ACM.

关键词： Image analysis

来源：评论

学校读者我要写书评

暂无评论

Unified Graph and Hypergraph Neural Network for Next-item Recommendation

Unified Graph and Hypergraph Neural Network for Next-item Re...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhang, Xinyu Jiang, Qize Zhang, Hanyuan Sun, Weiwei School of Computer Science Shanghai Key Laboratory of Data Science Fudan University Shanghai China Shanghai Institute of Intelligent Electronics & Systems Shanghai China

ISBN: (纸本)9798350368741

The task of next-item recommendation is a crucial component in recommendation systems. The challenge of this task lies in extracting complex interaction information from users' historical interactions with items. While prior research has transformed users' interaction histories into graphs and hypergraphs to mine high-order interactions, the integration of both remains uncharted. Existing methods treat graphs and hypergraphs separately in representation learning, missing out on their shared attributes. Addressing this gap, we introduce a novel unified framework that integrates graphs and hypergraphs into one unified message passing paradigm. Our method employs graph neural networks and hypergraph neural networks to continuously conduct representation learning, achieving end-to-end next item recommendation. Specifically, our framework consists of the following components: 1) a unique method for graph and hypergraph construction from interaction histories, with items as nodes and users as hyperedges;2) a novel message passing framework compatible with both graph and hypergraph neural networks;and 3) an innovative hypergraph neural network aggregation module enhanced with time and position encoders. The test results on multiple public benchmarks verify that our method outperforms current best practices in performance. © 2025 IEEE.

关键词： Graph Neural Network Hypergraph Neural Network Next-item Recommendation User Modeling

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：