检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xia, Tianle Ding, Liang Wan, Guojia Zhan, Yibing Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China The University of Sydney Australia JD Explore Academy College of Computing and Data Science Nanyang Technological University 639798 Singapore

ISBN: (纸本)157735897X

Answering complex queries over incomplete knowledge graphs (KGs) is a challenging task. Most previous works have focused on learning entity/relation embeddings and simulating first-order logic operators with various neural networks. However, they are bottlenecked by the inability to share world knowledge to improve logical reasoning, thus resulting in suboptimal performance. In this paper, we propose a complex reasoning schema over KG upon large language models (LLMs), containing a curriculum-based logical-aware instruction tuning framework, named LACT. Specifically, we augment the arbitrary first-order logical queries via binary tree decomposition, to stimulate the reasoning capability of LLMs. To address the difficulty gap among different types of complex queries, we design a simple and flexible logic-aware curriculum learning framework. Experiments across widely used datasets demonstrate that LACT has substantial improvements (brings an average +5.5% MRR score) over advanced methods, achieving the new state-of-the-art. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Driving Scene Understanding with Traffic Scene-Assisted Topology Graph Transformer 24

Driving Scene Understanding with Traffic Scene-Assisted Topo...

引用

32nd ACM International Conference on multimedia, MM 2024

作者： Rong, Fu Peng, Wenjin Lan, Meng Zhang, Qian Zhang, Lefei National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China School of Cyber Science and Engineering Wuhan University Wuhan China Hong Kong University of Science and Technology Hong Kong Hong Kong Horizon Robotics Beijing China National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Hubei Luojia Laboratory Wuhan China

ISBN: (纸本)9798400706868

Driving scene topology reasoning aims to understand the objects present in the current road scene and model their topology relationships to provide guidance information for downstream tasks. Previous approaches fail to adequately facilitate interactions among traffic objects and neglect to incorporate scene information into topology reasoning, thus limiting the comprehensive exploration of potential correlations among objects and diminishing the practical significance of the reasoning results. Besides, the lack of constraints on lane direction may introduce erroneous guidance information and lead to a decrease in topology prediction accuracy. In this paper, we propose a novel topology reasoning framework, dubbed TSTGT, to address these issues. Specifically, we design a divide-and-conquer topology graph Transformer to respectively infer the lane-lane and lane-traffic topology relationships, which can effectively aggregate the local and global object information in the driving scene and facilitate the topology relationship learning. Additionally, a traffic scene-assisted reasoning module is devised and combined with the topology graph Transformer to enhance the practical significance of lane-traffic topology. In terms of lane detection, we develop a point-wise matching strategy to infer lane centerlines with correct directions, thereby improving the topology reasoning accuracy. Extensive experimental results on Openlane-V2 benchmark validate the superiority of our TSTGT over state-of-the-art methods and the effectiveness of our proposed modules. The code is available at https://***/rongfu-dsb/TSTGT. © 2024 ACM.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Transferring fashion to surveillance with weak labels

引用

Neural Computing and Applications 2023年第18期35卷 13021-13035页

作者： Zheng, Qi He, Zheng Liang, Chao Chen, Jun Lin, Chia-Wen Tao, Dapeng National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan430072 China Collaborative Innovation Center of Geospatial Technology Wuhan430079 China Department of Electrical Engineering National Tsing Hua University Hsinchu Taiwan School of Information Science and Engineering Yunnan University Yunnan Kunming650504 China

In this paper, we address the problem of automatic clothing parsing in surveillance images using the information from user-generated tags, such as "jeans" and "T-shirt." Although clothing parsing has achieved great success in the fashion domain, it is quite challenging to parse target under practical surveillance conditions due to the presence of complex environmental interference, such as that from low resolution, viewpoint variations and lighting changes. Our method is developed to capture target information from the fashion domain and apply this information to a surveillance domain by weakly supervised transfer learning. Most target tags convey strong location information (e.g., "T-shirt" is always shown in the upper region), which can be used as weak labels for our transfer method. Both quantitative and qualitative experiments conducted on practical surveillance datasets demonstrate the effectiveness of the proposed surveillance data enhancing method. © 2020, Springer-Verlag London Ltd., part of Springer Nature.

关键词： Monitoring

来源：评论

学校读者我要写书评

暂无评论

Revisiting Adversarial Patches for Designing Camera-Agnostic Attacks against Person Detection 38

Revisiting Adversarial Patches for Designing Camera-Agnostic...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wei, Hui Wang, Zhixiang Zhang, Kewei Hou, Jiaqi Liu, Yuanwei Tang, Hao Wang, Zheng National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University China The University of Tokyo Japan School of Computer Science Peking University China

Physical adversarial attacks can deceive deep neural networks (DNNs), leading to erroneous predictions in real-world scenarios. To uncover potential security risks, attacking the safety-critical task of person detection has garnered significant attention. However, we observe that existing attack methods overlook the pivotal role of the camera, involving capturing real-world scenes and converting them into digital images, in the physical adversarial attack workflow. This oversight leads to instability and challenges in reproducing these attacks. In this work, we revisit patch-based attacks against person detectors and introduce a camera-agnostic physical adversarial attack to mitigate this limitation. Specifically, we construct a differentiable camera Image Signal Processing (ISP) proxy network to compensate for the physical-to-digital transition gap. Furthermore, the camera ISP proxy network serves as a defense module, forming an adversarial optimization framework with the attack module. The attack module optimizes adversarial patches to maximize effectiveness, while the defense module optimizes the conditional parameters of the camera ISP proxy network to minimize attack effectiveness. These modules engage in an adversarial game, enhancing cross-camera stability. Experimental results demonstrate that our proposed Camera-Agnostic Patch (CAP) attack effectively conceals persons from detectors across various imaging hardware, including two distinct cameras and four smartphones. © 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

ACRL-10K: A Dataset for Air Conditioner Refrigerant Leak Smoke Detection

ACRL-10K: A Dataset for Air Conditioner Refrigerant Leak Smo...

引用

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

作者： Jiang, Yuhan Wang, Zhongyuan Hua, Jie Liang, Jinbi Xu, Zengmin National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China School of Mathematics and Computing Science Guilin University of Electronic Technology Guilin China

ISBN: (纸本)9798350368741

In this paper, we introduce a new dataset for air conditioner refrigerant leak smoke detection, called ACRL-10K. The dataset is designed to develop algorithms for detecting refrigerant leak smoke faults during air conditioner recycling. It contains a total of 10, 724 images covering three common scenarios of air conditioner refrigerant leak: loading port, refrigerant extraction, and disassembly. All images are sourced from 656 video segments of real air conditioner recycling scenarios, captured by surveillance cameras deployed on an environmental company's recycling production line. The annotations for the refrigerant leak smoke in the images are performed by industry experts to ensure high accuracy and consistency. To the best of our knowledge, ACRL-10K is the first dataset specifically designed for refrigerant leak smoke detection. Based on the ACRL-10K dataset, we present the performance of mainstream object detectors, including the YOLO series, as a baseline to conduct the following work: 1) preliminarily summarize the challenges of using the dataset for refrigerant leak smoke detection;2) show the detection results of benchmark methods;and 3) make a comparison to identify the strengths and weaknesses of the baseline algorithms. In practice, the ACRL-10K dataset would hopefully advance research and applications in refrigerant leak early warning during air conditioner dismantling and recycling processes. © 2025 IEEE.

关键词： Air Conditioner Dataset Object Detection Refrigerant Leak Smoke Detection

来源：评论

学校读者我要写书评

暂无评论

Freevc: Towards High-Quality Text-Free One-Shot Voice Conversion 48

Freevc: Towards High-Quality Text-Free One-Shot Voice Conver...

引用

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

作者： Li, Jingyi Tu, Weiping Xiao, Li Wuhan University National Engineering Research Center for Multimedia Software School of Computer Science Wuhan430072 China Hubei Luojia Laboratory China Wuhan University Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan430072 China

ISBN: (纸本)9781728163277

Voice conversion (VC) can be achieved by first extracting source content information and target speaker information, and then reconstructing waveform with these information. However, current approaches normally either extract dirty content information with speaker information leaked in, or demand a large amount of annotated data for training. Besides, the quality of reconstructed waveform can be degraded by the mismatch between conversion model and vocoder. In this paper, we adopt the end-to-end framework of VITS for high-quality waveform reconstruction, and propose strategies for clean content information extraction without text annotation. We disentangle content information by imposing an information bottleneck to WavLM features, and propose the spectrogram-resize based data augmentation to improve the purity of extracted content information. Experimental results show that the proposed method outperforms the latest VC models trained with annotated data and has greater robustness. © 2023 IEEE.

关键词： data augmentation information bottleneck self-supervised learning voice conversion

来源：评论

学校读者我要写书评

暂无评论

When ControlNet Meets Inexplicit Masks: A Case Study of ControlNet on its Contour-following Ability 24

When ControlNet Meets Inexplicit Masks: A Case Study of Cont...

引用

32nd ACM International Conference on multimedia, MM 2024

作者： Xuan, Wenjie Xu, Yufei Zhao, Shanshan Wang, Chaoyue Liu, Juhua Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Wuhan University Wuhan China The University of Sydney Sydney Australia Nanyang Technological University Singapore Singapore

ISBN: (纸本)9798400706868

ControlNet excels at creating content that closely matches precise contours in user-provided masks. However, when these masks contain noise, as a frequent occurrence with non-expert users, the output would include unwanted artifacts. This paper first highlights the crucial role of controlling the impact of these inexplicit masks with diverse deterioration levels through in-depth analysis. Subsequently, to enhance controllability with inexplicit masks, an advanced Shape-aware ControlNet consisting of a deterioration estimator and a shape-prior modulation block is devised. The deterioration estimator assesses the deterioration factor of the provided masks. Then this factor is used in a modulation block to adaptively adjust the model's contour-following ability, which helps it dismiss the noise part in the inexplicit masks. Extensive experiments prove its effectiveness in encouraging ControlNet to interpret inaccurate spatial conditions robustly rather than blindly following the given contours, suitable for diverse kinds of conditions. We showcase application scenarios like modifying shape priors and composable shape-controllable generation. Codes are available at github. © 2024 ACM.

关键词： controlnet

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Chatbots and Social Robots in Education: FEPER Framework for Efficiency, Pedagogical and Ethical Requirements 15

Artificial Intelligence Chatbots and Social Robots in Educat...

引用

15th International Conference on Information, Intelligence, Systems and Applications, IISA 2024

作者： Virvou, Maria Tsihrintzis, George A. University of Piraeus Software Engineering Laboratory Department of Informatics Piraeus Greece Machine Learning Image Processing and Multimedia Applications Laboratory University of Piraeus Department of Informatics Piraeus Greece

ISBN: (纸本)9798350368833

Artificial Intelligence (AI) chatbots and social robots, when incorporated into educational settings, have the potential to significantly transform the learning experience, particularly by providing more personalised, one-on-one attention to students. However, deploying such technology in classrooms also presents challenges. These include unresolved issues related to human-AI interaction, pedagogy and theories, human oversight, data privacy, transparency, accuracy and trust. This paper explores the development of a comprehensive framework aimed at enhancing the efficiency, pedagogical effectiveness, and ethical use of AI-driven educational tools, focusing on social robots and chatbots. The framework addresses important factors such as interaction quality, requirements engineering strategies, and the alignment of AI functionalities with educational goals. It also examines ethical concerns, including data security, user transparency, and trustworthiness. By reviewing recent literature on social robots and chatbots and incorporating emerging ethical considerations alongside long-standing educational objectives, this research aims at establishing a holistic framework, FEPER, of best practices and requirements. The findings offer valuable insights for educators, policymakers, and developers aiming to create more dynamic, personalised, and ethical educational environments using AI technology. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling 38

InfoRM: Mitigating Reward Hacking in RLHF via Information-Th...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Miao, Yuchun Zhang, Sen Ding, Liang Bao, Rong Zhang, Lefei Tao, Dacheng National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University China The University of Sydney Australia Fudan University China Nanyang Technological University Singapore

Despite the success of reinforcement learning from human feedback (RLHF) in aligning language models with human values, reward hacking, also termed reward overoptimization, remains a critical challenge. This issue primarily arises from reward misgeneralization, where reward models (RMs) compute reward using spurious features that are irrelevant to human preferences. In this work, we tackle this problem from an information-theoretic perspective and propose a framework for reward modeling, namely InfoRM, by introducing a variational information bottleneck objective to filter out irrelevant information. Notably, we further identify a correlation between overoptimization and outliers in the IB latent space of InfoRM, establishing it as a promising tool for detecting reward overoptimization. Inspired by this finding, we propose the Cluster Separation Index (CSI), which quantifies deviations in the IB latent space, as an indicator of reward overoptimization to facilitate the development of online mitigation strategies. Extensive experiments on a wide range of settings and RM scales (70M, 440M, 1.4B, and 7B) demonstrate the effectiveness of InfoRM. Further analyses reveal that InfoRM's overoptimization detection mechanism is not only effective but also robust across a broad range of datasets, signifying a notable advancement in the field of RLHF. Code is available at: https://***/miaoyuchun/InfoRM. © 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

Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models 39

Divide, Conquer and Combine: A Training-Free Framework for H...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Wenbin Ding, Liang Zeng, Minyan Zhou, Xiabin Shen, Li Luo, Yong Yu, Wei Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China The University of Sydney Australia Jiangsu University China Shenzhen Campus of Sun Yat-sen University China College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)157735897X

Multimodal large language models (MLLMs) have experienced significant advancements recently, but still struggle to recognize and interpret intricate details in high-resolution (HR) images effectively. While state-of-the-art (SOTA) MLLMs claim to process images at 4K resolution, existing MLLM benchmarks only support up to 2K, leaving the capabilities of SOTA models on true HR images largely untested. Furthermore, existing methods for enhancing HR image perception in MLLMs rely on computationally expensive visual instruction tuning. To address these limitations, we introduce HR-Bench, the first deliberately designed benchmark to rigorously evaluate MLLM performance on 4K&8K images. Through extensive experiments, we demonstrate that while downsampling HR images leads to vision information loss, leveraging complementary modalities, e.g., text, can effectively compensate for this loss. Building upon this insight, we propose Divide, Conquer and Combine, a novel training-free framework for enhancing MLLM perception of HR images. Our method follows a three-staged approach: 1) Divide: recursively partitioning the HR image into patches and merging similar patches to minimize computational overhead, 2) Conquer: leveraging the MLLM to generate accurate textual descriptions for each image patch, and 3) Combine: utilizing the generated text descriptions to enhance the MLLM's understanding of the overall HR image. Extensive experiments show that: 1) the SOTA MLLM achieves 63% accuracy, which is markedly lower than the 87% accuracy achieved by humans on HR-Bench;2) our method brings consistent and significant improvements (a relative increase of +6% on HR-Bench and +8% on general multimodal benchmarks). Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Photointerpretation

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：