检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Zhao, Qingsong Wang, Yi Dou, Shuguang Gong, Chen Wang, Yin Zhao, Cairong Ji, Xiaopeng Jiang, Xinyang Department of Computer Science and Technology Tongji University Shanghai201804 China Shanghai AI Laboratory Shanghai200232 China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information School of Computer Science and Engineering Ministry of Education Nanjing University of Science and Technology Nanjing210094 China The State Key Lab of CAD&CG Zhejiang University China Shanghai China

How to improve discriminative feature learning is central in classification. Existing works address this problem by explicitly increasing inter-class separability and intra-class compactness, whether by constructing positive and negative pairs for contrastive learning or posing tighter class separating margins. These methods do not exploit the similarity between different classes as they adhere to independent identical distributions assumption in data. In this paper, we embrace the real-world data distribution setting that some classes share semantic overlaps due to their similar appearances or concepts. Regarding this hypothesis, we propose a novel regularization to improve discriminative learning. We first calibrate the estimated highest likelihood of one sample based on its semantically neighboring classes, then encourage the overall likelihood predictions to be deterministic by imposing an adaptive exponential penalty. As the gradient of the proposed method is roughly proportional to the uncertainty of the predicted likelihoods, we name it adaptive discriminative regularization (ADR), trained along with a standard cross entropy loss in classification. Extensive experiments demonstrate that it can yield consistent and non-trivial performance improvements in a variety of visual classification tasks (over 10 benchmarks). Furthermore, we find it is robust to long-tailed and noisy label data distribution. Its flexible design enables its compatibility with mainstream classification architectures and losses. © 2022, CC BY.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Animal Pose Estimation with Skeleton Anomaly-Aware Learning

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Han, Le Chen, Kaixuan Zhao, Lei Jiang, Yangbo Wang, Pengfei Zheng, Nenggan Zhejiang Hangzhou310007 China Zhejiang University College of Computer Science and Technology Zhejiang Hangzhou310007 China Zhejiang University State Key Laboratory of Blockchain and Data Security Zhejiang Hangzhou310007 China Institute of Blockchain and Data Security. China Zhejiang University School of Software Technology Ningbo China Zhejiang University State Key Lab of Brain-Machine Intelligence Hangzhou310007 China Zhejiang Provincial Government ZJU Collaborative Innovation Center for Artificial Intelligence by MOE Hangzhou310007 China Bengbu University School of Computer and Information Engineering Bengbu233030 China

Animal pose estimation is often constrained by the scarcity of annotations and the diversity of scenarios and species. The pseudo-label generation based unsupervised domain adaptation paradigm, which discriminates the predicted keypoints of unlabeled data based on the skeleton position consistency, has demonstrated effectiveness for such problems. However, existing methods generate pseudo-labels with massive false positives, because they cannot effectively distinguish sample pairs with the same errors. In this study, we propose a cross-domain animal pose estimation model from a novel perspective of skeleton anomaly learning. We construct a graph contrastive learning mechanism to acquire the skeleton anomaly-aware knowledge, which enables the generation of accurate pseudo-labels for target domain and imposes graph constraint on unlabeled data. And a skeleton anomaly-feedback based domain adaptation framework is designed to facilitate implicit alignment of object-specific features and joint training of cross-domain. Besides, we propose a novel rat pose dataset named UDARP-9.4K to address the gap of small-sized animal pose datasets encompassing diverse experimental scenarios. The related datasets are reviewed and evaluated in detail. Extensive experiments are conducted on UDARP-9.4K and two public datasets to demonstrate the superiority of the proposed model in cross-scenarios and cross-species animal pose estimation tasks. Further analysis reveals the effectiveness of the proposed model for skeleton structure feature learning. The UDARP-9.4K dataset is available here. © 1991-2012 IEEE.

关键词： Invertebrates

来源：评论

学校读者我要写书评

暂无评论

Robustness-Aware 3D Object Detection in Autonomous Driving: A Review and Outlook

arXiv

引用

arXiv 2024年

作者： Song, Ziying Liu, Lin Jia, Feiyang Luo, Yadan Jia, Caiyan Zhang, Guoxin Yang, Lei Wang, Li School of Computer Science & Technology Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing100044 China School of Information Technology and Electrical Engineering The University of Queensland St LuciaQLD4072 Australia School of Computer Science Beijing University of Posts and Telecommunications Beijing100876 China State Key Laboratory of Intelligent Green Vehicle and Mobility The School of Vehicle and Mobility Tsinghua University Beijing100084 China School of Mechanical Engineering Beijing Institute of Technology Beijing100081 China

In the realm of modern autonomous driving, the perception system is indispensable for accurately assessing the state of the surrounding environment, thereby enabling informed prediction and planning. The key step to this system is related to 3D object detection that utilizes vehicle-mounted sensors such as LiDAR and cameras to identify the size, the category, and the location of nearby objects. Despite the surge in 3D object detection methods aimed at enhancing detection precision and efficiency, there is a gap in the literature that systematically examines their resilience against environmental variations, noise, and weather changes. This study emphasizes the importance of robustness, alongside accuracy and latency, in evaluating perception systems under practical scenarios. Our work presents an extensive survey of camera-only, LiDAR-only, and multimodal 3D object detection algorithms, thoroughly evaluating their trade-off between accuracy, latency, and robustness, particularly on datasets like KITTI-C and nuScenes-C to ensure fair comparisons. Among these, multi-modal 3D detection approaches exhibit superior robustness, and a novel taxonomy is introduced to reorganize the literature for enhanced clarity. This survey aims to offer a more practical perspective on the current capabilities and the constraints of 3D object detection algorithms in real-world applications, thus steering future research towards robustness-centric advancements. Copyright © 2024, The Authors. All rights reserved.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

VHM: Versatile and Honest Vision Language Model for Remote Sensing Image Analysis

arXiv

引用

arXiv 2024年

作者： Pang, Chao Weng, Xingxing Wu, Jiang Li, Jiayu Liu, Yi Sun, Jiaxing Li, Weijia Wang, Shuai Feng, Litong Xia, Gui-Song He, Conghui School of Artificial Intelligence Wuhan University China Shanghai Artificial Intelligence Laboratory China School of Computer Science Wuhan University China Sun Yat-Sen University China Sensetime Research China State Key Lab. of LIESMARS Wuhan University China Institue for Math & AI Wuhan University China

This paper develops a Versatile and Honest vision language Model (VHM) for remote sensing image analysis. VHM is built on a large-scale remote sensing image-text dataset with rich-content captions (VersaD), and an honest instruction dataset comprising both factual and deceptive questions (HnstD). Unlike prevailing remote sensing image-text datasets, in which image captions focus on a few prominent objects and their relationships, VersaD captions provide detailed information about image properties, object attributes, and the overall scene. This comprehensive captioning enables VHM to thoroughly understand remote sensing images and perform diverse remote sensing tasks. Moreover, different from existing remote sensing instruction datasets that only include factual questions, HnstD contains additional deceptive questions stemming from the non-existence of objects. This feature prevents VHM from producing affirmative answers to nonsense queries, thereby ensuring its honesty. In our experiments, VHM significantly outperforms various vision language models on common tasks of scene classification, visual question answering, and visual grounding. Additionally, VHM achieves competent performance on several unexplored tasks, such as building vectorizing, multi-label classification and honest question answering. Copyright © 2024, The Authors. All rights reserved.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

InOR-Net: Incremental 3D Object Recognition Network for Point Cloud Representation

arXiv

引用

arXiv 2023年

作者： Dong, Jiahua Cong, Yang Sun, Gan Wang, Lixu Lyu, Lingjuan Li, Jun Konukoglu, Ender The State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China The University of Chinese Academy of Sciences Beijing100049 China The Computer Science Department Northwestern University Evanston United States The Sony AI Tokyo108-0075 Japan The School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China The Computer Vision Lab ETH Zurich Zürich8092 Switzerland

3D object recognition has successfully become an appealing research topic in the real-world. However, most existing recognition models unreasonably assume that the categories of 3D objects cannot change over time in the real-world. This unrealistic assumption may result in significant performance degradation for them to learn new classes of 3D objects consecutively, due to the catastrophic forgetting on old learned classes. Moreover, they cannot explore which 3D geometric characteristics are essential to alleviate the catastrophic forgetting on old classes of 3D objects. To tackle the above challenges, we develop a novel Incremental 3D Object Recognition Network (i.e., InOR-Net), which could recognize new classes of 3D objects continuously via overcoming the catastrophic forgetting on old classes. Specifically, a category-guided geometric reasoning is proposed to reason local geometric structures with distinctive 3D characteristics of each class by leveraging intrinsic category information. We then propose a novel critic-induced geometric attention mechanism to distinguish which 3D geometric characteristics within each class are beneficial to overcome the catastrophic forgetting on old classes of 3D objects, while preventing the negative influence of useless 3D characteristics. In addition, a dual adaptive fairness compensations strategy is designed to overcome the forgetting brought by class imbalance, by compensating biased weights and predictions of the classifier. Comparison experiments verify the state-of-the-art performance of the proposed InOR-Net model on several public point cloud datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Context-aware Multi-level Question Embedding Fusion for visual question answering

引用

Information Fusion 2024年 102卷

作者： Li, Shengdong Gong, Chen Zhu, Yuqing Luo, Chuanwen Hong, Yi Lv, Xueqiang School of Information Renmin University of China Beijing100872 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Zhejiang Lab Zhejiang Hangzhou311121 China Department of Computer Science California State University Los Angeles CA90032 United States School of Information Science and Technology Beijing Forestry University Beijing100083 China Engineering Research Center for Forestry-Oriented Intelligent Information Processing National Forestry and Grassland Administration 100083 China Beijing Key Laboratory of Internet Culture and Digital Dissemination Research Beijing Information Science and Technology University 100101 China

Question model has been widely concerned as the cornerstone of constructing Visual Question Answering (VQA) models. Existing question models attempt to exploit word context to extract multi-level concepts for modeling multi-level questions. However, they still have many defects. For example, most question models utilize simple fusion methods to fuse shallow modules and extract parameter-unshared low-level concepts, leading to poor modeling of multi-level questions;although some question models use deep bidirectional Transformer encoder in external knowledge transfer and BERT for multi-level questions, their complexity is still high. To solve these issues, we propose a novel low-complex multi-level contextual question model, termed Context-aware Multi-level Question Embedding Fusion (CMQEF). We formalize its concepts and theories, deduce its modeling process, optimization process and feature extraction process, analyze its low complexity and high expressiveness, and prove that it defines a new way to solve parameter non-sharing for extracting parameter-shared multi-level concepts and optimize the tradeoff between expressiveness and complexity in question models. Extensive experiments on VQAv2 and VQA-CPv2 validate that comparing with the state-of-the-art, our CMQEF outperforms it on SANs and UpDn, reduces the language priors of SANs and UpDn, and has preferable interpretability and applicability. Our code is available at https://***/lsdruc/CMQEF-for-VQA. © 2023 The Author(s)

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

A versatile interferometric technique for probing the thermophysical properties of complex fluids

引用

Light(science & Applications) 2022年第5期11卷 979-990页

作者： Gopal Verma Gyanendra Yadav Chaudry Sajed Saraj Longnan Li Nenad Miljkovic Jean Pierre Delville Wei Li GPL Photonics Lab State Key Laboratory of Applied OpticsChangchun Institute of OpticsFine Mechanics and PhysicsChinese Academy of Sciences130033 ChangchunChina School of Physical Sciences University of LiverpoolLiverpool L693BXUK Materials Research Laboratory University of IllinoisUrbanaILUSA Department of Mechanical Science and Engineering University of IllinoisUrbanaILUSA Department of Electrical and Computer Engineering University of IllinoisUrbanaILUSA International Institute for Carbon Neutral Energy Research(WPI-I2CNER) Kyushu University744 MotookaNishi-kuFukuoka 819-0395Japan University of Bordeaux CNRSLOMAUMR 5798F-33405 TalenceFrance

Laser-induced thermocapillary deformation of liquid surfaces has emerged as a promising tool to precisely characterize the thermophysical properties of pure ***,challenges arise for nanofluid(NF)and soft biofluid systems where the direct interaction of the laser generates an intriguing interplay between heating,momentum,and scattering forces which can even damage soft ***,we report a versatile,pump-probe-based,rapid,and non-contact interferometric technique that resolves interface dynamics of complex fluids with the precision of~1 nm in thick-film and 150 pm in thin-film regimes below the thermal limit without the use of lock-in or modulated *** characterize the thermophysical properties of complex NF in three exclusively different types of ***,when the NF is heated from the bottom through an opaque substrate,we demonstrate that our methodology permits the measurement of thermophysical properties(viscosity,surface tension,and diffusivity)of complex NF and ***,in a top illumination configuration,we show a precise characterization of NF by quantitively isolating the competing forces,taking advantage of the different time scales of these ***,we show the measurement of NF confined in a metal cavity,in which the transient thermoelastic deformation of the metal surface provides the properties of the NF as well as thermo-mechanical properties of the *** results reveal how the dissipative nature of the heatwave allows us to investigate thick-film dynamics in the thin-film regime,thereby suggesting a general approach for precision measurements of complex NFs,biofluids,and optofluidic devices.

关键词： deformation thermophysical film

来源：评论

学校读者我要写书评

暂无评论

Learning-Aided Multi-UAV Online Trajectory Coordination and Resource Allocation for Mobile WSNs

Learning-Aided Multi-UAV Online Trajectory Coordination and ...

引用

IEEE Conference on computer Communications Workshops, INFOCOM Wksps

作者： Lu Chen Suzhi Bi Xiaohui Lin Zheyuan Yang Yuan Wu Qiang Yet State Key Laboratory of Radio Frequency Heterogeneous Integration Shenzhen University Shenzhen China Department of Information Engineering The Chinese Unviersity of Hong Kong Shatin N. T. Hong Kong SAR State Key Lab of Internet of Things for Smart City The University of Macau Macao SAR Department of Computer Science Memorial University of Newfoundland Canada

In this paper, we consider a multi-UAV enabled wireless sensor network (WSN) where multiple unmanned aerial vehicles (UAVs) gather data from multiple randomly moving sensor nodes (SNs). We aim to minimize the long-term average energy consumption of all SNs while satisfying their average data rate requirements and energy constraints of the UAVs. We solve the problem by jointly optimizing the multi-UAV's trajectories, communication scheduling and SN's association decisions. In particular, we formulate it as a multi-stage stochastic mixed integer non-linear programming (MINLP) problem and design an online algorithm that integrates Lyapunov optimization and deep reinforcement learning (DRL) methods. Specifically, we first decouple the original multi-stage stochastic MINLP problem into a series of per-slot deterministic MINLP subproblems by applying Lyapunov optimization. For each per-slot problem, we use model-free DRL to obtain the optimal integer UAV-SN associations and model-based method to optimize the UAVs' trajectories and resource allocation. Simulation results reveal that although the communication environments change stochastically and rapidly, our proposed online algorithm can produce real-time solution that achieves high system performance and satisfies all the constraints.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Effect of trace boron on grain refinement of commercially pure aluminum by Al-5Ti-1B

引用

Transactions of Nonferrous Metals Society of China 2022年第4期32卷 1061-1069页

作者： Fei XIAO Ming-xu WU Yi-xiao WANG Wen-zhe ZHOU Shu-bin WANG Dong-hong WANG Guo-liang ZHU Michael JIANG Da SHU Jia-wei MI Bao-de SUN Shanghai Key Lab of Advanced High-temperature Materials and Precision Forming and State Key Laboratory of Metal Matrix Composites School of Materials Science and EngineeringShanghai Jiao Tong UniversityShanghai 200240China National Engineering Research Center of Light Alloy Net Forming School of Materials Science and EngineeringShanghai Jiao Tong UniversityShanghai 200240China Shenzhen Almate Inc. Shenzhen 518102China School of Engineering and Computer Science University of HullHullHU67RXUK

The effect of boron content on grain refinement of commercially pure aluminum by Al-5Ti-1B was quantitatively *** the boron content is less than 0.03 wt.%,the refining performance of Al-5Ti-1B gradually is weakened as the boron content increases,which is attributed to the reaction of boron with the Al_(3)Ti interlayer on TiB_(2)and the consumption of solute *** the contrary,when the boron content exceeds 0.03 wt.%,the refining performance of Al-5Ti-1B gradually recovers with increasing boron content,which is related to the formation of primary AlB_(2)particles that provide additional nucleant substrates.

关键词： aluminum alloy casting Al-5Ti-1B grain refinement boron treatment nucleation

来源：评论

学校读者我要写书评

暂无评论

Full-Atom Protein Pocket Design via Iterative Refinement

arXiv

引用

arXiv 2023年

作者： Zhang, Zaixi Lu, Zepu Hao, Zhongkai Zitnik, Marinka Liu, Qi Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence Anhui Hefei China Dept. of Comp. Sci. and Tech. Institute for AI THBI Lab BNRist Center Tsinghua-Bosch Joint ML Center Tsinghua China Harvard University United States

The design of de novo functional proteins that bind specific ligand molecules is paramount in therapeutics and bio-engineering. A critical yet formidable task in this endeavor is the design of the protein pocket, which is the cavity region of the protein where the ligand binds. Current methods are plagued by inefficient generation, inadequate context modeling of the ligand molecule, and the inability to generate side-chain atoms. Here, we present the Full-Atom Iterative Refinement (FAIR) method, designed to address these challenges by facilitating the co-design of protein pocket sequences, specifically residue types, and their corresponding 3D structures. FAIR operates in two steps, proceeding in a coarse-to-fine manner (transitioning from protein backbone to atoms, including side chains) for a full-atom generation. In each iteration, all residue types and structures are simultaneously updated, a process termed full-shot refinement. In the initial stage, the residue types and backbone coordinates are refined using a hierarchical context encoder, complemented by two structure refinement modules that capture both inter-residue and pocket-ligand interactions. The subsequent stage delves deeper, modeling the side-chain atoms of the pockets and updating residue types to ensure sequence-structure congruence. Concurrently, the structure of the binding ligand is refined across iterations to accommodate its inherent flexibility. Comprehensive experiments show that FAIR surpasses existing methods in designing superior pocket sequences and structures, producing average improvement exceeding 10% in AAR and RMSD metrics. FAIR is available at https://***/zaixizhang/FAIR. © 2023, CC BY.

关键词： Atoms

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：