检索结果-内蒙古大学图书馆

visual-Linguistic Feature Alignment with Semantic and Kinematic Guidance for Referring Multi-Object Tracking

IEEE Transactions on Multimedia 2025年 27卷 3034-3044页

作者： Li, Yizhe Zhou, Sanping Qin, Zheng Wang, Le National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Shaanxi Xi'an710049 China

Referring Multi-Object Tracking (RMOT) aims to dynamically track an arbitrary number of referred targets in a video sequence according to the language expression. Previous methods mainly focus on cross-modal fusion at the feature level with designed structures. However, the insufficient visual-linguistic alignment is prone to causing visual-linguistic mismatches, leading to some targets being tracked but not correctly referred especially when facing the language expression with complex semantics or motion descriptions. To this end, we propose to conduct visual-linguistic alignment with semantic and kinematic guidance to effectively align the visual features with more diverse language expressions. In this paper, we put forward a novel end-to-end RMOT framework SKTrack, which follows the transformer-based architecture with a Language-Guided Decoder (LGD) and a Motion-Aware Aggregator (MAA). In particular, the LGD performs deep semantic interaction layer-by-layer in a single frame to enhance the alignment ability of the model, while the MAA conducts temporal feature fusion and alignment across multiple frames to enable the alignment between visual targets and language expression with motion descriptions. Extensive experiments on the Refer-KITTI and Refer-KITTI-v2 demonstrate that SKTrack achieves state-of-the-art performance and verify the effectiveness of our framework and its components. © 1999-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Event-enhanced synthetic aperture imaging

引用

Science China(information Sciences) 2025年第3期68卷 388-390页

作者： Siqi LI Shaoyi DU Jun-Hai YONG Yue GAO Beijing National Research Center for Information Science and Technology School of SoftwareTsinghua University Institute for Brain and Cognitive Sciences Beijing Laboratory of Brain and Cognitive IntelligenceTsinghua University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and ApplicationsInstitute of Artificial Intelligence and Robotics Xi'an Jiaotong University

Synthetic aperture imaging(SAI) methods aim to see through dense occlusions and reconstruct the target scene behind occlusions. Traditional frame-based SAI methods,e.g., DeOccNet [1], take the occluded light field ima...

关键词：

来源：评论

学校读者我要写书评

暂无评论

Human-Like Decision-Making of Autonomous Vehicles in Dynamic Traffic Scenarios

引用

IEEE/CAA Journal of Automatica Sinica 2023年第10期10卷 1905-1917页

作者： Tangyike Zhang Junxiang Zhan Jiamin Shi Jingmin Xin Nanning Zheng National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and ApplicationsXi’an 710049 Institute of Artificial Intelligence and Robotics Xi’an Jiaotong UniversityXi’an 710049China Momenta Shanghai 201804China

With the maturation of autonomous driving technology, the use of autonomous vehicles in a socially acceptable manner has become a growing demand of the public. Human-like autonomous driving is expected due to the impact of the differences between autonomous vehicles and human drivers on *** human-like decision-making has become a research hotspot, a unified theory has not yet been formed, and there are significant differences in the implementation and performance of existing methods. This paper provides a comprehensive overview of human-like decision-making for autonomous vehicles. The following issues are discussed: 1) The intelligence level of most autonomous driving decision-making algorithms;2) The driving datasets and simulation platforms for testing and verifying human-like decision-making;3) The evaluation metrics of human-likeness;personalized driving;the application of decisionmaking in real traffic scenarios;and 4) The potential research direction of human-like driving. These research results are significant for creating interpretable human-like driving models and applying them in dynamic traffic scenarios. In the future, the combination of intuitive logical reasoning and hierarchical structure will be an important topic for further research. It is expected to meet the needs of human-like driving.

关键词： Autonomous vehicles decision-making driving behavior human-like driving

来源：评论

学校读者我要写书评

暂无评论

Refiner: Fine-grained Cross-modal Concepts Refinement for Compositional Zero-Shot Learning

Refiner: Fine-grained Cross-modal Concepts Refinement for Co...

引用

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

作者： Zhang, Xiao Jing, Haodong Chen, Hui Ma, Yongqiang Zheng, Nanning National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Shaanxi China

ISBN: (纸本)9798350368741

Recent Compositional Zero-Shot Learning (CZSL) methods increasingly adopt the pre-trained vision-language models to capture the contextual relations between image and text spaces. However, the single-class-token design from Transformer-based encoder inevitably captures contextual information from unrelated objects and background, thus hindering the modeling of fine-grained class-specific visual features. Suffering from cross-modal gap, prior methods also struggle to improve compositional recognition performance. To address these issues, we propose a fine-grained cross-modal concepts refinement framework, termed as Refiner, which comprises two pivotal components: (i) the fine-grained concepts refinement of image embeddings to capture state-object context within visual scenes, and (ii) the cross-modal information fusion to mitigate the modality gap. By leveraging learnable query vectors to capture region-specific semantic information pertinent to composition labels, our approach refines visual representations with fine-grained state-object context information. As for cross-modal information fusion, we construct a robust image-to-text mapping by aligning visual embeddings with states, objects, and compositions, respectively. Extensive experiments demonstrate that our Refiner achieves new state-of-the-art performance across all popular benchmarks in both closed- and open-world settings. © 2025 IEEE.

关键词： Compositional Zero-shot Learning Cross-Modal Fusion Fine-Grained Refinement Multimodal Models

来源：评论

学校读者我要写书评

暂无评论

SparallaxMPC: High-Speed Model Predictive Control Solver with High Sparsity and Parallelism

SparallaxMPC: High-Speed Model Predictive Control Solver wit...

引用

2024 China Automation Congress, CAC 2024

作者： Lei, ZhengXing Deng, Xiaodong Liu, Longjun Jiang, Caigui National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University China

ISBN: (纸本)9798350368604

Model Predictive Control (MPC) is one of the most popular methods used in control problem. However, MPC is computationally demanding with limited use of sparse and parallel implementations. We present SparallaxMPC, a high-speed MPC solver with parallel and sparse representation. Our approach is based on sparse matrix representation and leverages the structure of the MPC problem for efficiency. We demonstrate the effectiveness of SparallaxMPC by benchmarking it against the state-of-the-art solver CasADi, achieving more than a 3x acceleration. © 2024 IEEE.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Curriculum Learning for Ultra-Wide-Angle fundus Optic Disc Segmentation

Semi-Supervised Curriculum Learning for Ultra-Wide-Angle fun...

引用

2024 China Automation Congress, CAC 2024

作者： Wang, Yingkai Chen, Yiyi Wu, Jiayi Xin, Jingmin National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China

ISBN: (纸本)9798350368604

Segmentation of the optic disc in ultra-wide-angle fundus images could aid in detection and diagnosis of diabetic kidney disease and diabetic retinopathy. Due to the wide field of view, large image size, and small targets of ultra-wide-angle fundus images, it’s hard to annotate them. In this case, semi-supervised methods could solve this problem. However, standalone semi-supervised training does not take into account the differences between samples. We developed a new semi-supervised training method incorporating curriculum learning, where the model initially trains on easier samples and gradually progresses to more hard ones. This strategy could avoid the possible negative impact of the unlabeled samples in early stages in training and strengthen model’s robustness and serves as a plug- and-play approach and is adaptable to existing semi-supervised semantic segmentation methods. More concretely, we design a difficulty measurer to estimate the training difficulty of samples from the perspective of the entire dataset and a pace controller to control training time and duration of different samples according to their training difficulty. The experiment result shows the method we proposed could improves the performance. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

MEG Channel Selection Using Copula Entropy-Based Transfer Entropy for Motor Imagery BCI 46

MEG Channel Selection Using Copula Entropy-Based Transfer En...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Tang, Chao Jiang, Dongyao Chen, Badong Xi'an Jiaotong University National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an China

ISBN: (纸本)9798350371499

Multi-channel magnetoencephalography (MEG) data provides high spatiotemporal resolution for motor imagery (MI)-based brain-machine interfaces (BCIs). However, not all channels contribute to the performance of BCIs. Taking into account the importance of specific channels in measuring their causal relationships with other channels during MI tasks, a novel channel selection method using copula entropy-based transfer entropy (CTE) is proposed to select task-relevant channels. Experiments on a publicly available dataset validate the effectiveness of the proposed methods. Compared to using all channels, channel selection based on CTE can significantly (p © 2024 IEEE.

关键词： Magnetoencephalography

来源：评论

学校读者我要写书评

暂无评论

Multi-grained Correspondence Learning of Audio-language Models for Few-shot Audio Recognition 24

Multi-grained Correspondence Learning of Audio-language Mode...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhao, Shengwei Xu, Linhai Liu, Yuying Du, Shaoyi National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Shaanxi Xi'an China

ISBN: (纸本)9798400706868

Large-scale pre-trained audio-language models excel in general multi-modal representation, facilitating their adaptation to downstream audio recognition tasks in a data-efficient manner. However, existing few-shot audio recognition methods based on audio-language models primarily focus on learning coarse-grained correlations, which are not sufficient to capture the intricate matching patterns between the multi-level information of audio and the diverse characteristics of category concepts. To address this gap, we propose multi-grained correspondence learning for bootstrapping audio-language models to improve audio recognition with few training samples. This approach leverages generative models to enrich multi-modal representation learning, mining the multi-level information of audio alongside the diverse characteristics of category concepts. Multi-grained matching patterns are then established through multi-grained key-value cache and multi-grained cross-modal contrast, enhancing the alignment between audio and category concepts. Additionally, we incorporate optimal transport to tackle temporal misalignment and semantic intersection issues in fine-grained correspondence learning, enabling flexible fine-grained matching. Our method achieves state-of-the-art results on multiple benchmark datasets for few-shot audio recognition, with comprehensive ablation experiments validating its effectiveness. © 2024 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

LSTM with AhI-model based Kalman Filter for Lithium-ion Battery State of Charge Estimation

LSTM with AhI-model based Kalman Filter for Lithium-ion Batt...

引用

2024 China Automation Congress, CAC 2024

作者： Luo, Xiangyong Dang, Lujuan Yang, Meng Chen, Badong National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an710049 China

ISBN: (纸本)9798350368604

Accurate state of charge (SOC) estimation of lithium-ion battery in battery management system (BMS) is important for the safety and reliability of electronic devices and electric vehicles. This paper proposes a LSTM-extended Kalman filter based on AhI-model (LSTM-EA), which constrains SOC result from LSTM with an AhI-model based Kalman filter. AhI-model is based on Ampere-hour integration method and requires simpler structure to obtain estimated SOC with higher accuracy and robustness. In the experiments, the public datasets from the Center for Advanced Life Cycle engineering (CALCE) are used to validate the SOC estimation performance. The mean absolute error (MAE) and maximum error of the proposed method are less than 2.51% and 8.82% respectively. © 2024 IEEE.

关键词： State of charge

来源：评论

学校读者我要写书评

暂无评论

General Planning Method for Humanoid Collaborative Robots using Large Language Models

General Planning Method for Humanoid Collaborative Robots us...

引用

2024 China Automation Congress, CAC 2024

作者： Gao, Runqin Shi, Jiamin Tian, Shu Chen, Shitao National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an710049 China

ISBN: (纸本)9798350368604

Humanoid robots, capable of simulating human behavior and decision-making, have garnered extensive attention due to their anthropomorphic structures and versatile functional designs. Traditionally, actions and high-level decision-making in robots have been manually achieved by developers, requiring modifications and adaptations for different task requirements, thus lacking autonomous decision-making capabilities. With the rapid advancement of deep learning technologies, large language models trained on internet data have provided new solutions for robot intelligence, demonstrating effective applications in high-level task planning for robots. Based on this, we propose a general high-level task planning method using large language models, implemented on a mobile single-arm humanoid robot as the platform. This method consists of two core components: high-level decision planning and low-level action execution, coupled through the robot’s atomic action interface. The robot autonomously completes sequential action planning by receiving natural language task instructions and executes long-term, complex, general indoor collaborative tasks. By deploying on a real robot, we conducted sub-module tests and overall system performance tests, successfully achieving the process of sorting and organizing tasks in an indoor experimental environment. © 2024 IEEE.

关键词： Anthropomorphic robots

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：