检索结果-内蒙古大学图书馆

UAV Video Vehicle Detection: Benchmark and Baseline

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Xiao, Yun Wang, Jinfa Zhao, Zhicheng Jiang, Bo Li, Chenglong Tang, Jin Anhui Univ Sch Artificial Intelligence Key Lab Intelligent Comp & Signal Proc Hefei 230601 Peoples R China Anhui Univ Sch Artificial Intelligence Anhui Prov Key Lab Secur Artificial Intelligence Hefei 230601 Peoples R China Anhui Univ Sch Comp Sci & Technol Anhui Prov Key Lab Multimodal Cognit Computat Informat Mat & Intelligent Sensing Lab Anhui Prov Hefei 230601 Peoples R China

With the increasing application of unmanned aerial vehicles (UAVs) in intelligent transportation systems, vehicle object detection in UAV videos has received increasing attention. Precise categorization and detection for vehicles in UAVs is important in many practical applications. However, existing object detection methods, tailored for natural images, often fall short of accurately identifying vehicle objects. Additionally, high-altitude UAV imaging mainly employs horizontal bounding box annotation, frequently leading to significant obstruction and overlapping. Hence, we propose a new task called UAV video vehicle detection (VVD) to achieve precise detection and categorization of vehicles in high-altitude UAV imaging environments. To facilitate the research and development of UAV VVD, we construct the first large-scale well-annotated benchmark UAV VVD dataset, which includes 70 UAV videos captured at a 500-m altitude, with 361489 vehicle instances annotated by the oriented bounding boxes and vehicle categories. Moreover, we introduce a novel category refinement network (CRNet) approach that extracts and refines vehicle object features from the bounding box of the detection results to classify vehicle categories. This approach effectively eliminates the interference of the background and other vehicle objects in candidate boxes. Notably, the vehicle object features are projected into subspace, enabling the category refinement module (CRM) to focus more on the distinctive characteristics of the vehicle object itself through normalization operations. We conduct extensive experiments on the proposed VVD dataset. Experimental results demonstrate the superiority and effectiveness of the proposed CRNet method. The relevant code and dataset are available at https://***/mmic-lcl.

关键词： Autonomous aerial vehicles Object detection Vehicle detection Feature extraction Annotations Benchmark testing Accuracy Training data mining Automobiles Category refinement network (CRNet) object detection unmanned aerial vehicle (UAV) video vehicle detection (VVD) vehicle categories

来源：评论

学校读者我要写书评

暂无评论

Language-Image Consistency Augmentation and Distillation Network for visual grounding

引用

PATTERN REcognitION 2025年 166卷

作者： Ke, Xiao Xu, Peirong Guo, Wenzhong Fuzhou Univ Coll Comp & Data Sci Fujian Prov Key Lab Networking Comp & Intelligent Fuzhou 350116 Peoples R China Minist Educ Engn Res Ctr Big Data Intelligence Fuzhou 350116 Peoples R China

With the advancement of Vision-Language Pretraining, unified multimodal models have exhibited promising performance in various downstream tasks. However, existing models, which relied on a generic structure for knowledge extraction in Visual Grounding task, did not fully leverage the consistency information between modalities, leading to challenges in generalization. To address this, we proposed a Language-Image Consistency Augmentation and Distillation Network (CADN) based on CLIP model. CADN balanced task loss to alleviate overfitting by allocating weights based on consistency information within CLIP features to penalize task loss. Furthermore, to retain consistency information from the pretrained model during training, we designed Consistency-Aware Self-Distillation Module (CASD), utilized as a converter after feature encoding. This module introduced additional loss functions supervised by CLIP similarity matrix and self-attention weights to ensure the restoration of consistency information in features. Additionally, we proposed Language-Enhanced Masked Attention (LEMA) to generate Spatial-Channel masks, guiding cross-modal attention to adaptively select regions and intensities of multimodal features. This enhanced the quality of decoding features, enabling query vectors to focus on semantic features relevant to textual descriptions, thus improving model performance in VG task. Experimental results not only demonstrated that our proposed model can achieve superior performance on REC datasets, but also demonstrated the distribution changes of feature consistency information through visualization experiments. These results may offer new insights and methodologies for the study and application of cross-modal consistency.

关键词： Visual grounding Referring expression comprehension Self-distillation

来源：评论

学校读者我要写书评

暂无评论

LGS-KT: Integrating logical and grammatical skills for effective programming knowledge tracing

引用

NEURAL NETWORKS 2025年 185卷 107164页

作者： Sun, Xinjie Liu, Qi Zhang, Kai Shen, Shuanghong Zhuang, Yan Guo, Yuxiang Liupanshui Normal Univ Sch Comp Sci Liupanshui Peoples R China Univ Sci & Technol China Sch Comp Sci & Technol Hefei Peoples R China Univ Sci & Technol China Sch Artificial Intelligence & Data Sci Hefei Peoples R China State Key Lab Cognit Intelligence Hefei Peoples R China

Knowledge tracing (KT) estimates students' mastery of knowledge concepts or skills by analyzing their historical interactions. Although general KT methods have effectively assessed students' knowledge states, specific measurements of students' programming skills remain insufficient. Existing studies mainly rely on exercise outcomes and do not fully utilize behavioral data during the programming process. Therefore, we integrate a L ogical and G rammar S kills K nowledge T racing ( LGS-KT ) model to enhance programming education. This model integrates static analysis and dynamic monitoring (such as CPU and memory consumption) to evaluate code elements, providing a thorough assessment of code quality. By analyzing students' multiple iterations on the same programming problem, we constructed a reweighted logical skill evolution graph to assess the development of students' logical skills. Additionally, to enhance the interactions among representations with similar grammatical skills, we developed a grammatical skills interaction graph based on the similarity of knowledge concepts. This approach significantly improves the accuracy of inferring students' programming grammatical skill states. The LGS-KT model has demonstrated superior performance in predicting student outcomes. Our research highlights the potential application of a KT model that integrates logical and grammatical skills in programming exercises. To support reproducible research, we have published the data and code at https://***/xinjiesun-ustc/LGS-KT, encouraging further innovation in this field.

关键词： Knowledge tracing data mining Logical skill Grammatical skill Programming education

来源：评论

学校读者我要写书评

暂无评论

A Prompt-Based Hierarchical Pipeline for Cross-Domain Slot Filling

引用

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2024年 32卷 3061-3075页

作者： Wei, Xiao Li, Yuhang Si, Yuke Wang, Longbiao Wang, Xiaobao Dang, Jianwu Tianjin Univ Coll Intelligence & Comp Tianjin Key Lab Cognit Comp & Applicat Tianjin 300350 Peoples R China Huiyan Technol Tianjin Co Ltd Tianjin Peoples R China

In task-oriented dialogue systems, slot filling aims to identify the semantic slot types of each token in user utterances. Due to the lack of sufficient supervised data in many scenarios, it is necessary to transfer relevant knowledge by using cross-domain slot filling. Previous studies rely on manually additional meta-information to build the relationships among similar slots across domains, yet not fully utilizing the knowledge learned by language models in the pre-training stage. In this study, we propose a prompt-based hierarchical pipeline (PHP) with three innovations. First, we design a hierarchical pipeline to separately model domain-independent syntactic structures and domain-specific semantic structures, i.e., span detection and slot prediction. Second, we improve the prompt paradigm with discriminative structure to fully utilize pre-trained language models, which reformulates downstream tasks into pre-trained tasks. Finally, we polish our template and verbalizer to effectively utilize task-specific prior knowledge, adding some meta-information and updating their additional trainable parameters. We conducted extensive experiments on three datasets to evaluate our method, and experimental results show that our method significantly outperforms the previous state-of-the-art results.

关键词： Task analysis Filling Pipelines Predictive models labeling Hidden Markov models Syntactics Cross-domain slot filling hierarchical multi-task learning prompt learning natural language understanding

来源：评论

学校读者我要写书评

暂无评论

Reliable data Augmented Contrastive Learning for Sequential Recommendation

引用

IEEE TRANSACTIONS ON BIG data 2024年第6期10卷 694-705页

作者： Zhao, Mankun Sun, Aitong Yu, Jian Li, Xuewei He, Dongxiao Yu, Ruiguo Yu, Mei Tianjin Univ Coll Intelligence & Comp Tianjin 300350 Peoples R China Tianjin Key Lab Adv Networking TANKLab Tianjin 300350 Peoples R China Tianjin Key Lab Cognit Comp & Applicat Tianjin 300350 Peoples R China

Sequential recommendation aims to capture users' dynamic preferences. Due to the limited information in the sequence and the uncertain user behavior, data sparsity has always been a key problem. Although data augmentation methods can alleviate this issue, unreliable data can affect the performance of such models. To solve the above problems, we propose a new framework, namely Reliable data Augmented Contrastive Learning Recommender (RDCRec). Specifically, in order to generate more high-quality reliable items for data augmentation, we design a multi-attributes oriented sequence generator. It moves auxiliary information from the input layer to the attention layer for learning a better attention distribution. Then, we replace a percentage of items in the original sequence with reliable items generated by the generator as the augmented sequence, for creating a high-quality view for contrastive learning. In this way, RDCRec can extract more meaningful user patterns by using the self-supervised signals of the reliable items, thereby improving recommendation performance. Finally, we train a discriminator to identify unreplaced items in the augmented sequence thus we can update item embeddings selectively in order to increase the exposure of more reliable items and improve the accuracy of recommendation results. The discriminator, as an auxiliary model, is jointly trained with the generative task and the contrastive learning task. Large experiments on four popular datasets that are commonly used demonstrate the effectiveness of our new method for sequential recommendation.

关键词： Reliability data augmentation Contrastive learning Generators Training Transformers Correlation Sequential recommendation contrastive learning attention mechanism data augmentation

来源：评论

学校读者我要写书评

暂无评论

Where is the Next Step? Predicting the Scientific Impact of Research Career

引用

IEEE TRANSACTIONS ON BIG data 2025年第3期11卷 1116-1127页

作者： Zhang, Hefu Ge, Yong Zhuang, Yan Chen, Enhong Univ Sci & Technol China Sch Comp Sci State Key Lab Cognit Intelligence Hefei 230027 Peoples R China Univ Arizona Tucson AZ 85721 USA

Predicting the scientific impact of research scholars is increasingly crucial for career planning, particularly for young scholars considering career transitions. However, predicting a scholar's future development, especially after they move to a different academic group, presents significant challenges. To tackle this issue, we propose a Future Publication Impact Prediction Network (FPIPN) based on graph neural networks. FPIPN leverages rich information from a heterogeneous academic graph for impact prediction. We employ a hierarchical attention mechanism to learn the significance of graph information and utilize a knowledge distillation strategy to assess future impact based on historical records. Extensive experiments on a real-world academic dataset showcase the effectiveness of our approach compared to state-of-the-art methods.

关键词： Scientific impact heterogeneous graph graph representation knowledge distillation Scientific impact heterogeneous graph graph representation knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

Bidirectional Patch-Aware Attention Network for Few-Shot Learning

引用

IEEE TRANSACTIONS ON compUTATIONAL SOCIAL SYSTEMS 2025年

作者： Mao, Yu Lin, Shaojie Lin, Zilong Lin, Yaojin Minnan Normal Univ Sch Comp Sci Zhangzhou 363000 Fujian Peoples R China Minnan Normal Univ Key Lab Data Sci & Intelligence Applicat Zhangzhou 363000 Fujian Peoples R China Minnan Normal Univ Key Lab Data Sci & Intelligence Applicat Zhangzhou 363000 Fujian Peoples R China

Few-shot learning (FSL) aims to train a model using a minimal number of samples and subsequently apply this model to recognize unseen classes. Recently, metric-based methods mainly focus on exploring the relationship between the support set and the query set through attention mechanism in solving FSL problems. However, these methods typically employ unidirectional computation when calculating the attention relationship between support and query. This unidirectional approach not only limits the depth and breadth of knowledge acquisition but may also lead to mismatched patches between support and query, thereby affecting the overall performance of the model. In this article, we propose a bidirectional patch-aware attention network for few-shot learning (BPAN) to address this issue. First, we extract subimages via grid cropping and feed them into the learned feature extractor to obtain patch features. Moreover, self-attention is used to assign different weights to patch features and reconstruct them. Then, PFCAM is proposed to mutually explore the patch feature relationship between the support set and the support set, further reconstruct the patch features, and aggregate multiple patch features of each image into one feature through a learnable parameter matrix for the purpose of prediction. Finally, the template for each class is constructed to extend the results of PFCAM to the few-shot classification scenario. Experiments on three benchmark datasets show that BPAN achieves superior performance.

关键词： Feature extraction Few shot learning Image reconstruction Attention mechanisms Vectors Semantics computational modeling Training Prototypes Dogs Attention mechanism bidirectional patchaware feature aggregation few-shot learning

来源：评论

学校读者我要写书评

暂无评论

HMNet: a hierarchical multi-modal network for educational video concept prediction

引用

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 2023年第9期14卷 2913-2924页

作者： Huang, Wei Xiao, Tong Liu, Qi Huang, Zhenya Ma, Jianhui Chen, Enhong Univ Sci & Technol China Anhui Prov Key Lab Big Data Anal & Applicat Hefei Peoples R China State Key Lab Cognit Intelligence Hefei Peoples R China

Educational video concept prediction is a challenging task in the online education system that aims to assign appropriate hierarchical concepts to the video. The key to this problem is to model and fuse the multimodal information of the video. However, most prior studies tend to ignore the incremental characteristics of the educational video, and most of the video segmentation strategies do not apply well to the educational video. Moreover, most existing methods overlook the class hierarchy and do not consider the class dependencies when predicting the hierarchical concepts of a video. To that end, in this paper, we propose a Hierarchical Multi-modal Network (HMNet) framework for predicting the hierarchical concepts of educational videos via fusing the multimodal information and modeling the class dependencies. Specifically, we first apply a video divider for extracting keyframes from the video, which considers the incremental characteristics of the educational video. The video is divided into a series of video sections with subtitles. Then, we utilize a multi-modal encoder to obtain the unified representation for multi-modality. Finally, we design a hierarchical predictor capable of fusing the multi-modality representation, modeling the class dependencies and predicting the hierarchical concepts of video in a top-down manner. Extensive experimental results on two real-world datasets demonstrate the effectiveness and explanatory power of HMNet.

关键词： Educational videos Multi-modality Hierarchical multi-label classification

来源：评论

学校读者我要写书评

暂无评论

EHPR: Learning evolutionary hierarchy perception representation based on quaternion for temporal knowledge graph completion

引用

INFORMATION SCIENCES 2025年 688卷

作者： Guo, Jiujiang Zhao, Mankun Yu, Jian Yu, Ruiguo Song, Jianhang Wang, Qifei Xu, Linying Yu, Mei Tianjin Univ Coll Intelligence & Comp Tianjin 300354 Peoples R China Tianjin Univ Tianjin Key Lab Adv Networking Tianjin 300354 Peoples R China Tianjin Univ Tianjin Key Lab Cognit Comp & Applicat Tianjin 300354 Peoples R China

Research on temporal knowledge graphs garners attention due to the intricate connection between facts and dynamic temporal factors. However, existing research uses timestamp as auxiliary data for representation learning and directly integrate it into facts, resulting in the inability to capture the intrinsic connections between relations under time evolution. To handle these challenges, we propose the E volutionary H ierarchy P erception R epresentation (EHPR), which first leverages the Hamilton product to perform rotational transformations on relation and entity over time, aiming to learn temporal relation and temporal entity with close interactions with time information. Later, EHPR is divided into two modules: (a) Rotating the head entity towards the tail entity using temporal relation through Hamilton product to model complex patterns with quaternion rotation capabilities. (b) Adopting an evolutionary hierarchical factor to capture the differences in modulus distribution between the temporal head entity and the temporal tail entity, aiming to manage the evolutionary hierarchical information between different temporal entities. In this way, EHPR not only utilizes the rich quaternion rotation capabilities to model various relation patterns but also further enables modeling of evolutionary hierarchical patterns through evolutionary hierarchy factors. Experiments show that EHPR achieves remarkable performance on six mature benchmarks compared to state-of-the-art models. Furthermore, we successfully transferred the core idea of EHPR into complex embeddings, showcasing the framework's adaptability. compared to complex embedding models, EHPR also demonstrates stronger expressive abilities with the Hamilton operator, surpassing the performance of complex Hermitian operator.

关键词： Temporal knowledge graph Quaternion Evolutionary hierarchy information

来源：评论

学校读者我要写书评

暂无评论

Invariant representation learning via decoupling style and spurious features

引用

MACHINE LEARNING 2025年第2期114卷 1-20页

作者： Li, Ruimeng Pu, Yuanhao Li, Zhaoyi Wu, Chenwang Xie, Hong Lian, Defu Univ Sci & Technol China Sch Artificial Intelligence & Data Sci Hefei 230026 Anhui Peoples R China Univ Sci & Technol China Sch Comp Sci & Technol Hefei 230027 Anhui Peoples R China State Key Lab Cognit Intelligence Hefei 230088 Anhui Peoples R China

This paper considers the out-of-distribution (OOD) generalization problem under the setting that both style distribution shift and spurious features exist and domain labels are missing. This setting frequently arises in real-world applications and is underlooked because previous approaches mainly handle either of these two factors. The critical challenge is decoupling style and spurious features in the absence of domain labels. We propose a structural causal model (SCM) for the image generation process to address this challenge, considering both style distribution shifts and spurious features. The proposed SCM enables us to design a new framework called IRSS, which can gradually separate style distribution and spurious features from images by introducing adversarial neural networks and multi-environment optimization, thus achieving OOD generalization. Moreover, it does not require additional supervision (e.g., domain labels) other than the images and their corresponding labels. Experiments on benchmark datasets demonstrate that IRSS outperforms traditional OOD methods and solves the problem of Invariant risk minimization degradation, enabling the extraction of invariant features under distribution shift.

关键词： computer vision Domain generalization Representation learning Causal learning

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：