检索结果-内蒙古大学图书馆

Named Entity Recognition Based on Knowledge Fusion and Boundary Feature Sharing

学校读者我要写书评

暂无评论

Named Entity Recognition Based on Knowledge Fusion and Bound...

Advanced Algorithms and control Engineering (ICAACE), International Conference on

作者： Anrui Li Housheng Su School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan P. R. China Key Laboratory of Image Processing and Intelligence Control of Ministry of Education Huazhong University of Science and Technology Wuhan P. R. China

ISBN: (数字)9798331535087

ISBN: (纸本)9798331535094

Named entity recognition is a core task in the field of information extraction, which aims to recognize a relevant entity from unstructured text and classify that entity. Aiming at the problem that existing nested named entity recognition models cannot achieve better compatibility in recognizing long entities and the performance of the models, this study proposes a nested named entity recognition model based on knowledge fusion and boundary feature sharing. First, a joint training network based on the concepts of lexicon and knowledge graph is constructed to improve the text feature representation to obtain richer contextual information; second, the bimodal attention mechanism is used to capture the semantic correlation between lexical items and generate the spanning semantic representation matrix; furthermore, the boundary feature sharing strategy is designed to improve the generalization ability of the model for the rough transition problem of entity spanning boundaries. To verify the effectiveness of the model, it is tested on three benchmark datasets, including ACE2004, ACE2005, and SciERC datasets. The experimental results show that the proposed model outperforms the corresponding baseline model in terms of entity recognition F1 index.

关键词： Training Knowledge engineering Attention mechanisms Text recognition Semantics Named entity recognition Knowledge graphs Lexicon Information retrieval Context modeling

Learning Analysis of Kernel Ridgeless Regression with Asymmetric Kernel Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： He, Fan He, Mingzhen Shi, Lei Huang, Xiaolin Suykens, Johan A.K. STADIUS Center for Dynamical Systems Signal Processing and Data Analytics KU Leuven Leuven Belgium MOE Key Laboratory of System Control and Information Processing Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China Shanghai Key Laboratory for Contemporary Applied Mathematics School of Mathematical Sciences Fudan University Shanghai200433 China Shanghai Artificial Intelligence Laboratory Shanghai200232 China MOE Key Laboratory of System Control and Information Processing Institute of Image Processing and Pattern Recognition Institute of Medical Robotics Shanghai Jiao Tong University Shanghai200240 China

Ridgeless regression has garnered attention among researchers, particularly in light of the "Benign Overfitting" phenomenon, where models interpolating noisy samples demonstrate robust generalization. However, kernel ridgeless regression does not always perform well due to the lack of flexibility. This paper enhances kernel ridgeless regression with Locally-Adaptive-Bandwidths (LAB) RBF kernels, incorporating kernel learning techniques to improve performance in both experiments and theory. For the first time, we demonstrate that functions learned from LAB RBF kernels belong to an integral space of Reproducible Kernel Hilbert Spaces (RKHSs). Despite the absence of explicit regularization in the proposed model, its optimization is equivalent to solving an 0-regularized problem in the integral space of RKHSs, elucidating the origin of its generalization ability. Taking an approximation analysis viewpoint, we introduce an lq-norm analysis technique (with 0 © 2024, CC BY.

关键词： Vector spaces

HR-Pro: Point-supervised Temporal Action Localization via Hierarchical Reliability Propagation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Huaxin Wang, Xiang Xu, Xiaohao Qing, Zhiwu Gao, Changxin Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China University of Michigan Ann Arbor United States

Point-supervised Temporal Action Localization (PSTAL) is an emerging research direction for label-efficient learning. However, current methods mainly focus on optimizing the network either at the snippet-level or the instance-level, neglecting the inherent reliability of point annotations at both levels. In this paper, we propose a Hierarchical Reliability Propagation (HR-Pro) framework, which consists of two reliability-aware stages: Snippet-level Discrimination Learning and Instance-level Completeness Learning, both stages explore the efficient propagation of high-confidence cues in point annotations. For snippet-level learning, we introduce an online-updated memory to store reliable snippet prototypes for each class. We then employ a Reliability-aware Attention Block to capture both intra-video and inter-video dependencies of snippets, resulting in more discriminative and robust snippet representation. For instance-level learning, we propose a point-based proposal generation approach as a means of connecting snippets and instances, which produces high-confidence proposals for further optimization at the instance level. Through multi-level reliability-aware learning, we obtain more reliable confidence scores and more accurate temporal boundaries of predicted proposals. Our HR-Pro achieves state-of-the-art performance on multiple challenging benchmarks, including an impressive average mAP of 60.3% on THUMOS14. Notably, our HR-Pro largely surpasses all previous point-supervised methods, and even outperforms several competitive fully-supervised methods. Code will be available at https://***/pipixin321/HR-Pro. Copyright © 2023, The Authors. All rights reserved.

关键词： Reliability

Evolutionary attraction–repulsion algorithm embedded with LLM for UAV task allocation

学校读者我要写书评

暂无评论

Advanced Engineering Informatics 2025年 66卷

作者： Wu, Bowen Xiao, Renbin School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Institute of Artificial Intelligence Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan430074 China

Labor division provides an adaptive and scalable technique for unmanned systems. However, its designing process usually relies heavily on the manually crafted paradigms, leading to inefficiencies and insufficient performance. To overcome these challenges, this paper introduce an evolutionary approach to labor division algorithm design. Drawing inspiration from the regulatory behaviors observed in natural lion populations, we propose a bipolar feedback-guided attraction–repulsion mechanism. A formal model is developed to encapsulate this mechanism, and we provide an in-depth analysis of the algorithm's evolution through the framework of systems science. In addition, we leverage prompt engineering techniques to integrate a large language model (LLM) with our proposed mechanism, facilitating a bidirectional enhancement between the two. This integration culminates in the development of the ARE-LLM framework, a robust and adaptive solution for designing labor division algorithms. To demonstrate the practical applicability of our approach, we apply the ARE-LLM framework to the UAV-based task allocation problem for enemy air defense suppression. The experimental results indicate that our method outperforms several advanced approaches. In a scenario involving 50 UAVs tasked with completing 300 assignments, the total distance traveled is only 9 % of that required by the ALPDA algorithm, while the processing time is reduced to 8 % of that used by ALPDA. © 2025 Elsevier Ltd

关键词： Target drones

Saliency Regularization for Self-Training with Partial Annotations

学校读者我要写书评

暂无评论

Saliency Regularization for Self-Training with Partial Annot...

International Conference on Computer Vision (ICCV)

作者： Shouwen Wang Qian Wan Xiang Xiang Zhigang Zeng School of Artificial Intelligence and Automation Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control Ministry of Education Wuhan Research Institute of Posts and Telecommunications

Partially annotated images are easy to obtain in multi-label classification. However, unknown labels in partially annotated images exacerbate the positive-negative imbalance inherent in multi-label classification, which affects supervised learning of known labels. Most current methods require sufficient image annotations, and do not focus on the imbalance of the labels in the supervised training phase. In this paper, we propose saliency regularization (SR) for a novel self-training framework. In particular, we model saliency on the class-specific maps, and strengthen the saliency of object regions corresponding to the present labels. Besides, we introduce consistency regularization to mine unlabeled information to complement unknown labels with the help of SR. It is verified to alleviate the negative dominance caused by the imbalance, and achieve state-of-the-art performance on Pascal VOC 2007, MS-COCO, VG-200, and Openimages V3.

关键词：

Few-shot Action Recognition with Captioning Foundation Models

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Xiang Zhang, Shiwei Yuan, Hangjie Zhang, Yingya Gao, Changxin Zhao, Deli Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Alibaba Group China Zhejiang University China

Transferring vision-language knowledge from pretrained multimodal foundation models to various downstream tasks is a promising direction. However, most current few-shot action recognition methods are still limited to a single visual modality input due to the high cost of annotating additional textual descriptions. In this paper, we develop an effective plug-and-play framework called CapFSAR to exploit the knowledge of multimodal models without manually annotating text. To be specific, we first utilize a captioning foundation model (i.e., BLIP) to extract visual features and automatically generate associated captions for input videos. Then, we apply a text encoder to the synthetic captions to obtain representative text embeddings. Finally, a visual-text aggregation module based on Transformer is further designed to incorporate cross-modal spatio-temporal complementary information for reliable few-shot matching. In this way, CapFSAR can benefit from powerful multimodal knowledge of pretrained foundation models, yielding more comprehensive classification in the low-shot regime. Extensive experiments on multiple standard few-shot benchmarks demonstrate that the proposed CapFSAR performs favorably against existing methods and achieves state-of-the-art performance. The code will be made publicly available. Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

Improving Transferability of Adversarial Point Clouds with Model Commonalities

学校读者我要写书评

暂无评论

Improving Transferability of Adversarial Point Clouds with M...

IEEE International Conference on Cyborg and Bionic Systems (CBS)

作者： Junting Lv Lianguang Liu Yutong Zhang Depeng Li Zhigang Zeng School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Wuhan China

Although deep learning of 3D point clouds has made significant progress, the robustness of 3D models has not been fully investigated. Existing 3D attack methods show satisfactory performance under the white-box setting but frequently suffer from a low transferability to attack black-box models. A key point to improve the transferability of attacks is to find the commonalities of multiple models. To this end, a novel attack method is proposed by only leveraging perturbations in local geometric feature areas termed FAP. Specifically, local perturbations are pertinently added by calculating the curvature to sample more points in the feature areas that 3D models potentially focus on. Moreover, to address the drawback of poor isometric robustness common to 3D models, we propose a generalized framework for diversifying input samples by adding random isometric transformations (DIT) in the attack process, which can be combined with other attack methods to improve their transferability. Evaluated on a variety of typical 3D models, the proposed attack method outperforms the current gradient-based methods in transferable black-box attacks, and the effectiveness of the proposed framework is demonstrated by extending it to other attack methods.

关键词： Point cloud compression Solid modeling Three-dimensional displays Shape Perturbation methods Closed box Focusing

Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Qing, Zhiwu Zhang, Shiwei Wang, Jiayu Wang, Xiang Wei, Yujie Zhang, Yingya Gao, Changxin Sang, Nong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Alibaba Group China Fudan University China

Despite diffusion models having shown powerful abilities to generate photorealistic images, generating videos that are realistic and diverse still remains in its infancy. One of the key reasons is that current methods intertwine spatial content and temporal dynamics together, leading to a notably increased complexity of text-to-video generation (T2V). In this work, we propose HiGen, a diffusion modelbased method that improves performance by decoupling the spatial and temporal factors of videos from two perspectives, i.e., structure level and content level. At the structure level, we decompose the T2V task into two steps, including spatial reasoning and temporal reasoning, using a unified denoiser. Specifically, we generate spatially coherent priors using text during spatial reasoning and then generate temporally coherent motions from these priors during temporal reasoning. At the content level, we extract two subtle cues from the content of the input video that can express motion and appearance changes, respectively. These two cues then guide the model's training for generating videos, enabling flexible content variations and enhancing temporal stability. Through the decoupled paradigm, HiGen can effectively reduce the complexity of this task and generate realistic videos with semantics accuracy and motion stability. Extensive experiments demonstrate the superior performance of HiGen over the state-of-the-art T2V methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

Canine EEG Helps Human: Cross-Species and Cross-Modality Epileptic Seizure Detection via Multi-Space Alignment

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Ziwei Li, Siyang Wu, Dongrui Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Hubei Key Laboratory of Brain-inspired Intelligent Systems School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

Epilepsy significantly impacts global health, affecting about 65 million people worldwide, along with various animal species. The diagnostic processes of epilepsy are often hindered by the transient and unpredictable nature of seizures. Here we propose a multi-space alignment approach based on cross-species and cross-modality electroencephalogram (EEG) data to enhance the detection capabilities and understanding of epileptic seizures. By employing deep learning techniques, including domain adaptation and knowledge distillation, our framework aligns cross-species and cross-modality EEG signals to enhance the detection capability beyond traditional within-species and within-modality models. Experiments on multiple surfaces and intracranial EEG datasets of humans and canines demonstrated substantial improvements in detection accuracy, achieving over 90% AUC scores for cross-species and cross-modality seizure detection with extremely limited labeled data from the target species/modality. To our knowledge, this is the first study that demonstrates the effectiveness of integrating heterogeneous data from different species and modalities to improve EEG-based seizure detection performance. This is a pilot study that provides insights into the challenges and potential of multi-species and multi-modality data integration, offering an effective solution for future work to collect huge EEG data to train large brain models. © 2024, CC BY.

关键词： Electroencephalography