检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Hang Xu Xinyuan Liu Qiang Zhao Yike Ma Chenggang Yan Feng Dai Hangzhou Dianzi University Hangzhou China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology Chinese Academy of Sciences Beijing China

Spherical image object detection emerges in many applications from virtual reality to robotics and automatic driving, while many existing detectors use $l_{n}$ -norms loss for regression of spherical bounding boxes. There are two intrinsic flaws for $l_{n}$ -norms loss, i.e., independent optimization of parameters and inconsistency between metric (dominated by IoU) and loss. These problems are common in planar image detection but more significant in spherical image detection. Solution for these problems has been extensively discussed in planar image detection by using IoU loss and related variants. However, these solutions cannot be migrated to spherical image object detection due to the undifferentiable of the Spherical IoU (SphIoU). In this paper, we design a simple but effective regression loss based on Gaussian Label Distribution Learning (GLDL) for spherical image object detection. Besides, we observe that the scale of the object in a spherical image varies greatly. The huge differences among objects from different categories make the sample selection strategy based on SphIoU challenging. Therefore, we propose GLDL-ATSS as a better training sample selection strategy for objects of the spherical image, which can alleviate the drawback of IoU threshold-based strategy of scale-sample imbalance. Extensive results on various two datasets with different baseline detectors show the effectiveness of our approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Glance and focus: memory prompting for multi-event video question answering 23

Glance and focus: memory prompting for multi-event video que...

引用

Proceedings of the 37th International Conference on Neural information Processing Systems

作者： Ziyi Bai Ruiping Wang Xilin Chen Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China and University of Chinese Academy of Sciences Beijing China

Video Question Answering (VideoQA) has emerged as a vital tool to evaluate agents' ability to understand human daily behaviors. Despite the recent success of large vision language models in many multi-modal tasks, complex situation reasoning over videos involving multiple human-object interaction events still remains challenging. In contrast, humans can easily tackle it by using a series of episode memories as anchors to quickly locate question-related key moments for reasoning. To mimic this effective reasoning strategy, we propose the Glance-Focus model. One simple way is to apply an action detection model to predict a set of actions as key memories. However, these actions within a closed set vocabulary are hard to generalize to various video domains. Instead of that, we train an Encoder-Decoder to generate a set of dynamic event memories at the glancing stage. Apart from using supervised bipartite matching to obtain the event memories, we further design an unsupervised memory generation method to get rid of dependence on event annotations. Next, at the focusing stage, these event memories act as a bridge to establish the correlation between the questions with high-level event concepts and low-level lengthy video content. Given the question, the model first focuses on the generated key event memory, then focuses on the most relevant moment for reasoning through our designed multi-level cross-attention mechanism. We conduct extensive experiments on four Multi-Event VideoQA benchmarks including STAR, EgoTaskQA, AGQA, and NExT-QA. Our proposed model achieves state-of-the-art results, surpassing current large models in various challenging reasoning tasks. The code and models are available at https://***/ByZ0e/Glance-Focus.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prediction of exosomal piRNAs based on deep learning for sequence embedding with attention mechanism

Prediction of exosomal piRNAs based on deep learning for seq...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Liu, Yajun Ding, Yulian Li, Aimin Fei, Rong Guo, Xie Wu, Fangxiang Xi'an University of Technology Shaanxi Key Laboratory for Network Computing and Security Technology Xi'an China University of Saskatchewan Division of Biomedical Engineering Saskatoon Canada Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an China University of Saskatchewan Division of Biomedical Engineering Department of Computer Science Department of Mechanical Engineering Saskatoon Canada

ISBN: (纸本)9781665468190

PIWI-interacting RNAs (piRNAs) are a type of small non-coding RNAs which bind with the PIWI proteins to exert biological effects in various regulatory mechanisms. A growing amount of evidence reveals that exosomal piRNAs are potential biomarkers for diagnosis and treatment of complex diseases. Effective methods for the prediction of exosomal piRNAs are the foundation of piRNA functional research. In this study, we propose an end-to-end deep network for identifying exosomal piRNAs based on features learned from natural language processing (NLP) models for sequence embedding with attention mechanism. First, a benchmark dataset is constructed by processing piRNA subcellular localization annotated data and sequence data. Moreover, bagging positive unlabeled learning is applied to get the reliable negative set. Finally, we treat a piRNA sequence as a sentence and its k-mer subsequence as a token. Sequence embedding models with self-attention mechanism is designed to extract features from exosome piRNA sequences, which are used for the prediction task. Compared with three competing methods, our model achieves the best performance and reveals the key factors of exosomal piRNA sequences by the attention mechanism. Our model characterizes exosomal piRNAs and could be beneficial for researchers to investigate exosomal piRNAs' functions. © 2022 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

A Novel Remaining Useful Life Prediction Model Based on Adaptive Feature Fusion and its Application to Rolling Bearings

SSRN

引用

SSRN 2024年

作者： Guo, Kai Ma, Jun Wu, Jiande Xiong, Xin Faculty of Information Engineering & Automation Kunming University of Science and Technology Kunming650500 China Yunnan International Joint Laboratory of Intelligent Control and Application of Advanced Equipment Kunming University of Science and Technology Kunming650500 China Yunnan Key Laboratory of Intelligent Systems and Computing Yunnan University Kunming650500 China

As a key component in the transmission system of high-speed trains, once a failure occurs, it will directly affect the safety of train operation. Therefore, it is of great significance to construct a degradation index that can comprehensively characterize the running state of bearings and establish a reliable remaining useful life model to ensure the safety of train operation. Aiming at the problems that the redundant features in the existing multi-feature fusion process affect the diagnosis performance and the spurious fluctuations phenomenon of the fusion features causes the inaccurate determination of the start fault time and leads to the low prediction accuracy of remaining useful life (RUL), A method based on adaptive feature fusion and autoregressive integrated moving average model is proposed for rolling bearings prediction. The research in this study demonstrates that by comparing and verifying with two sets of public data, the proposed method is effective in accurately identifying the features that are most sensitive to degradation trends, accurately determine the initial fault moment of bearings, achieve effective prediction of the RUL of bearings, and the related research results can provide reference basis for predictive maintenance of train bearings. © 2024, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Beyond MLE: convex learning for text generation 23

Beyond MLE: convex learning for text generation

引用

Proceedings of the 37th International Conference on Neural information Processing Systems

作者： Chenze Shao Zhengrui Ma Min Zhang Yang Feng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences and University of Chinese Academy of Sciences School of Future Science and Engineering Soochow University

Maximum likelihood estimation (MLE) is a statistical method used to estimate the parameters of a probability distribution that best explain the observed data. In the context of text generation, MLE is often used to train generative language models, which can then be used to generate new text. However, we argue that MLE is not always necessary and optimal, especially for closed-ended text generation tasks like machine translation. In these tasks, the goal of model is to generate the most appropriate response, which does not necessarily require it to estimate the entire data distribution with MLE. To this end, we propose a novel class of training objectives based on convex functions, which enables text generation models to focus on highly probable outputs without having to estimate the entire data distribution. We investigate the theoretical properties of the optimal predicted distribution when applying convex functions to the loss, demonstrating that convex functions can sharpen the optimal distribution, thereby enabling the model to better capture outputs with high probabilities. Experiments on various text generation tasks and models show the effectiveness of our approach. It enables autoregressive models to bridge the gap between greedy and beam search, and facilitates the learning of non-autoregressive models with a maximum improvement of 9+ BLEU points. Moreover, our approach also exhibits significant impact on large language models (LLMs), substantially enhancing their generative capability on various tasks. Source code is available at https://***/ictnlp/Convex-Learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EDA: Enhanced Domain-Adversarial Training for Anatomical Landmark Detection

EDA: Enhanced Domain-Adversarial Training for Anatomical Lan...

引用

IEEE International Symposium on Biomedical Imaging

作者： Fan Yang S. Kevin Zhou School of Biomedical Engineering Division of Life Sciences and Medicine University of Science and Technology of China Hefei Anhui China Center for Medical Imaging Robotics Analytic Computing & Learning (MIRACLE) Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou Jiangsu China Key Laboratory of Precision and Intelligent Chemistry USTC Hefei Anhui China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Manually annotating anatomical landmarks in medical images requires experienced clinicians and is a labor-intensive process. However, recent AI-assisted methods for landmark detection often rely on the training and test data originating from the same domain. This work introduces a novel unsupervised domain adaptation (UDA) framework aimed at anatomical landmark detection from a medical image, designed to bridge the gap between a source domain with labels and an unlabeled target domain. Specifically, we have developed a new Domain-Adversarial Network that incorporates skip connections to transfer and fuse high-resolution feature maps. Additionally, we proposed Dynamic Gaussian Learning, which allows the model to escape from local error regions. We carry out experiments on landmark detection for both head and chest, and the results demonstrate that our method achieves state-of-the-art performances in each experiment.

关键词： Training Measurement Adaptation models Three-dimensional displays Smoothing methods Head Kernel Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Image Moment Invariants to Rotational Motion Blur

arXiv

引用

arXiv 2023年

作者： Mo, Hanlin Hao, Hongxiang Zhao, Guoying Center for Machine Vision and Signal Analysis University of Oulu Finland Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

Rotational motion blur caused by the circular motion of the camera or/and object is common in life. Identifying objects from images affected by rotational motion blur is challenging because this image degradation severely impacts image quality. Therefore, it is meaningful to develop image invariant features under rotational motion blur and then use them in practical tasks, such as object classification and template matching. This paper proposes a novel method to generate image moment invariants under general rotational motion blur and provides some instances. Further, we achieve their invariance to similarity transform. To the best of our knowledge, this is the first time that moment invariants for rotational motion blur have been proposed in the literature. We conduct extensive experiments on various image datasets disturbed by similarity transform and rotational motion blur to test these invariants’ numerical stability and robustness to image noise. We also demonstrate their performance in image classification and handwritten digit recognition. Current state-of-the-art blur moment invariants and deep neural networks are chosen for comparison. Our results show that the moment invariants proposed in this paper significantly outperform other features in various tasks. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Design of Control Circuit for Active Metasurface Based on Varactor Diode

Design of Control Circuit for Active Metasurface Based on Va...

引用

International Applied Computational Electromagnetics Society Symposium (ACES)

作者： Yue Zhang Yuefei Liu Guohui Yang Kuang Zhang Yingsong Li School of Electronics and Information Engineering Harbin Institute of Technology Harbin China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China

A control circuit for active metasurface based on varactor diode is designed in this paper. By varying the reverse bias voltage on the varactor diode, the designed circuit can regulate the additional phase of the active meta-atoms. The circuit adopts a form of one master and multiple slaves, which can simultaneously control the bias voltage of 960 meta-atoms. Each slave can control up to 64 channels. The control accuracy is 0.04V. The power consumption of a single slave is 160mW. Though experiment verification, the circuit has a good effect in controlling the beam deflection of the metasurface and generating OAM beams.

关键词：

来源：评论

学校读者我要写书评

暂无评论

mmFAS: Multimodal Face Anti-Spoofing Using Multi-Level Alignment and Switch-Attention Fusion 39

mmFAS: Multimodal Face Anti-Spoofing Using Multi-Level Align...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Chen, Geng Xie, Wuyuan Lin, Di Liu, Ye Wang, Miaohui College of CSSE Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University China State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications China College of Intelligence and Computing Tianjin University China School of Automation Nanjing University of Posts and Telecommunications China

ISBN: (纸本)157735897X

The increasing number of presentation attacks on reliable face matching has raised concerns and garnered attention towards face anti-spoofing (FAS). However, existing methods for FAS modeling commonly fuse multiple visual modalities (e.g., RGB, Depth, and Infrared) in a straightforward manner, disregarding latent feature gaps that can hinder representation learning. To address this challenge, we propose a novel multimodal FAS framework (mmFAS) that focuses on explicit alignment and fusion of latent features across different modalities. Specifically, we develop a multimodal alignment module to alleviate the latent feature gap by using instance-level contrastive learning and class-level matching simultaneously. Further, we explore a new switch-attention based fusion module to automatically aggregate complementary information and control model complexity. To evaluate the anti-spoofing performance more effectively, we adopt a challenging yet meaningful cross-database protocol involving four benchmark multimodal FAS datasets to simulate real-world scenarios. Extensive experimental results demonstrate the effectiveness of mmFAS in improving the accuracy of FAS systems, outperforming 10 representative methods. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Home Safety IoT Monitoring Method Based on ZigBee Networking

A Novel Home Safety IoT Monitoring Method Based on ZigBee Ne...

引用

International Conference on Wireless Communications, Networking and Applications, WCNA 2021

作者： An, Ning Li, Peng Wang, Xiaoming Wu, Xiaojun Dang, Yuntong School of Computer Science Shaanxi Normal University Xi’an710119 China Key Laboratory of Intelligent Computing and Service Technology for Folk Song Ministry of Culture and Tourism Xi’an710119 China Key Laboratory of Modern Teaching Technology Ministry of Education Xi’an710062 China Engineering Laboratory of Teaching Information Technology of Shaanxi Province Xi’an710119 China School of Music Shaanxi Normal University Xi’an710119 China

ISBN: (纸本)9789811924552

This paper realizes the design of home safety early warning system by studying the wireless communication networking technology of ZigBee and WiFi, as well as sensor communication technology, which is based on taking home safety monitoring as the application background. In this study, CC2530 chip was used as ZigBee wireless communication module. A novel home security IoT monitoring method was proposed through sensor triggering, human activity trajectory perception algorithm design, and wireless networking and communication optimization. Meanwhile, the safety early warning and remote monitoring of home staff can be realized, and home safety can be guaranteed. The system can achieve the purpose of home monitoring and early warning with low software and hardware cost through the experimental design and result analysis. It can not only provide reference for the design of sensor communication system, but also provide technical reference for aging society and response. © 2022, The Author(s).

关键词： Zigbee

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：