检索结果-内蒙古大学图书馆

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Junke Wang Dongdong Chen Chong Luo Bo He Lu Yuan Zuxuan Wu Yu-Gang Jiang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University Shanghai Collaborative Innovation Center of Intelligent Visual Computing Microsoft Cloud + AI Microsoft Research Asia University of Maryland College Park

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

The core of video understanding tasks, such as recognition, captioning, and tracking, is to automatically de-tect objects or actions in a video and analyze their temporal evolution. Despite sharing a common goal, different tasks often rely on distinct model architectures and annotation formats. In contrast, natural language processing benefits from a unified output space, i.e., text sequences, which simplifies the training of powerful foundational language models, such as GPT-3, with extensive training cor-pora. Inspired by this, we seek to unify the output space of video understanding tasks by using languages as labels and additionally introducing time and box tokens. In this way, a variety of video tasks could be formulated as video-grounded token generation. This enables us to address var-ious types of video tasks, including classification (such as action recognition), captioning (covering clip captioning, video question answering, and dense video captioning), and localization tasks (such as visual object tracking) within a fully shared encoder-decoder architecture, following a generative framework. Through comprehensive experiments, we demonstrate such a simple and straightforward idea is quite effective and can achieve state-of-the-art or compet-itive results on seven video benchmarks, providing a novel perspective for more universal video understanding. Code is available at https://***/wangjk666/OmniVid.

关键词： Training Location awareness Visualization Vocabulary Computer architecture Benchmark testing Robustness

来源：评论

学校读者我要写书评

暂无评论

System for the large scale intelligent treatment of sludge 2

System for the large scale intelligent treatment of sludge

引用

2nd International Conference on Information technology and intelligent Control, CITIC 2022

作者： Yang, Rui Gan, Lin Mo, Qinglong Li, Yuhong Hu, Ruihan Guangdong Institute of Intelligent Manufacturing Guangdong Key Laboratory of Modern Control Technology Guangzhou510070 China Cloud Computing Center Chinese Academy of Sciences Dongguan523808 China Guangdong Key Laboratory of Modern Control Technology Guangdong Institute of Intelligent Manufacturing Guangzhou China Engineering Research Center of Intelligence Perception and Autonomous Control Ministry of Education Beijing China Xinjiang Production and Construction Corps Key Laboratory of Modern Agricultural Machinery Shihezi University Shihezi China

ISBN: (纸本)9781510657649

In this study, by examining the effects of the optimal carbon-nitrogen ratio and other factors on the composting effect, the optimal composting parameters of municipal sludge and kitchen waste were determined, and the carbon emissions were calculated at the same time, It had reference value for carbon neutralization and carbon peak. On the basis of reduction, harmlessness and resource utilization, a coordinated aerobic composting process for municipal sludge, kitchen waste and agricultural and forestry waste was established. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Carbon

来源：评论

学校读者我要写书评

暂无评论

Novel activation function with pixelwise modeling capacity for lightweight neural network design

Novel activation function with pixelwise modeling capacity f...

引用

作者： Liu, Yi Guo, Xiaozhou Tan, Kaijun Gong, Guoliang Lu, Huaxiang Lab of Artificial Networks Institute of Semiconductors Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing China

The development of lightweight networks makes neural networks more efficient to be widely applied to various tasks. Considering the deployment of hardware like edge devices and mobile phones, we prioritize lightweight networks. However, their accuracy has always lagged far behind SOTA networks. In this article, we present a simple yet effective activation function, called WReLU, to improve the performance of lightweight networks significantly by adding a residual spatial condition. Moreover, we use a strategy to switch activation functions after determining which convolutional layer to use. We perform experiments on ImageNet 2012 classification dataset in CPU, GPU, and edge devices. Experiments demonstrate that WReLU improves the accuracy of classification significantly. Meanwhile, our strategy balances the effect of additional parameters and multiply accumulate. Our method improves the accuracy of SqueezeNet and SqueezeNext by more than 5% without increasing extensive parameters and computation. For the lightweight network with a large number of parameters, such as MobileNet and ShuffleNet, there is also a significant improvement. Additionally, the inference speed of most lightweight networks using our WReLU strategy is almost the same as the baseline model on different platforms. Our approach not only ensures the practicability of the lightweight network but also improves its performance. © 2021 John Wiley & Sons Ltd.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Suppress content shift: better diffusion features via off-the-shelf generation techniques 24

Suppress content shift: better diffusion features via off-th...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Benyuan Meng Qianqian Xu Zitai Wang Zhiyong Yang Xiaochun Cao Qingming Huang Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Peng Cheng Laboratory Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS School of Computer Science and Tech. University of Chinese Academy of Sciences School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Key Laboratory of Big Data Mining and Knowledge Management CAS

ISBN: (纸本)9798331314385

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is available at https://***/Darkbblue/diffusion-content-shift.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploiting Knowledge Embedding to Improve the Description for Image Captioning 5th

Exploiting Knowledge Embedding to Improve the Description fo...

引用

5th China Conference on Knowledge Graph, and Semantic computing, CCKS 2020

作者： Song, Dandan Peng, Cuimei Yang, Huan Liao, Lejian Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications Beijing Key Laboratory of Intelligent Information Technology School of Computer Science and Technology Beijing Institute of Technology Beijing China

ISBN: (纸本)9789811619632

Most existing methods for image captioning are based on the encoder-decoder framework which directly translates visual features into sentences, without exploiting commonsense knowledge available in the form of knowledge graph. Inspired by the success of information retrieval and question answering systems that leverage prior knowledge, we explore a knowledge embedding approach for image captioning. In this paper, we propose a Knowledge Embedding with Attention on Attention (KE-AoA) method for image captioning, which judges whether or how well the objects are related and augments semantic correlations and constraints between them. The KE-AoA method combines knowledge base method (TransE) and text method (Skip-gram), adding external knowledge graph information (triplets) into the language model to guide the learning of word vectors as the regularization term. Then it employs the AoA module to model the relations among different objects. As more inherent relations and commonsense knowledge are learned, the model can generate better image descriptions. The experiments on MSCOCO data sets achieve a significant improvement on the existing methods and validate the effectiveness of our prior knowledge-based approach. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

intelligent 3D Visual defect Detection for Industrial Applications 3

Intelligent 3D Visual defect Detection for Industrial Applic...

引用

2022 3rd International Conference on Internet of Things, Artificial Intelligence and Mechanical Automation, IoTAIMA 2022

作者： Yang, Rui Ke, Hualin Gan, Lin Li, Yuhong Hu, Ruihan Guangdong Institute of Intelligent Manufacturing Guangdong Key Laboratory of Modern Control Technology Guangzhou510070 China Cloud Computing Center Chinese Academy of Sciences Dongguan523808 China Guangdong Key Laboratory of Modern Control Technology Guangdong Institute of Intelligent Manufacturing Guangzhou China Engineering Research Center of Intelligence Perception and Autonomous Control Ministry of Education Beijing China Xinjiang Production and Construction Corps Key Laboratory of Modern Agricultural Machinery Shihezi University Shihezi China

Currently, new energy industries such as electric vehicles and energy storage batteries are experiencing rapid growth throughout the world. As a recognized ideal energy storage element, lithium batteries have also attracted considerable interest. To improve image contrast, the industry employs image preprocessing algorithms. Due to the high requirement of image consistency in the template matching method, which is difficult to meet in practice, and the large apparent difference between defects, it is challenging to design features. Therefore, the framework for defect detection is based on a method of deep learning with strong feature expression capability. In light of the severe imbalance in the number of samples in defect detection, data augmentation and generation methods are used to simulate real samples in order to improve the training effect of deep neural networks and alleviate the burden of data annotation to some extent. © 2022 Institute of Physics Publishing. All rights reserved.

关键词： Lithium batteries

来源：评论

学校读者我要写书评

暂无评论

How to Train Your Neural Network for Molecular Structure Generation from Mass Spectra?

How to Train Your Neural Network for Molecular Structure Gen...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Kai Zhao Yanmin Liu Longyang Dian Shiwei Sun Xuefeng Cui School of Computer Science and Technology Shandong University Qingdao China State Key Laboratory of Microbial Technology Shandong University Qingdao China Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Mass spectrometry serves as a pivotal tool for the analysis of small molecules through an examination of their mass-to-charge ratios. Recent advancements in deep learning have markedly enhanced the analysis of mass spectrometric data, facilitating the prediction of novel small molecule structures without the necessity of extensive databases. Nonetheless, the paucity of annotated datasets impedes the efficacious training of molecular generation models predicated on MS 2 spectra. To mitigate this limitation, we introduce ctMSNovelist, an avant-garde method that amalgamates pre-training, fine-tuning, and co-training techniques to construct a more precise model for the generation of molecular structures from tandem mass spectrometry data. This novel approach augments both the training regimen and the predictive accuracy of the MSNovelist model, thereby surmounting the obstacle of limited data. The methodology commences with the pretraining of a Variational Autoencoder (VAE) to generate molecular fingerprints derived from SMILES strings. Subsequently, it undergoes fine-tuning to emulate noisy fingerprints originating from mass spectrometry (MS) data. Concurrently, MSNovelist is co-trained utilizing these simulated fingerprints, inclusive of the highly noisy variants produced in the early stages of VAE training. The incorporation of a substantial volume of noisy data serves to enhance model accuracy and avert overfitting. We evaluated ctMSNovelist using the GNPS dataset and attained a SMILES prediction accuracy of 48.8%, representing a 4.1% enhancement over MSNovelist. It is pertinent to note that the sole distinction between ctMSNovelist and MSNovelist in this experiment was the training process. The code and models are publicly available at https://***/xfcui/ctMSNovelist.

关键词： Training Solid modeling Accuracy Biological system modeling Fingerprint recognition Predictive models Mass spectroscopy Data models Noise measurement Overfitting

来源：评论

学校读者我要写书评

暂无评论

Deep Representation Learning for Electron Ionization Mass Spectra Retrieval

Deep Representation Learning for Electron Ionization Mass Sp...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Shibo Liu Xuan Zhang Anlei Jiao Shiwei Sun Longyang Dian Xuefeng Cui School of Computer Science and Technology Shandong University Qingdao China Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China State Key Laboratory of Microbial Technology Shandong University Qingdao China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

The task of retrieving and analyzing mass spectra is indispensable for the identification of compounds in mass spectrometry (MS). This methodology is of critical importance as it enables researchers to correlate observed spectra with established databases, thereby precisely determining the chemical composition of samples. The primary challenges to its efficacy lie in optimizing the balance between retrieval accuracy and processing speed. Empirical studies have demonstrated that by converting mass spectra into embeddings via deep learning, it is possible to achieve both high accuracy and speed in retrieval. Nevertheless, there are complex challenges associated with employing deep learning for spectral embedding, particularly within the domain of electron ionization mass spectrometry (EI-MS). In this paper, we introduce a novel representation learning technique termed EI-MS2VEC for EI-MS retrieval. Our spectrum retrieval methodology surpasses current state-of-the-art techniques such as FastEI. For the in-silico library, we attain hit rate@1 and hit rate@10 of 43.6% and 84.5%, respectively, compared to FastEI’s 36.7% and 80.4%. Moreover, our retrieval approach operates with an order of magnitude greater speed than FastEI. The source code is available on Github (https://***/xfcui/EI-MS2VEC).

关键词： Representation learning Deep learning Accuracy Databases Source coding Ionization Predictive models Mass spectroscopy Electrons Software development management

来源：评论

学校读者我要写书评

暂无评论

Combating Online Misinformation Videos: Characterization, Detection, and Future Directions

arXiv

引用

arXiv 2023年

作者： Bu, Yuyan Sheng, Qiang Cao, Juan Qi, Peng Wang, Danding Li, Jintao Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences China Institute of Computing Technology Chinese Academy of Sciences China Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China

With information consumption via online video streaming becoming increasingly popular, misinformation video poses a new threat to the health of the online information ecosystem. Though previous studies have made much progress in detecting misinformation in text and image formats, video-based misinformation brings new and unique challenges to automatic detection systems: 1) high information heterogeneity brought by various modalities, 2) blurred distinction between misleading video manipulation and nonmalicious artistic video editing, and 3) new patterns of misinformation propagation due to the dominant role of recommendation systems on online video platforms. To facilitate research on this challenging task, we conduct this survey to present advances in misinformation video detection. We first analyze and characterize the misinformation video from three levels including signals, semantics, and intents. Based on the characterization, we systematically review existing works for detection from features of various modalities to techniques for clue integration. We also introduce existing resources including representative datasets and useful tools. Besides summarizing existing studies, we discuss related areas and outline open issues and future directions to encourage and guide more research on misinformation video detection. The corresponding repository is at https://***/ICTMCG/Awesome-Misinfo-Video-Detection. © 2023, CC BY-NC-SA.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

USV Path Planning Under Marine Environment Simulation Using DWA and Safe Reinforcement Learning 19

USV Path Planning Under Marine Environment Simulation Using ...

引用

19th IEEE International Conference on Automation Science and Engineering, CASE 2023

作者： Qu, Tianci Xiong, Gang Ali, Hub Dong, Xisong Han, Yunjun Shen, Zhen Institute of Automation Chinese Academy of Sciences The State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Institute of Automation Chinese Academy of Sciences Beijing Engineering Research Center of Intelligent Systems and Technology Beijing100190 China Chinese Academy of Sciences Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Dongguan523808 China Qingdao Academy of Intelligent Industries Qingdao266109 China

ISBN: (纸本)9798350320695

It is a challenge for USV navigation due to uncertainties and disturbances in the complex marine environment, which may lead to tilting or collision. However, current path planning methods for USVs lack dynamic environment adaptivity and timeliness. We formulate this problem as a Markov Decision Process (MDP) and combine the advantages of Dynamic Window Approach (DWA) and Safe Reinforcement Learning (RL) to solve it. First, the state encoding output by DWA is employed as observation to reduce the state dimension. Second, a safety-ensured reward function is designed to avoid collision areas. Then, the actor-critic network based on RL algorithm is used. Along with the RL training, the parameters in DWA is adaptively adjusted. Simulation experiments with dynamic waves and ocean currents demonstrate the adaptivity of our method, with avg. trajectory length decreased by 10%, avg. time cost decreased by 17%, and avg. speed increased by 18%, compared to the case using only DWA. © 2023 IEEE.

关键词： Reinforcement 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：