检索结果-内蒙古大学图书馆

EC²Detect: Real-Time Online Video Object Detection in Edge-Cloud Collaborative IoT

IEEE Internet of Things Journal 2022年第20期9卷 20382-20392页

作者： Siyan Guo Cong Zhao Guiqin Wang Jiaqing Yang Shusen Yang National Engineering Laboratory for Big Data Analytics and the School of Mathematics and Statistics Xi’an Jiaotong University Xi’an China Department of Computing Imperial College London London U.K. National Engineering Laboratory for Big Data Analytics and the School of Computer Science and Technology Xi’an Jiaotong University Xi’an China School of Mathematics and Statistics Xi’an Jiaotong University Xi’an China National Engineering Laboratory for Big Data Analytics and Ministry of Education Key Laboratory for Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an China Industrial Artificial Intelligence Center Pazhou Laboratory Guangzhou China

Video object detection is a fundamental technology of intelligent video analytics for Internet of Things (IoT) applications. However, even with extraordinary detection accuracy, predominating solutions based on deep convolutional neural networks (DCNNs) cannot achieve real-time online object detection on video streams with a low end-to-end (E2E) response latency and therefore cannot be applied to proliferating latency-sensitive IoT applications like autonomous driving requiring large-scale intelligent video analytics. To address this issue, we present EC2Detect, an edge-cloud collaborative real-time online video object detection method. Specifically, we propose a tracking-assisted object detection architecture based on edge-cloud collaboration with keyframe selection, where the accurate but heavy object detection is conducted by the Cloud on sparse keyframes adaptively selected according to their semantic variation, and the lightweight object tracking is used to localize and identify objects in other frames at edge devices. Extensive experiments of our real-world prototype demonstrate that, EC2Detect significantly outperforms state-of-the-art methods in terms of processing speed (up to $4.77\times $ faster), E2E latency (up to $8.12 \times $ lower), and edge-cloud bandwidth occupation ( $17 \times $ lower) with an acceptable mAP, which can effectively support large-scale intelligent video analytics in practice. Source code of EC2Detect is available at https://***/ECCDetect/ECCDetect .

关键词： Object detection Image edge detection Streaming media Internet of Things Collaboration Visual analytics Feature extraction

来源：评论

学校读者我要写书评

暂无评论

EFFICIENTLY PARAMETERIZED NEURAL METRIPLECTIC SYSTEMS

arXiv

引用

arXiv 2024年

作者： Gruber, Anthony Lee, Kookjin Lim, Haksoo Park, Noseong Trask, Nathaniel Center for Computing Research Sandia National Laboratories AlbuquerqueNM United States School of Computing and Augmented Intelligence Arizona State University TempeAZ United States Big Data Analytics Laboratory Yonsei University Seoul Korea Republic of Big Data Analytics Laboratory Korea Advanced Institute of Science and Technology Daejeon Korea Republic of School of Engineering and Applied Science University of Pennsylvania PhiladelphiaPA United States

Metriplectic systems are learned from data in a way that scales quadratically in both the size of the state and the rank of the metriplectic data. Besides being provably energy conserving and entropy stable, the proposed approach comes with approximation results demonstrating its ability to accurately learn metriplectic dynamics from data as well as an error estimate indicating its potential for generalization to unseen timescales when approximation error is low. Examples are provided which illustrate performance in the presence of both full state information as well as when entropic variables are unknown, confirming that the proposed approach exhibits superior accuracy and scalability without compromising on model expressivity. Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond

arXiv

引用

arXiv 2023年

作者： Xu, Fangzhi Lin, Qika Han, Jiawei Zhao, Tianzhe Liu, Jun Cambria, Erik The School of Computer Science and Technology Xi’an Jiao-tong University Shaanxi Xi’an710049 China The Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering National Engineering Lab for Big Data Analytics Shaanxi Xi’an710049 China The School of Computer Science and Engineering Nanyang Technological University Singapore

Logical reasoning consistently plays a fundamental and significant role in the domains of knowledge engineering and artificial intelligence. Recently, Large Language Models (LLMs) have emerged as a noteworthy innovation in natural language processing (NLP). However, the question of whether LLMs can effectively address the task of logical reasoning, which requires gradual cognitive inference similar to human intelligence, remains unanswered. To this end, we aim to bridge this gap and provide comprehensive evaluations in this paper. Firstly, to offer systematic evaluations, we select fifteen typical logical reasoning datasets and organize them into deductive, inductive, abductive and mixed-form reasoning settings. Considering the comprehensiveness of evaluations, we include 3 early-era representative LLMs and 4 trending LLMs. Secondly, different from previous evaluations relying only on simple metrics (e.g., accuracy), we propose fine-level evaluations in objective and subjective manners, covering both answers and explanations, including answer correctness, explain correctness, explain completeness and explain redundancy. Additionally, to uncover the logical flaws of LLMs, problematic cases will be attributed to five error types from two dimensions, i.e., evidence selection process and reasoning process. Thirdly, to avoid the influences of knowledge bias and concentrate purely on benchmarking the logical reasoning capability of LLMs, we propose a new dataset with neutral content. Based on the in-depth evaluations, this paper finally forms a general evaluation scheme of logical reasoning capability from six dimensions (i.e., Correct, Rigorous, Self-aware, Active, Oriented and No hallucination). It reflects the pros and cons of LLMs and gives guiding directions for future works. © 2023, CC BY.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Generative Model-based Feature Knowledge Distillation for Action Recognition

arXiv

引用

arXiv 2023年

作者： Wang, Guiqin Zhao, Peng Shi, Yanjiang Zhao, Cong Yang, Shusen School of Computer Science and Technology Xi’an Jiaotong University China School of Mathematics and Statistics Xi’an Jiaotong University China National Engineering Laboratory for Big Data Analytics Xi’an Jiaotong University China

Knowledge distillation (KD), a technique widely employed in computer vision, has emerged as a de facto standard for improving the performance of small neural networks. However, prevailing KD-based approaches in video tasks primarily focus on designing loss functions and fusing cross-modal information. This overlooks the spatial-temporal feature semantics, resulting in limited advancements in model compression. Addressing this gap, our paper introduces an innovative knowledge distillation framework, with the generative model for training a lightweight student model. In particular, the framework is organized into two steps: the initial phase is Feature Representation, wherein a generative model-based attention module is trained to represent feature semantics;Subsequently, the Generative-based Feature Distillation phase encompasses both Generative Distillation and Attention Distillation, with the objective of transferring attention-based feature semantics with the generative model. The efficacy of our approach is demonstrated through comprehensive experiments on diverse popular datasets, proving considerable enhancements in video action recognition task. Moreover, the effectiveness of our proposed framework is validated in the context of more intricate video action detection task. Our code is available at https://***/aaai24/Generative-based-KD. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Joint Energy and Frequency Regulation Market Clearing Considering Wind Power Uncertainty

Joint Energy and Frequency Regulation Market Clearing Consid...

引用

IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia)

作者： Yemin Wu Jiyao Wang Chenyu Peng Chunyu Chen Xuemei Dai Jianxiao Wang School of Electrical Engineering China University of Mining and Technology Xuzhou China School of Electrical Engineering Shanghai Electric Power University Shanghai China National Engineering Laboratory of Big Data Analytics and Applied Technologies Peking University Beijing China

Efficient integration of renewable power such as wind energy in electricity markets is among the highest priorities. However, the deterministic market designs may not effectively adapt to the uncertainty of renewable power. In this paper, we investigate a joint energy and frequency regulation market clearing considering wind power uncertainty. By introducing the chance-constrained market design, we propose a joint market-clearing strategy for both conventionally deterministic units and uncertain wind farms. By the simulation based on real market data, we show that as the confidence level increases, system stability improves, but this comes at the expense of increased wind abandonment losses and higher operating costs in the market. Simultaneously, a higher penetration of wind power leads to lower market operating costs and energy shadow prices.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transfer and Alignment Network for Generalized Category Discovery

arXiv

引用

arXiv 2023年

作者： An, Wenbin Tian, Feng Shi, Wenkai Chen, Yan Wu, Yaqiang Wang, Qianying Chen, Ping School of Automation Science and Engineering Xi’an Jiaotong University China School of Computer Science and Technology Xi’an Jiaotong University China National Engineering Laboratory for Big Data Analytics China Lenovo Research China Department of Engineering University of Massachusetts Boston United States

Generalized Category Discovery (GCD) is a crucial real-world task that aims to recognize both known and novel categories from an unlabeled dataset by leveraging another labeled dataset with only known categories. Despite the improved performance on known categories, current methods perform poorly on novel categories. We attribute the poor performance to two reasons: biased knowledge transfer between labeled and unlabeled data and noisy representation learning on the unlabeled data. The former leads to unreliable estimation of learning targets for novel categories and the latter hinders models from learning discriminative features. To mitigate these two issues, we propose a Transfer and Alignment Network (TAN), which incorporates two knowledge transfer mechanisms to calibrate the biased knowledge and two feature alignment mechanisms to learn discriminative features. Specifically, we model different categories with prototypes and transfer the prototypes in labeled data to correct model bias towards known categories. On the one hand, we pull instances with known categories in unlabeled data closer to these prototypes to form more compact clusters and avoid boundary overlap between known and novel categories. On the other hand, we use these prototypes to calibrate noisy prototypes estimated from unlabeled data based on category similarities, which allows for more accurate estimation of prototypes for novel categories that can be used as reliable learning targets later. After knowledge transfer, we further propose two feature alignment mechanisms to acquire both instance- and category-level knowledge from unlabeled data by aligning instance features with both augmented features and the calibrated prototypes, which can boost model performance on both known and novel categories with less noise. Experiments on three benchmark datasets show that our model outperforms SOTA methods, especially on novel categories. Theoretical analysis is provided for an in-depth understanding

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Weakly-Supervised Action Localization by Hierarchically-structured Latent Attention Modeling

Weakly-Supervised Action Localization by Hierarchically-stru...

引用

International Conference on Computer Vision (ICCV)

作者： Guiqin Wang Peng Zhao Cong Zhao Shusen Yang Jie Cheng Luziwei Leng Jianxing Liao Qinghai Guo School of Computer Science and Technology Xi’an Jiao Tong University School of Mathematics and Statistics Xi’an Jiao Tong University National Engineering Laboratory for Big Data Analytics Xi’an Jiao Tong University ACS Lab Huawei Technologies

Weakly-supervised action localization aims to recognize and localize action instancese in untrimmed videos with only video-level labels. Most existing models rely on multiple instance learning(MIL), where the predictions of unlabeled instances are supervised by classifying labeled bags. The MIL-based methods are relatively well studied with cogent performance achieved on classification but not on localization. Generally, they locate temporal regions by the video-level classification but overlook the temporal variations of feature semantics. To address this problem, we propose a novel attention-based hierarchically-structured latent model to learn the temporal variations of feature semantics. Specifically, our model entails two components, the first is an unsupervised change-points detection module that detects change-points by learning the latent representations of video features in a temporal hierarchy based on their rates of change, and the second is an attention-based classification model that selects the change-points of the foreground as the boundaries. To evaluate the effectiveness of our model, we conduct extensive experiments on two benchmark datasets, THUMOS-14 and ActivityNet-v1.3. The experiments show that our method outperforms current state-of-the-art methods, and even achieves comparable performance with fully-supervised methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mind Reasoning Manners: Enhancing Type Perception for Generalized Zero-shot Logical Reasoning over Text

arXiv

引用

arXiv 2023年

作者： Xu, Fangzhi Liu, Jun Lin, Qika Zhao, Tianzhe Zhang, Jian Zhang, Lingling School of Computer Science and Technology Xi’an Jiaotong University Xi’an China Shaanxi Province Key Laboratory of Satellite and Terrestrial Network Tech. R&D National Engineering lab for Big Data Analytics Xi’an China

Logical reasoning task involves diverse types of complex reasoning over text, based on the form of multiple-choice question answering. Given the context, question and a set of options as the input, previous methods achieve superior performances on the full-data setting. However, the current benchmark dataset has the ideal assumption that the reasoning type distribution on the train split is close to the test split, which is inconsistent with many real application scenarios. To address it, there remain two problems to be studied: (1) How is the zero-shot capability of the models (train on seen types and test on unseen types)? (2) How to enhance the perception of reasoning types for the models? For problem 1, we propose a new benchmark for generalized zero-shot logical reasoning, named ZsLR. It includes six splits based on the three type sampling strategies. For problem 2, a type-aware model TaCo is proposed. It utilizes both the heuristic input reconstruction and the contrastive learning to improve the type perception in the global representation. Extensive experiments on both the zero-shot and full-data settings prove the superiority of TaCo over the state-of-the-art methods. Also, we experiment and verify the generalization capability of TaCo on other logical reasoning dataset. © 2023, CC BY.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Logic-Aware Knowledge Graph Reasoning for Structural Sparsity under Large Language Model Supervision 25

Logic-Aware Knowledge Graph Reasoning for Structural Sparsit...

引用

34th ACM Web Conference, WWW 2025

作者： Pan, Yudai Hong, Jiajie Zhao, Tianzhe Song, Lingyun Liu, Jun Shang, Xuequn School of Computer Science Northwest Polytechnical University Shaanxi Xi’an China Key Laboratory of Big Data Storage and Management Northwestern Polytechnical University Shaanxi Xi’an China School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an China Research & Development Institute of Northwestern Polytechnical University in Shenzhen Shenzhen China National Engineering Lab for Big Data Analytics Xi’an Jiaotong University Shaanxi Xi’an China

ISBN: (纸本)9798400712746

Knowledge Graph (KG) reasoning aims to predict missing entities in incomplete triples, which requires adequate structural information to derive accurate embeddings. However, KGs in the real world are not as dense as the idealized benchmarks, where sparse graph structures restrict the comprehensive structural information for superior performance. Although the logical semantics in KGs shows its potential in alleviating the impact of structural sparsity, there still exist some challenges. The deficient supervision and the semantic gap of logic make it difficult to introduce logical semantics in sparse KG reasoning. To this end, we propose a novel KG reasoning approach LoLLM injecting logic with the supervised information supplied by the Large Language Model (LLM), which is proved to be effective in evaluating and scoring. Firstly, LoLLM derives structural embeddings employing a graph convolutional network (GCN) with relation-aware and triple-aware attention. LoLLM secondly constructs reasoning paths instantiated from the first-order logic rules extracted from sparse KGs, and injects the logical semantics by a designed LLM-enhanced tuning strategy. We propose a textual loss (TL) and a logical loss (LL) in the optimization and obtain logical tuning embeddings of KG in this process. Finally, LoLLM fuses structural embeddings from the GCN and logical tuning embeddings from the LLM-enhanced tuning for scoring and incomplete triple prediction. Extensive experiments on two sparse KGs and a benchmark show that LoLLM outperforms state-of-the-art structure-based and Language Model (LM)-augmented baselines. Moreover, the logic rules with corresponding confidences provide explicit explanations as an interpretable paradigm. © 2025 Copyright held by the owner/author(s).

关键词： Structural analysis

来源：评论

学校读者我要写书评

暂无评论

Weakly-Supervised Action Localization by Hierarchically-structured Latent Attention Modeling

arXiv

引用

arXiv 2023年

作者： Wang, Guiqin Zhao, Peng Zhao, Cong Yang, Shusen Cheng, Jie Leng, Luziwei Liao, Jianxing Guo, Qinghai School of Computer Science and Technology Xi’an Jiaotong University China ACS Lab Huawei Technologies China School of Mathematics and Statistics Xi’an Jiaotong University China National Engineering Laboratory for Big Data Analytics Xi’an Jiaotong University China

Weakly-supervised action localization aims to recognize and localize action instancese in untrimmed videos with only video-level labels. Most existing models rely on multiple instance learning(MIL), where the predictions of unlabeled instances are supervised by classifying labeled bags. The MIL-based methods are relatively well studied with cogent performance achieved on classification but not on localization. Generally, they locate temporal regions by the video-level classification but overlook the temporal variations of feature semantics. To address this problem, we propose a novel attention-based hierarchically-structured latent model to learn the temporal variations of feature semantics. Specifically, our model entails two components, the first is an unsupervised change-points detection module that detects change-points by learning the latent representations of video features in a temporal hierarchy based on their rates of change, and the second is an attention-based classification model that selects the change-points of the foreground as the boundaries. To evaluate the effectiveness of our model, we conduct extensive experiments on two benchmark datasets, THUMOS-14 and ActivityNetv1.3. The experiments show that our method outperforms current state-of-the-art methods, and even achieves comparable performance with fully-supervised methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

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：