检索结果-内蒙古大学图书馆

Embedding VLAD in Transformer for Video Question Answering

学校读者我要写书评

暂无评论

Jisuanji Xuebao/Chinese Journal of Computers 2023年第4期46卷 671-689页

作者： Guo, Dan Yao, Shen-Tao Wang, Hui Wang, Meng School of Computer and Information Engineering Hefei University of Technology Hefei230601 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230094 China Key Laboratory of Knowledge Engineering with Big Data（Hefei University of Technology） Ministry of Education Hefei230601 China Intelligent Interconnected Systems Laboratory of Anhui Province（Hefei University of Technology） Hefei230601 China

Video question answering（VideoQA）is a typical cross-modal understanding task. Its challenge lies in how to learn appropriate multimodal representation and cross-modal correlation for answer inference. Most existing video question answering methods focus on the latter，e. g.，relationship learning between each video frame or clip and word. In this work， we devote to advanced feature embedding of both video and query. We develop a clustering-based VLAD technique for VideoQA. The novelty of our work is the joint exploitation of temporal aggregation and correlation in multimodality. We propose an end-to-end trainable Transformed VLAD embedding network， named TVLAD-Net. TVLAD-Net constructs a differentiable aggregation network module（i. e.， convolutional Residual-less VLAD Block）to generate compact VLAD descriptors（transforming N frames，clips or words to compact K descriptors while K © 2023 Science Press. All rights reserved.

关键词： Semantics

UAV-assisted Joint Mobile Edge Computing and data Collection via Matching-enabled Deep Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Boxiong Kang, Hui Li, Jiahui Sun, Geng Sun, Zemin Wang, Jiacheng Niyato, Dusit College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China College of Computing and Data Science Nanyang Technological University 639798 Singapore College of Computing and Data Science Nanyang Technological University Singapore

Unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) and data collection (DC) have been popular research issues. Different from existing works that consider MEC and DC scenarios separately, this paper investigates a multi-UAV-assisted joint MEC-DC system. Specifically, we formulate a joint optimization problem to minimize the MEC latency and maximize the collected data volume. This problem can be classified as a non-convex mixed integer programming problem that exhibits long-term optimization and dynamics. Thus, we propose a deep reinforcement learning-based approach that jointly optimizes the UAV movement, user transmit power, and user association in real time to solve the problem efficiently. Specifically, we reformulate the optimization problem into an action space-reduced Markov decision process (MDP) and optimize the user association by using a two-phase matching-based association (TMA) strategy. Subsequently, we propose a soft actor-critic (SAC)-based approach that integrates the proposed TMA strategy (SAC-TMA) to solve the formulated joint optimization problem collaboratively. Simulation results demonstrate that the proposed SAC-TMA is able to coordinate the two subsystems and can effectively reduce the system latency and improve the data collection volume compared with other benchmark algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

Scene-Adaptive Person Search via Bilateral Modulations

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jiang, Yimin Wang, Huibing Peng, Jinjia Fu, Xianping Wang, Yang School of Information Science and Technology Dalian Maritime University Dalian China School of Cyber Security and Computer Hebei University Baoding China Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology Hefei China

Person search aims to localize specific a target person from a gallery set of images with various scenes. As the scene of moving pedestrian changes, the captured person image inevitably bring in lots of background noise and foreground noise on the person feature, which are completely unrelated to the person identity, leading to severe performance degeneration. To address this issue, we present a Scene-Adaptive Person Search (SEAS) model by introducing bilateral modulations to simultaneously eliminate scene noise and maintain a consistent person representation to adapt to various scenes. In SEAS, a Background Modulation Network (BMN) is designed to encode the feature extracted from the detected bounding box into a multi-granularity embedding, which reduces the input of background noise from multiple levels with norm-aware. Additionally, to mitigate the effect of foreground noise on the person feature, SEAS introduces a Foreground Modulation Network (FMN) to compute the clutter reduction offset for the person embedding based on the feature map of the scene image. By bilateral modulations on both background and foreground within an end-to-end manner, SEAS obtains consistent feature representations without scene noise. SEAS can achieve state-of-the-art (SOTA) performance on two benchmark datasets, CUHK-SYSU with 97.1% mAP and PRW with 60.5% mAP. The code is available at https://***/whbdmu/SEAS. © 2024, CC0.

关键词： Embeddings

LSBert: Lexical Simplification Based on BERT

学校读者我要写书评

暂无评论

IEEE/ACM Transactions on Audio Speech and Language Processing 2021年 29卷 3064-3076页

作者： Qiang, Jipeng Li, Yun Zhu, Yi Yuan, Yunhao Shi, Yang Wu, Xindong Department of Computer Science Jiangsu Yangzhou China Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Ministry of Education Anhui Hefei China Mininglamp Academy of Sciences Minininglamp Beijing 100864 China

Lexical simplification (LS) aims at replacing complex words with simpler alternatives. LS commonly consists of three main steps: complex word identification, substitute generation, and substitute ranking. Existing LS methods focus on the contextual information of the complex word in the last step (substitute ranking). However, they miss out the following two facts: (1) The word complexity of a polysemous word is very closely related to its context;(2) The step of substitute generation regardless of the context will inevitably produce a large number of spurious candidates. Therefore, we propose a novel LS system LSBert based on pretrained language model BERT to address the aforementioned issues, which is capable of making use of the wider context when both identifying the words in need of simplification and generating substitute candidates for the complex words. Specifically, LSBert consists of a network for complex word identification by fine-tuning BERT and a network for substitute generation based on BERT. Experimental results show that LSBert performs well in both complex word identification and substitute generation, achieving state-of-the-art results in three benchmarks. © 2014 IEEE.

关键词： BERT Complex word identification Lexical simplification Sentence simplification

High-Quality Noise Detection for knowledge Graph Embedding with Rule-Based Triple Confidence 18th

学校读者我要写书评

暂无评论

High-Quality Noise Detection for Knowledge Graph Embedding w...

18th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2021

作者： Hong, Yan Bu, Chenyang Wu, Xindong Ministry of Education Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei China Mininglamp Academy of Sciences Mininglamp Technology Beijing China

ISBN: (纸本)9783030891879

knowledge representation learning is usually used in knowledge reasoning and other related fields. Its goal is to use low-dimensional vectors to represent the entities and relations in a knowledge graph. In the process of automatic knowledge graph construction, the complexity of unstructured text and the incorrect text may make automatic construction tools unable to accurately obtain the semantic information in the text. This leads to high-quality noise with matched entity types but semantic errors. Currently knowledge representation learning methods assume that the knowledge in knowledge graphs is completely correct, and ignore the noise data generated in the process of automatic construction of knowledge graphs, resulting in errors in the vector representation of entities and relations. In order to reduce the negative impact of noise data on the construction of a representation learning model, in this study, a high-quality noise detection method with rule information is proposed. Based on the semantic association between triples in the same rule, we propose the concept of rule-based triple confidence. The calculation strategy of triple confidence is designed inspired by probabilistic soft logic (PSL). The influence of high-quality noise data in the training process of the model can be weakened by this confidence. Experiments show the effectiveness of the proposed method in dealing with high-quality noise. © 2021, Springer Nature Switzerland AG.

关键词： knowledge graph

HVIS: A Human-like Vision and Inference System for Human Motion Prediction

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Lyu, Kedi Chen, Haipeng Liu, Zhenguang Yin, Yifang Lin, Yukang Jiao, Yingying College of Computer Science and Technology Jilin University Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun China The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Institute of Blockchain and Data Security Hangzhou China A*STAR Singapore Tsinghua Shenzhen International Graduate School Nanshan District Shenzhen China

Grasping the intricacies of human motion, which involve perceiving spatio-temporal dependence and multi-scale effects, is essential for predicting human motion. While humans inherently possess the requisite skills to navigate this issue, it proves to be markedly more challenging for machines to emulate. To bridge the gap, we propose the Human-like Vision and Inference System (HVIS) for human motion prediction, which is designed to emulate human observation and forecast future movements. HVIS comprises two components: the human-like vision encode (HVE) module and the human-like motion inference (HMI) module. The HVE module mimics and refines the human visual process, incorporating a retina-analog component that captures spatiotemporal information separately to avoid unnecessary crosstalk. Additionally, a visual cortex-analogy component is designed to hierarchically extract and treat complex motion features, focusing on both global and local features of human poses. The HMI is employed to simulate the multi-stage learning model of the human brain. The spontaneous learning network simulates the neuronal fracture generation process for the adversarial generation of future motions. Subsequently, the deliberate learning network is optimized for hard-to-train joints to prevent misleading learning. Experimental results demonstrate that our method achieves new state-of-the-art performance, significantly outperforming existing methods by 19.8% on Human3.6M, 15.7% on CMU Mocap, and 11.1% on G3D. © 2025, CC BY.

关键词： Motion estimation

Size-Invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection 41

学校读者我要写书评

暂无评论

Size-Invariance Matters: Rethinking Metrics and Losses for I...

41st International Conference on Machine Learning, ICML 2024

作者： Li, Feiran Xu, Qianqian Bao, Shilong Yang, Zhiyong Cong, Runmin Cao, Xiaochun Huang, Qingming Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD. Copyright 2024 by the author(s)

关键词： Object detection

Optimizing Human Pose Estimation Through Focused Human and Joint Regions

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Jiao, Yingying Wang, Zhigang Liu, Zhenguang Fan, Shaojing Wu, Sifan Wu, Zheqi Xu, Zhuoyue College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China College of Computer Science and Technology Zhejiang Gongshang University China The State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China School of Computing National University of Singapore Singapore

Human pose estimation has given rise to a broad spectrum of novel and compelling applications, including action recognition, sports analysis, as well as surveillance. However, accurate video pose estimation remains an open challenge. One aspect that has been overlooked so far is that existing methods learn motion clues from all pixels rather than focusing on the target human body, making them easily misled and disrupted by unimportant information such as background changes or movements of other people. Additionally, while the current Transformer-based pose estimation methods has demonstrated impressive performance with global modeling, they struggle with local context perception and precise positional identification. In this paper, we try to tackle these challenges from three aspects: (1) We propose a bilayer Human-keypoint Mask module that performs coarse-to-fine visual token refinement, which gradually zooms in on the target human body and keypoints while masking out unimportant figure regions. (2) We further introduce a novel deformable cross attention mechanism and a bidirectional separation strategy to adaptively aggregate spatial and temporal motion clues from constrained surrounding contexts. (3) We mathematically formulate the deformable cross attention, constraining that the model focuses solely on the regions centered at the target person body. Empirically, our method achieves state-of-the-art performance on three large-scale benchmark datasets. A remarkable highlight is that our method achieves an 84.8 mean Average Precision (mAP) on the challenging wrist joint, which significantly outperforms the 81.5 mAP achieved by the current state-of-the-art method on the PoseTrack2017 dataset. Copyright © 2025, The Authors. All rights reserved.

关键词： Benchmarking

A Deletable and Modifiable Blockchain Scheme Based on Record Verification Trees and the Multisignature Mechanism

学校读者我要写书评

暂无评论

Computer Modeling in engineering & Sciences 2021年第7期128卷 223-245页

作者： Daojun Han Jinyu Chen Lei Zhang Yatian Shen Yihua Gao Xueheng Wang Henan Key Laboratory of Big Data Analysis and Processing Henan UniversityKaifeng47500China Institute of Data and Knowledge Engineering Henan UniversityKaifeng47500China School of Computer and Information Engineering Henan UniversityKaifeng47500China Department of Network and Finance Agricultural Bank of China Limited Xuchang BranchXuchang461000China School of Software Pingdingshan UniversityPingdingshan467000China Department of Network and Finance Agricultural Bank of China Limited Nanyang BranchNanyang473000China

As one of the most valuable technologies,blockchains have received extensive attention from researchers and industry circles and are widely applied in various ***,data on a blockchain cannot be *** a result,it is impossible to clean invalid and sensitive data and correct erroneous ***,to a certain extent,hinders the application of blockchains in supply chains and Internet of *** address this problem,this study presents a deletable and modifiable blockchain scheme(DMBlockChain)based on record verification trees(RVTrees)and the multisignature scheme.(1)In this scheme,an RVTree structure is designed and added to the block *** RVTree can not only ensure that a record is true and valid but,owing to its unique binary structure,also verify whether modification and deletion requests are valid.(2)In DMBlockChain,the multisignature mechanism is also *** mechanism requires the stakeholders’signatures for each modification or deletion request and thus ensures that a record will not be modified arbitrarily.A user’s request is deemed valid only if it is dually verified by the RVTree and the multisignature *** analysis finds that DMBlockChain can provide a secure and valid means for modifying and deleting records in a block while ensuring the integrity of the block and that DMBlockChain can effectively save space in some scenarios that require frequent records modification.

关键词： Blockchain record verification trees multisignature DMBlockChain