检索结果-内蒙古大学图书馆

Article Reranking by Memory-Enhanced key Sentence Matching for Detecting Previously Fact-Checked Claims

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Sheng, Qiang Cao, Juan Zhang, Xueyao Li, Xirong Zhong, Lei Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Key Lab of Data Engineering and Knowledge Engineering Renmin University of China China

False claims that have been previously fact-checked can still spread on social media. To mitigate their continual spread, detecting previously fact-checked claims is indispensable. Given a claim, existing works retrieve fact-checking articles (FC-articles) for detection and focus on reranking candidate articles in the typical two-stage retrieval framework. However, their performance may be limited as they ignore the following characteristics of FC-articles: (1) claims are often quoted to describe the checked events, providing lexical information besides semantics;and (2) sentence templates to introduce or debunk claims are common across articles, providing pattern information. In this paper, we propose a novel reranker, MTM (Memoryenhanced Transformers for Matching), to rank FC-articles using key sentences selected using event (lexical and semantic) and pattern information. For event information, we propose to finetune the Transformer with regression of ROUGE. For pattern information, we generate pattern vectors as a memory bank to match with the parts containing patterns. By fusing event and pattern information, we select key sentences to represent an article and then predict if the article fact-checks the given claim using the claim, key sentences, and patterns. Experiments on two real-world datasets show that MTM outperforms existing methods. Human evaluation proves that MTM can capture key sentences for explanations. The code and the dataset are at https://***/ICTMCG/MTM. © 2021, CC BY-SA.

关键词： Semantics

Image manipulation detection by multi-view multi-scale supervision

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Chen, Xinru Dong, Chengbo Ji, Jiaqi Cao, Juan Li, Xirong MoE Key Lab of Data Engineering and Knowledge Engineering Renmin University of China AIMC Lab School of Information Renmin University of China Institute of Computing Technology Chinese Academy of Sciences State Key Laboratory of Media Convergence Production Technology and Systems

The key challenge of image manipulation detection is how to learn generalizable features that are sensitive to manipulations in novel data, whilst specific to prevent false alarms on authentic images. Current research emphasizes the sensitivity, with the specificity overlooked. In this paper we address both aspects by multi-view feature learning and multi-scale supervision. By exploiting noise distribution and boundary artifact surrounding tampered regions, the former aims to learn semantic-agnostic and thus more generalizable features. The latter allows us to learn from authentic images which are nontrivial to be taken into account by current semantic segmentation network based methods. Our thoughts are realized by a new network which we term MVSS-Net. Extensive experiments on five benchmark sets justify the viability of MVSS-Net for both pixel-level and image-level manipulation detection. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantic Segmentation

Image Manipulation Detection by Multi-View Multi-Scale Supervision

学校读者我要写书评

暂无评论

Image Manipulation Detection by Multi-View Multi-Scale Super...

International Conference on Computer Vision (ICCV)

作者： Xinru Chen Chengbo Dong Jiaqi Ji Juan Cao Xirong Li MoE Key Lab of Data Engineering and Knowledge Engineering Renmin University of China AIMC Lab School of Information Renmin University of China Institute of Computing Technology Chinese Academy of Sciences State Key Laboratory of Media Convergence Production Technology and Systems

ISBN: (纸本)9781665428132

关键词： Representation learning Image segmentation Computer vision Sensitivity Costs Image edge detection Semantics

Developing Global Digital Economy after COVID-19: Preface for ITQM 2020 & 2021

学校读者我要写书评

暂无评论

Procedia Computer Science 2021年 199卷 1-9页

作者： Liu, Yubin Shi, Yong Wang, Yong Ergu, Daji Berg, Daniel Tien, James Li, Jianping Tian, Yingjie Southwest Minzu University Sichuan Chengdu610041 China College of Information Science and Technology University of Nebraska at Omaha OmahaNE68182 United States Key Lab of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China College of Engineering University of Miami Coral GablesFL33124 United States School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China

Welcome to the Eighth International Conference on Information Technology and Quantitative Management (ITQM 2020 & 2021), July 9-11, Chengdu, China. The theme of ITQM 2020 & 2021 is “Developing Global Digital Economy after COVID-19”. ITQM 2020 & 2021 is organized by International Academy of Information Technology and Quantitative Management (IAITQM), Southwest Minzu University, Chinese Academy of Sciences and University of Nebraska at Omaha. IAITQM was formally inaugurated on June 3, 2012 with more than 50 founding members from China, United States, Australia, Japan, Lithuania, Poland, Romania, Spain, Singapore, South Korea, The Netherlands, Turkey and other countries. The International Conference on Information Technology and Quantitative Management (ITQM), established by IAITQM, is a global forum for exchanging research findings and case studies that bridge the latest information technology and quantitative management techniques. It explores how the use of information technology techniques to improve quantitative management and how the development of management tools can reshape the development of information technology. The First International Conference on Information Technology and Quantitative Management (ITQM 2013) took place in Suzhou, China. The Second International Conference on Information Technology and Quantitative Management (ITQM 2014) was held in Moscow, Russia. The Third International Conference on Information Technology and Quantitative Management (ITQM 2015) was held at Rio de Janeiro, Brazil. The Forth International Conference on Information Technology and Quantitative Management (ITQM 2016) was held at Asan, Korea. The Fifth International Conference on Information Technology and Quantitative Management (ITQM 2017) was held at New Delhi, India. The Sixth International Conference on Information Technology and Quantitative Management (ITQM 2018) was hosted at Omaha, USA. The Seventh International Conference on Information Technology and Quantitative

关键词：

Generalized Face Forgery Detection via Adaptive Learning for Pre-trained Vision Transformer

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Luo, Anwei Cai, Rizhao Kong, Chenqi Ju, Yakun Kang, Xiangui Huang, Jiwu Kot, Alex C. The School of Information Technology Jiangxi University of Finance and Economics Nanchang330013 China The School of Computer Science and Engineering Sun Yat-Sen University Guangzhou510006 China Lab. School of Electrical and Electronic Engineering Nanyang Technology University Singapore The Guangdong Key Laboratory of Intelligent Information Processing National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China The China-Singapore International Joint Research Institute Singapore

With the rapid progress of generative models, the current challenge in face forgery detection is how to effectively detect realistic manipulated faces from different unseen domains. Though previous studies show that pre-trained Vision Transformer (ViT) based models can achieve some promising results after fully fine-tuning on the Deepfake dataset, their generalization performances are still unsatisfactory. One possible reason is that fully fine-tuned ViT-based models may disrupt the pre-trained features [1], [2] and overfit to some data-specific patterns [3]. To alleviate this issue, we present a Forgery-aware Adaptive Vision Transformer (FA-ViT) under the adaptive learning paradigm, where the parameters in the pre-trained ViT are kept fixed while the designed adaptive modules are optimized to capture forgery features. Specifically, a global adaptive module is designed to model long-range interactions among input tokens, which takes advantage of self-attention mechanism to mine global forgery clues. To further explore essential local forgery clues, a local adaptive module is proposed to expose local inconsistencies by enhancing the local contextual association. In addition, we introduce a fine-grained adaptive learning module that emphasizes the common compact representation of genuine faces through relationship learning in fine-grained pairs, driving these proposed adaptive modules to be aware of fine-grained forgery-aware information. Extensive experiments demonstrate that our FA-ViT achieves state-of-the-arts results in the cross-dataset evaluation, and enhances the robustness against unseen perturbations. Particularly, FA-ViT achieves 93.83% and 78.32% AUC scores on Celeb-DF and DFDC datasets in the cross-dataset evaluation. The code and trained model have been released at: https://***/LoveSiameseCat/FAViT. Copyright © 2023, The Authors. All rights reserved.

关键词： Contrastive Learning

Suicidal Ideation Cause Extraction From Social Texts

学校读者我要写书评

暂无评论

IEEE ACCESS 2020年 8卷 169333-169351页

作者： Liu, Dexi Fu, Qi Wan, Changxuan Liu, Xiping Jiang, Tengjiao Liao, Guoqiong Qiu, Xiangqing Liu, Renqiang Jiangxi Univ Finance & Econ Sch Informat Management Nanchang 330013 Jiangxi Peoples R China Jiangxi Univ Finance & Econ Jiangxi Prov Key Lab Data & Knowledge Engn Nanchang 330013 Jiangxi Peoples R China Jiangxi Sci & Technol Normal Univ Sch Commun & Elect Nanchang 330013 Jiangxi Peoples R China

Suicide has become a major public health and social concern in the world. Suicidal ideation cause extraction (SICE) in social texts can provide support for suicide prevention. This article summarizes the research on suicidal ideation causes (SICs) through the use of psychological and sociological analysis. Then, a social text-based SIC dataset is constructed and analyzed statistically for various features. A CRF model is provided along with Char-BiLSTM-CRF, which uses concatenation of word embeddings and character embeddings as word representation inputs. Then, the effects on the task are explored by the word (W), part of speech (POS), dependence relationship (DP), suicidal psychology (PCS), emotion (ET), and language (LG) features in the CRF model. The experiment shows that the word features worked best. POS and DP can be somehow covered by word features. PCS, ET and LG features can improve the effect of SICE. It also shows that Char-BiLSTM-CRF is better than CRF in general, but CRF still has advantages in terms of precision. Adding character embeddings and CRF layers can significantly improve the extraction using Char-BiLSTM-CRF. The experiment also compared three-word embeddings with Word2vec, ELMo and BERT. Compared with Word2vec, the F-value of ELMo is increased by approximately 5% on average, and compared with ELMo, the C_F and E_F of BERT are increased by 3.5% and 2.3%, respectively. Finally, the challenge of SICE is discussed based on the experimental results of Char-BiLSTM-CRF.

关键词： Silicon carbide Psychology Social network services data mining Economics Sociology Biological system modeling Suicidal ideation suicidal ideation cause extraction (SICE) social text CRF char-BiLSTM-CRF

Reading-strategy Inspired Visual Representation Learning for Text-to-Video Retrieval

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Dong, Jianfeng Wang, Yabing Chen, Xianke Qu, Xiaoye Li, Xirong He, Yuan Wang, Xun The College of Computer and Information Engineering Zhejiang Gongshang University Hangzhou310035 China The State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China The School of Electronic Information and Communications Huazhong University of Science and Technology Hubei430074 China The Key Lab of Data Engineering and Knowledge Engineering Renmin University of China The AIMC Lab. School of Information Renmin University of China Beijing100872 China The Alibaba Group Beijing100102 China

This paper aims for the task of text-to-video retrieval, where given a query in the form of a natural-language sentence, it is asked to retrieve videos which are semantically relevant to the given query, from a great number of unlabeled videos. The success of this task depends on cross-modal representation learning that projects both videos and sentences into common spaces for semantic similarity computation. In this work, we concentrate on video representation learning, an essential component for text-to-video retrieval. Inspired by the reading strategy of humans, we propose a Reading-strategy Inspired Visual Representation Learning (RIVRL) to represent videos, which consists of two branches: a previewing branch and an intensive-reading branch. The previewing branch is designed to briefly capture the overview information of videos, while the intensive-reading branch is designed to obtain more in-depth information. Moreover, the intensive-reading branch is aware of the video overview captured by the previewing branch. Such holistic information is found to be useful for the intensive-reading branch to extract more fine-grained features. Extensive experiments on three datasets are conducted, where our model RIVRL achieves a new state-of-the-art on TGIF and VATEX. Moreover, on MSR-VTT, our model using two video features shows comparable performance to the state-of-the-art using seven video features and even outperforms models pre-trained on the large-scale HowTo100M dataset. Code is available at https://***/LiJiaBei-7/rivrl. © 2022, CC BY.

关键词： Video recording

In-memory join algorithms on GPUs for large-data 21

学校读者我要写书评

暂无评论

In-memory join algorithms on GPUs for large-data

21st IEEE International Conference on High Performance Computing and Communications, 17th IEEE International Conference on Smart City and 5th IEEE International Conference on data Science and Systems, HPCC/SmartCity/DSS 2019

作者： Guo, Chengxin Chen, Hong Key Lab of Data Engineering and Knowledge Engineering of Ministry of Education School of Information Renmin University of China Beijing China

ISBN: (纸本)9781728120584

In traditional databases, join is one of the most computationally expensive operations in query processing. During the past years, GPU has been adopted to improve the performance of join processing because of the features of massive parallelism and high memory bandwidth. Limited by the capacity of GPU memory and the absence of virtual memory management, however, handling the relations that exceed the capacity of the GPU memory is a challenge for GPU-based join algorithms. Because of the high computing throughput provided by GPUs and the low bandwidth of data communication between the CPUs and the GPUs, data have to be partitioned to fit the features of GPUs and to reduce the cost of data transmission. Furthermore, a series of novel techniques have been developed on the GPUs, which can benefit the join algorithms. In this work, we focus on the optimizing of processing join operator on large relations and propose the designs of in-memory hash join and sort-merge join on GPUs. We present the data partition method on the GPUs implemented with a pipeline mechanism. Furthermore, the shuffle instructions and the CUDA streams are applied in our algorithms to best utilize the GPUs. Experimental results indicate that our hash join algorithm delivers up to 1.51X and 1.24X speedup over the state-of-the-art hash join algorithm on CPUs on NVIDIA GTX1080ti-Pascal GPU and TitanV-Volta GPU respectively. For sort-merge join, our algorithm achieves up to 3.52X and 2.21X improvements on the same GPUs respectively compared to the baselines on CPUs. © 2019 IEEE.

关键词： Graphics processing unit

Parallel hybrid join algorithm on GPU 21

学校读者我要写书评

暂无评论

Parallel hybrid join algorithm on GPU

作者： Guo, Chengxin Chen, Hong Zhang, Feng Li, Cuiping Key Lab of Data Engineering and Knowledge Engineering Ministry of Education School of Information Renmin University of China Beijing China

ISBN: (纸本)9781728120584

In data analytics applications, join is a general and time consuming operation. Optimizing join algorithms can benefit the query processing significantly. The emerging of GPUs provides a massive parallelism solution for improving the performance of the join operation. The hash join (HJ) and sort merge join (SMJ), which are two widely used join algorithms, have been proved effective for efficient join processing on the GPUs. Both algorithms have their own advantages and drawbacks, offering the chance of combining the advantages of HJ and SMJ on GPUs. In processing join operation on GPUs, data need to be transmitted between the CPU and the GPU due to the discrete GPU memory design, which causes performance degradation because of the high PCIe data transfer overhead. As GPUs are becoming more powerful than before, the performance gap between data transmission and GPU execution increases, which makes it even harder to implement an efficient join on GPUs. In this paper, we focus on the optimization of join algorithms on GPUs. We propose the Parallel Hybrid Join algorithm on GPUs(PHYJ) to combine the advantages of HJ and SMJ, and overlap the data communication and GPU execution with a pipeline mechanism. In our evaluation, the PHYJ shows up to 1.72X and 1.55X speedup over the up-to-date HJ and SMJ algorithms respectively on a NVIDIA GTX 1080ti-Pascal GPU. On the TitanV-Volta GPU, up to 1.54X and 1.42X improvements can be achieved over the baseline HJ and SMJ algorithms respectively. © 2019 IEEE.

关键词： Graphics processing unit