检索结果-内蒙古大学图书馆

32nd ACM International Conference on Multimedia, MM 2024

作者： Li, Yudong Hou, Xianxu Dezhi, Zheng Shen, Linlin Zhao, Zhe School of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of AI and Advanced Computing Xi'an Jiaotong-Liverpool University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Tencent AI Lab Beijing China

ISBN: (纸本)9798400706868

While significant progress has been made in multi-modal learning driven by large-scale image-text datasets, there is still a noticeable gap in the availability of such datasets within the facial domain. To facilitate and advance the field of facial representation learning, we present FLIP-80M, a large-scale visual-linguistic dataset comprising over 80 million face images paired with text descriptions. FLIP-80M is constructed by leveraging the large openly available image-text-pair dataset LAION-5B and a mixed-method approach to filter face-related pairs from both visual and linguistic perspectives. Our curation process involves face detection, face caption classification, text de-noising, and synthesis-based image augmentation. As a result, FLIP-80M stands as the largest face-text dataset to date. To evaluate the potential of our dataset, we fine-tune the CLIP model using the proposed FLIP-80M, to create FLIP (Facial Language-Image Pretraining) and assess its representation capabilities across various downstream tasks. Our experiments demonstrate that our FLIP model achieves state-of-the-art results in a range of face analysis tasks, including face parsing, face alignment, and face attribute classification. The dataset and models are available at https://***/ydli-ai/FLIP. © 2024 ACM.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Forest-based translation rule extraction

Forest-based translation rule extraction

引用

2008 Conference on Empirical Methods in Natural Language processing, EMNLP 2008, Co-located with AMTA 2008 and the International Workshop on Spoken Language Translation

作者： Mi, Haitao Huang, Liang Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing 100190 China Dept. of Computer and Information Science University of Pennsylvania Levine Hall 3330 Walnut St. Philadelphia PA 19104 United States

Translation rule extraction is a fundamental problem in machine translation, especially for linguistically syntax-based systems that need parse trees from either or both sides of the bitext. The current dominant practice only uses 1-best trees, which adversely affects the rule set quality due to parsing errors. So we propose a novel approach which extracts rules from a packed forest that compactly encodes exponentially many parses. Experiments show that this method improves translation quality by over 1 BLEU point on a state-of-the-art tree-to-string system, and is 0.5 points better than (and twice as fast as) extracting on 30- best parses. When combined with our previous work on forest-based decoding, it achieves a 2.5 BLEU points improvement over the baseline, and even outperforms the hierarchical system of Hiero by 0.7 points. © 2008 Association for Computational Linguistics.

关键词： Hierarchical systems

来源：评论

学校读者我要写书评

暂无评论

A generic approach to classify sports video shots and its application in event detection 09

A generic approach to classify sports video shots and its ap...

引用

1st International Conference on Internet Multimedia computing and Service, ICIMCS 2009

作者： Li, Lingfang Duan, Ling-Yu Huang, Qingming Du, Jun Gao, Wen Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Institute of Digital Media Peking University Beijing 100871 China Graduate University of Chinese Academy of Sciences Beijing 100190 China NEC Research Labs. China Beijing 100084 China

ISBN: (纸本)9781605588407

Shot type is useful information for semantic sports video analysis. Most existing approaches utilize predefined rules and domain knowledge to derive shot types in sports video. Although these methods have achieved promising results in some specific games, it is hard to extend them from one sport to another. To address this problem, we propose a generic approach to classify shots in sports video. Our approach utilizes bag of visual words model to represent key frame for each shot based on Scale Invariant Feature Transform (SIFT) feature points;either Support Vector Machine (SVM) or Probabilistic Latent Semantic Analysis (PLSA) are then employed to classify key frame to determine shot type. As our approach relies little on domain knowledge, it can be more easily extended to different sports. We have evaluated our shot classification approach over five types of sports video and have achieved promising results. To show the usefulness and effectiveness of our shot classification, we apply the results of shot type to detect events in basketball video via a generative-discriminative model. In addition, we have observed that some common visual parts frequently appear across various shots in the same sport or even different but relevant sports. For instance, soccer and basketball are relevant sports in the sense of field-ball game. Motivated by this observation, we attempt to alleviate the problem of insufficient sports video data in some applications by sharing these visual parts across different but relevant kinds of sports. Copyright 2009 ACM.

关键词： Sports

来源：评论

学校读者我要写书评

暂无评论

EPiK-a Workflow for Electron Tomography in Kepler

引用

Procedia computer science 2014年 20卷 2295-2305页

作者： Ruijuan Chen Xiaohua Wan Ilkay Altintas Jianwu Wang Daniel Crawl Sébastien Phan Albert Lawrence Mark Ellisman National Center for Microscopy and Imaging Research University of California San Diego La Jolla CA USA. Key Lab of Intelligent Information Processing and Advanced Computing Research Lab Institute of Computing Technology Chinese Academy of Sciences Beijing China. San Diego Supercomputer Center University of California San Diego La Jolla CA USA.

Scientific workflows integrate data and computing interfaces as configurable, semi-automatic graphs to solve a scientific problem. Kepler is such a software system for designing, executing, reusing, evolving, archiving and sharing scientific workflows. Electron tomography (ET) enables high-resolution views of complex cellular structures, such as cytoskeletons, organelles, viruses and chromosomes. Imaging investigations produce large datasets. For instance, in Electron Tomography, the size of a 16 fold image tilt series is about 65 Gigabytes with each projection image including 4096 by 4096 pixels. When we use serial sections or montage technique for large field ET, the dataset will be even larger. For higher resolution images with multiple tilt series, the data size may be in terabyte range. Demands of mass data processing and complex algorithms require the integration of diverse codes into flexible software structures. This paper describes a workflow for Electron Tomography Programs in Kepler (EPiK). This EPiK workflow embeds the tracking process of IMOD, and realizes the main algorithms including filtered backprojection (FBP) from TxBR and iterative reconstruction methods. We have tested the three dimensional (3D) reconstruction process using EPiK on ET data. EPiK can be a potential toolkit for biology researchers with the advantage of logical viewing, easy handling, convenient sharing and future extensibility.

关键词： EPiK Electron Tomography Kepler Scientific workflows TxBR

来源：评论

学校读者我要写书评

暂无评论

Human reappearance detection based on on-line learning

Human reappearance detection based on on-line learning

引用

作者： Hu, Lei Wang, Yizhou Jiang, Shuqiang Huang, Qingming Gao, Wen Key Lab of Intelligent Information Processing Chinese Academy of Sciences Beijing 100080 China Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 China Graduate University Chinese Academy of Sciences Beijing 100049 China Institute of Digital Media Peking University Beijing 100871 China Key Lab of Machine Perception Peking University MOE China

ISBN: (纸本)9781424421756

Many video surveillance applications require detecting human reappearances in a scene monitored by a camera or over a network of cameras. This is the human reappearance detection (HRD) problem. Studying this problem is important for analyzing a surveillance scenario at semantic level. In this paper, we propose a novel online learning frameworkfor solving HRD problem. Both generative model and discriminative model are employed in this framework and a voting scheme is presented to fuse the decisions ofboth models for determining whether a just entered person is one of those who have shown up, i.e. whether a reappearance happens. Both models will be updated based on mistake-driven online learning strategy. Our experimental results show that the adopted online learning framework not only improves the reappearance detection accuracy but also achieves high robustness in various surveillance scenes. © 2008 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Exploring heterogeneous semantic data for topic-specific crawling and search

International Journal of Digital Content Technology and its ...

引用

International Journal of Digital Content Technology and its Applications 2011年第7期5卷 335-349页

作者： Yang, Kun Huang, Rui Lin, Fen Shi, Zhongzhi Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences 100190 Beijing China National Institute of Metrology 100013 Beijing China

This paper explores heterogeneous semantic data in Web 1.0, Semantic Web and Web 2.0 for topicspecific crawling and search. A statistical Semantic Association Model (SAM) is proposed to support semantic interoperability among four different models of thesauruses, categories, ontologies, and folksonomies. Based on this model, a focused crawling and semantic search framework is developed. In focused crawling of potentially related textual and semantic data, URLs are ordered before crawling and irrelevant Web pages are filtered out after crawling according to SAM-based semantic relevance ranking. In order that the retrieved results are more semantically related to the user queries, approaches of SAM-based semantic query expansion and meta-search result aggregation are designed. Experiments show that the proposed model and framework effectively integrates both keyword data and heterogeneous semantic data for topic-specific crawling and search.

关键词： Semantic Web

来源：评论

学校读者我要写书评

暂无评论

PKU at ImageCLEF 2008: Experiments with query extension techniques for text-based and content-based image retrieval

PKU at ImageCLEF 2008: Experiments with query extension tech...

引用

2008 Working Notes for CLEF Workshop, CLEF 2008 - Co-located with the 12th European Conference on Digital Libraries, ECDL 2008

作者： Zhou, Zhi Tian, Yonghong Li, Yuanning Liu, Ting Huang, Tiejun Gao, Wen Institute of Digital Media School of EE and CS Peking University Beijing100871 China Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Science Beijing100190 China Graduate University Chinese Academy of Sciences Beijing100080 China

In this paper, we present our solutions for the WikipediaMM task at ImageCLEF 2008. The aim of this task is to investigate effective retrieval approaches in the context of a large-scale and heterogeneous collection of Wikipedia images that are searched by textual queries (and/or sample images and/or concepts) describing a user's information need. We first experimented with a text-based image retrieval approach with query extension, where the expansion terms are automatically selected from a knowledge base that is (semi-)automatically constructed from Wikipedia. We show how this open, constantly evolving encyclopedia can yield inexpensive knowledge structures that are specifically tailored to effectively enhance the semantics of queries. Encouragingly, the experimental results rank in the first place among all submitted runs. The second approach we experimented with is content-based image retrieval (CBIR), in which we first train 1-vs-all classifiers for all query concepts by using the training images obtained by Yahoo! search, and then treat the retrieval task as visual concept detection in the given Wikipedia image set. By comparison, this approach performs better than other submitted CBIR runs. Finally, we experimented with a cross-media image retrieval approach by combining and re-ranking text-based and content-based retrieval results. Despite the final experimental results were not formally submitted before the deadline, this approach performs remarkably better than the text-based retrieval or CBIR approaches.

关键词： Content based retrieval

来源：评论

学校读者我要写书评

暂无评论

A new regression method based on SVM classification

A new regression method based on SVM classification

引用

2011 8th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2011, Jointly with the 2011 7th International Conference on Natural Computation, ICNC'11

作者： Dong, Yi Cheng, Wei Li, Shengfeng Institute of Applied Mathematics Bengbu College Bengbu China School of Management Hefei Univ. of Technology Hefei China Key Lab. of Intelligent Computing and Signal Processing Anhui University Hefei China Anhui Vocational College of Electronics and Information Technology Bengbu China

ISBN: (纸本)9781612841816

SVM (Support Vector Machines) is a novel algorithm of machine learning which is based on SLT (Statistical Learning Theory). It can solve the problem characterized by nonlinear, high dimension, small sample and local minimizing perfectly. For non-linear problem, the forecasting technique of FCTR (First classification, then regression) was proposed, based on the classification approach of SVM and has carried on the simulation experiment. The experiment shows that the fitting value which obtains using the return to first would be more precise than directly. Using this method to food production forecast, its accuracy is superior to other production forecasting methods. © 2011 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Characterizing and Understanding Development of Social computing Through DBLP: A Data-Driven Analysis

引用

Journal of Social computing 2022年第4期3卷 287-302页

作者： Jiaqi Wu Bodian Ye Qingyuan Gong Atte Oksanen Cong Li Jingjing Qu Felicia F.Tian Xiang Li Yang Chen the Shanghai Key Lab of Intelligent Information Processing the School of Computer ScienceFudan UniversityShanghai 200438China the Faculty of Social Sciences Tampere UniversityTampere 33100Finland School of Information Science and Technology Fudan UniversityShanghai 200438China Shanghai Artificial Intelligence Laboratory Shanghai 200232China. School of Social Development and Public Policy Fudan UniversityShanghai 200433China. Institute of Complex Networks and Intelligent Systems Shanghai Research Institute for Intelligent Autonomous SystemsTongji UniversityShanghai 200092China.

During the past decades,the term“social computing”has become a promising interdisciplinary area in the intersection of computer science and social *** this work,we conduct a data-driven study to understand the development of social computing using the data collected from Digital Bibliography and Library Project(DBLP),a representative computer science bibliography *** have observed a series of trends in the development of social computing,including the evolution of the number of publications,popular keywords,top venues,international collaborations,and research *** findings will be helpful for researchers and practitioners working in relevant fields.

关键词： social computing Digital Bibliography and Library Project(DBLP) bibliometric evolution visualization

来源：评论

学校读者我要写书评

暂无评论

DISTANCE RESTRICTED TRANSFORMER ENCODER FOR MULTI-labEL CLASSIFICATION

DISTANCE RESTRICTED TRANSFORMER ENCODER FOR MULTI-LABEL CLAS...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Wang, Xiaomei Li, Yaqian Luo, Tong Guo, Yandong Fu, Yanwei Xue, Xiangyang School of Computer Science Fudan University Shanghai China OPPO Research Institute Shanghai China The School of Data Science MOE Frontiers Center for Brain Science Shanghai Key Lab of Intelligent Information Processing Fudan University Shanghai China

ISBN: (纸本)9781665438643

Multi-label image classification is a fundamental but challenging task in Multimedia *** aims to predict a set of labels presented in an image. Great progress has been made by exploring convolutional neural network with binary cross-entropy loss recently. However, conventional approaches are limited to highlight the key visual contents associated with target labels and pay little attention to confining the distances between visual and positive/negative label representations. To target these aspects, we firstly introduce a variant transformer encoder model for acquiring the underlying and crucial visual information related to ground truth labels. Specifically, a novel primal feature guided net is designed to maintain the original visual features during encoding process. Secondly, we exploit a distance restricted learning strategy in a common semantic space to shrink the distances of images with positive labels while expand with the negative ones during training stage. Extensive experiments are executed on MSCOCO and WIDER Attribute datasets and outstanding performance is achieved compared with other state-of-the-art models. © 2021 IEEE

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：