Filters








15,068 Hits in 5.3 sec

Cross-media Scientific Research Achievements Query based on Ranking Learning [article]

Benzhi Wang and Meiyu Liang and Ang Li
2022 arXiv   pre-print
In view of the above background, this paper expounds on the research status from four aspects: characteristic learning of scientific research results, cross-media research results query, ranking learning  ...  of scientific research results, and cross-media scientific research achievement query system.  ...  At present, the research on data query of cross-media scientific research results is not mature, so how to effectively learn the semantic information of cross-media scientific research results has become  ... 
arXiv:2204.12121v1 fatcat:z7aosynjdvch7jync3vddoyouq

Cross-Modal Retrieval using Random Multimodal Deep Learning

H Somasekar
2019 JOURNAL OF MECHANICS OF CONTINUA AND MATHEMATICAL SCIENCES  
This paper proposed a Random Multimodal Deep Learning (RMDL) based Recurrent Neural Network (RNN) for cross-media retrieval.  ...  Since strongly supervised strategies use the class labels that might be missing in practice, this paper mainly concentrates on weakly managed learning for cross-media recovery, in which only textimage  ...  Mean Rank for Text Query This section presents the performance of the proposed RMDL-based retrieval method on Twitter100k.  ... 
doi:10.26782/jmcms.2019.04.00016 fatcat:jkpne7zeenbolhyllbuhgcqwjy

Internet cross-media retrieval based on deep learning

Bin Jiang, Jiachen Yang, Zhihan Lv, Kun Tian, Qinggang Meng, Yan Yan
2017 Journal of Visual Communication and Image Representation  
Based on the traditional content of cross media learning research, we can . 1 .1.  ...  In this paper, we propose a real time internet cross-media retrieval based on deep learning.  ... 
doi:10.1016/j.jvcir.2017.02.011 fatcat:jxefua77mrf63i57ikpkhwvsbm

A New Benchmark and Approach for Fine-grained Cross-media Retrieval

Xiangteng He, Yuxin Peng, Liu Xie
2019 Proceedings of the 27th ACM International Conference on Multimedia - MM '19  
Cross-media retrieval is to return the results of various media types corresponding to the query of any media type. Existing researches generally focus on coarse-grained cross-media retrieval.  ...  However, few researches focus on fine-grained cross-media retrieval, which is a highly challenging and practical task.  ...  It will encourage further researches on fine-grained cross-media retrieval. (2) A new approach -We have proposed the FGCrossNet, which is a uniform deep model to simultaneously learn the common representations  ... 
doi:10.1145/3343031.3350974 dblp:conf/mm/HePX19 fatcat:3h54vm5hobblphrwapxsyywyf4

Mining and searching association relation of scientific papers based on deep learning [article]

Jie Song and Meiyu Liang and Zhe Xue and Feifei Kou and Ang Li
2022 arXiv   pre-print
Therefore, the research on mining and searching the association relationship of scientific papers based on deep learning has far-reaching practical significance.  ...  technological big data and help to design applications to serve scientific researchers.  ...  Based on interest ranking, relevance ranking, feedback mechanism, and ranking optimization mechanism, one can realize the retrieval and sorting of scientific papers and efficient partition indexing of  ... 
arXiv:2204.11488v1 fatcat:zxwvpnids5bopberzumjofgupq

Second order probabilistic models for within-document novelty detection in academic articles

Laurence A.F. Park, Simeon Simoff
2014 Proceedings of the 37th international ACM SIGIR conference on Research & development in information retrieval - SIGIR '14  
Incorporating Query-Specific Feedback Into Learning-To-Rank Models Ethem Can, Bruce Croft, R. Manmatha 3. Diversifying Query Suggestions Based on Query Documents Youngho Kim, Bruce Croft 4.  ...  Item Group Based Pairwise Preference Learning for Personalized Ranking Shuang Qiu, Jian Cheng, Ting Yuan, Cong Leng, Hanqing Lu 100. Where Not to Go?  ... 
doi:10.1145/2600428.2609520 dblp:conf/sigir/ParkS14 fatcat:ye2rtri2xjbyrjvkkzgt7srcfu

A Semantic Approach to Cross-Disciplinary Research Collaboration

Laurens De Vocht, Davy Van Deursen, Erik Mannens, Rik Van de Walle
2012 International Journal of Emerging Technologies in Learning (iJET)  
We propose an environment that improves the scientific research and learning process by allowing researchers to efficiently browse the information and concepts represented as learning objects.  ...  The research data is extracted from many online resources and Social Media. We implement learning objects as an abstraction of the semantically modeled research data.  ...  ACKNOWLEDGMENT The research activities that have been described in this paper were funded by Ghent University, the Social Learning Department at Graz University of Technology, the Interdisciplinary Institute  ... 
doi:10.3991/ijet.v7is2.2331 fatcat:l3ykdo4bsfh4nnchw2u6ig55v4

Online social image ranking in diversified preferences

Xuezhuan Zhao, Lishen Pei, Tao Li, Zheng Zhang
2020 EURASIP Journal on Image and Video Processing  
By re-ranking the rank output of OMKR based on each preference ranking model, we obtain a set of ranking lists encoding different potential aspects of user preference.  ...  By optimizing the ranking performance with multi-dimensional queries, the semantic consistency between the image ranking and textual query input is directly maximized without relying on the intermediate  ...  It takes as input a set of training queries as well as a set of ranked online social media images, and outputs a trained model to achieve high ranking performance on new queries.  ... 
doi:10.1186/s13640-020-00540-4 fatcat:mkva766gh5cdxbztsbcfiz6lse

Cross-Media Similarity Evaluation for Web Image Retrieval in the Wild [article]

Jianfeng Dong, Xirong Li, Duanqing Xu
2018 arXiv   pre-print
Image retrieval experiments on the challenging Clickture dataset show that the proposed text2image compares favorably to recent deep learning based alternatives.  ...  Queries are automatically categorized according to the proposed query visualness measure, and later connected to the evaluation of multiple cross-media similarity models on three test sets.  ...  Yuxiao Hu) for evaluating our results on IRC-MM15-test. The authors also thank the anonymous reviewers for their insightful comments.  ... 
arXiv:1709.01305v2 fatcat:adfiz723k5d7vopelt2l7vriri

SciEv: Finding Scientific Evidence Papers for Scientific News [article]

Md Reshad Ul Hoque, Jiang Li, Jian Wu
2022 arXiv   pre-print
The system achieves a P@1=50%, P@5=71%, and P@10=74% when it uses a TFIDF-based text representation. The transformer-based re-ranker achieves a comparable performance but costs twice as much time.  ...  In the past decade, many scientific news media that report scientific breakthroughs and discoveries emerged, bringing science and technology closer to the general public.  ...  We trained a multi-disciplinary transformer-based transfer-learning model that beats other heuristic and learning-based models, achieving an F1=0.93-1.  ... 
arXiv:2205.00126v1 fatcat:bouw4n5xxvdftoyko5nd3dvsga

High diversity transforms multimedia information retrieval into a cross-cutting field

James Z. Wang, Nozha Boujemaa, Yixin Chen
2007 SIGMOD record  
It has address algorithms for region-based query systems with semantics localization, efficient queries by example, query by concepts, aspects of the on-line learning of user queries, propagation of semantic  ...  Liu et al. explored image annotation based on manifold ranking. Gao and Fan proposed a multilevel image annotation approach using salient objects and concept ontology.  ... 
doi:10.1145/1276301.1276315 fatcat:cdowdmpllbcf3mea7m2wotbuyq

Content Facets For Individual Information Needs In Media

Elisabeth Lex, Stefanie Lindstaedt, Michael Granitzer, Harald Kosch
2018 Zenodo  
From the media consumer perspective, navigating the haystack of information produced by media as well as finding content that meets ones quality demands is challenging.  ...  Several proposed content facets have successfully been implemented in APA Labs, a Web-based framework for faceted search in traditional and social me- dia.  ...  The uogTr group used a Machine Learning approach based on a Voting Model as well as a learning-to-rank method, specifically the AdaRank to learn ranking models for the fact inclinations [Macdonald et  ... 
doi:10.5281/zenodo.1195993 fatcat:ce3ljnthjfhkpir3y4atnnlicy

Content Facets For Individual Information Needs In Media

Elisabeth Lex, Stefanie Lindstaedt, Michael Granitzer, Harald Kosch
2018 Zenodo  
From the media consumer perspective, navigating the haystack of information produced by media as well as finding content that meets ones quality demands is challenging.  ...  Several proposed content facets have successfully been implemented in APA Labs, a Web-based framework for faceted search in traditional and social me- dia.  ...  The uogTr group used a Machine Learning approach based on a Voting Model as well as a learning-to-rank method, specifically the AdaRank to learn ranking models for the fact inclinations [Macdonald et  ... 
doi:10.5281/zenodo.1196397 fatcat:udr3736ejbek5lzl34tu4g4ppq

Gathering training sample automatically for social event visual modeling

Xueliang Liu, Benoit Huet
2012 Proceedings of the 2012 international workshop on Socially-aware multimedia - SAM '12  
In recent years, the emergence of social media on the Internet has derived many of interesting research and applications.  ...  A novel ranking approach is devised to select a set of negative samples. The visual event models are learned from automatically collected samples using SVM.  ...  Common tags, along with their corresponding photos, are identified based on a novel approach inspired from learning to rank [10] , which we detail in section 3.2.  ... 
doi:10.1145/2390876.2390881 dblp:conf/mm/LiuH12 fatcat:4q565k2nmzazzpunzs5z74swly

Guest Editorial: Large-Scale Multimedia Content Analysis on Social Media

Haojie Li, Zheng-Jun Zha, Benoit Huet, Qi Tian
2016 Multimedia tools and applications  
.), where people record, share/broadcast, and comment on media content, i.e., images and videos, leading to an accelerated proliferation of social media on the Internet.  ...  The rapid increase of social media has raised numerous new research challenges to multimedia content analysis.  ...  Two image ranking methods, i.e., distance weights based re-ranking and bit importance based re-ranking methods are developed to rerank the hashing indexed images for the given query.  ... 
doi:10.1007/s11042-016-3255-z fatcat:t6pi6bjigfg57dj5aaa7hbafgy
« Previous Showing results 1 — 15 out of 15,068 results