Filters








27,099 Hits in 4.8 sec

Preface SSW 2011 [chapter]

Paolo Cappellari, Roberto De Virgilio, Mark Roantree
2011 Lecture Notes in Business Information Processing  
A collaborative framework for annotating images in semantic search is presented in the paper by Hong and Reiff-Marganiec.  ...  In the short poster paper, McGinnes presents a semantic strategy to exploit ontologies for image retrieval in conceptual modeling.  ...  A collaborative framework for annotating images in semantic search is presented in the paper by Hong and Reiff-Marganiec.  ... 
doi:10.1007/978-3-642-22056-2_55 fatcat:hvnxenm22ndfxb7gmvklsrot3u

Collaborative analysis of multi-gigapixel imaging data using Cytomine

Raphaël Marée, Loïc Rollus, Benjamin Stévens, Renaud Hoyoux, Gilles Louppe, Rémy Vandaele, Jean-Michel Begon, Philipp Kainz, Pierre Geurts, Louis Wehenkel
2016 Bioinformatics  
It uses web development methodologies and machine learning in order to readily organize, explore, share, and analyze (semantically and quantitatively) multi-gigapixel imaging data over the internet.  ...  Results: We developed Cytomine to foster active and distributed collaboration of multidisciplinary teams for large-scale image-based studies.  ...  Acknowledgement We thank Pierre Ansen, Julien Confetti, and Olivier Caubo for various code contributions, and Alain Empain for system administration.  ... 
doi:10.1093/bioinformatics/btw013 pmid:26755625 pmcid:PMC4848407 fatcat:hhqsekbw3zft5d5ge3kart3eca

WebLogo-2M: Scalable Logo Detection by Deep Learning from the Web

Hang Su, Shaogang Gong, Xiatian Zhu
2017 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)  
progressively improving model capability.  ...  Specifically, we propose a novel incremental learning approach, called Scalable Logo Self-Training (SLST), capable of automatically self-discovering informative training images from noisy web data for  ...  Self-Training A Multi-Class Logo Detector We aim to automatically train a multi-class logo detection model incrementally from noisy and weakly labelled web images.  ... 
doi:10.1109/iccvw.2017.41 dblp:conf/iccvw/SuGZ17 fatcat:kc6p6kdrrrh7jbn6vec7sekf4y

Webly Supervised Semantic Segmentation

Bin Jin, Maria V. Ortiz Segovia, Sabine Susstrunk
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
We introduce a novel three-stage training pipeline to progressively learn semantic segmentation models.  ...  We propose a weakly supervised semantic segmentation algorithm that uses image tags for supervision.  ...  Conclusion We propose a novel three-stage training pipeline to progressively learn the semantic segmentation model from three sets of web images.  ... 
doi:10.1109/cvpr.2017.185 dblp:conf/cvpr/JinSS17 fatcat:gjqq5done5gwhcdojtftwvifwq

Recent Advances and Challenges of Semantic Image/Video Search

Shih-Fu Chang, Wei-Ying Ma, Arnold Smeulders
2007 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07  
Index Terms -semantic indexing, image and video search, content labeling, statistical modeling  ...  Such semantic indexing paradigm has been driven by the increasing availability of the large resources of corpora, novel labeling approaches, innovative image features, and machine learning techniques for  ...  IMAGE LABEL BY WEB SEARCH Manual annotation of image or video data is costly and difficult to scale up to a large set of concepts.  ... 
doi:10.1109/icassp.2007.367292 dblp:conf/icassp/ChangMS07 fatcat:wgnw233c4ndbtc5zrvrb4g5wqe

Webly Supervised Image Classification with Metadata: Automatic Noisy Label Correction via Visual-Semantic Graph

Jingkang Yang, Weirong Chen, Litong Feng, Xiaopeng Yan, Huabin Zheng, Wayne Zhang
2020 Proceedings of the 28th ACM International Conference on Multimedia  
However, adopting search queries or hashtags as web labels of images for training brings massive noise that degrades the performance of DNNs.  ...  For example, searching 'tiger cat' on Flickr will return a dominating number of tiger images rather than the cat images.  ...  Each image contains web tags and human-annotated ground-truth labels for the 81 concepts.  ... 
doi:10.1145/3394171.3413952 dblp:conf/mm/YangCFYZZ20 fatcat:iithcxh27rbcvov4m7uqa4hv4u

Learning Semantics From Multimedia Web Resources: An Introduction to the Special Issue

Qi Tian, Jinhui Tang, Marcel Worring, Daniel Gatica-perez
2012 IEEE transactions on multimedia  
ACKNOWLEDGMENT We thank all the reviewers for their valuable comments that ultimately ensure the high quality of the special issue, and all the contributing authors for their interesting and innovative  ...  Van der Schaar for sharing our vision and providing guidance. The editorial staff of T-MM, especially R. Wollman, has been extremely supportive, helpful, and patient throughout the entire process.  ...  The TA Ranking based Multi-correlation Tensor Factorization model is proposed to perform annotation prediction, which are considered as users' potential annotations for the images.  ... 
doi:10.1109/tmm.2012.2208026 fatcat:uohusfrilrcdvgrzac7xf3olq4

Scalable Deep Learning Logo Detection [article]

Hang Su, Shaogang Gong, Xiatian Zhu
2018 arXiv   pre-print
progressively improving model capability in a cross-model co-learning manner.  ...  Specifically, we propose a novel incremental learning approach, called Scalable Logo Self-co-Learning (SL^2), capable of automatically self-discovering informative training images from noisy web data for  ...  ., the Royal Society Newton Advanced Fellowship Programme (NA150459), and InnovateUK Industrial Challenge Project on Developing and Commercialising Intelligent Video Analytics Solutions for Public Safety  ... 
arXiv:1803.11417v2 fatcat:znlkivypxfdunm7iu3fmrsondu

An introduction to the special issue

Meixun Zhao, Liguang Sun, Quanzhen Chen, Wensheng Jiang
2013 Journal of Ocean University of China  
ACKNOWLEDGMENT We thank all the reviewers for their valuable comments that ultimately ensure the high quality of the special issue, and all the contributing authors for their interesting and innovative  ...  Van der Schaar for sharing our vision and providing guidance. The editorial staff of T-MM, especially R. Wollman, has been extremely supportive, helpful, and patient throughout the entire process.  ...  The TA Ranking based Multi-correlation Tensor Factorization model is proposed to perform annotation prediction, which are considered as users' potential annotations for the images.  ... 
doi:10.1007/s11802-013-2240-7 fatcat:yftgrrrowbdhlg32gaolzkuoza

EXACT: a collaboration toolset for algorithm-aided annotation of images with annotation version control

Christian Marzahl, Marc Aubreville, Christof A Bertram, Jennifer Maier, Christian Bergler, Christine Kröger, Jörn Voigt, Katharina Breininger, Robert Klopfleisch, Andreas Maier
2021 Scientific Reports  
In many research areas, scientific progress is accelerated by multidisciplinary access to image data and their interdisciplinary annotation.  ...  multi-centre whole slide image tumour annotation, and highly specialised whale sound spectroscopy clustering.  ...  All dynamic web-page contents like annotations, images or sub-images (tiles) for WSIs are loaded via JavaScript over the REST-API.  ... 
doi:10.1038/s41598-021-83827-4 pmid:33623058 pmcid:PMC7902667 fatcat:ipclys2hpzg5xdodpfaemkv2jm

A flexible, open, decentralized system for digital pathology networks

Robert Schuler, David E Smith, Gowri Kumaraguruparan, Ann Chervenak, Anne D Lewis, Dallas M Hyde, Carl Kesselman
2012 Studies in Health Technology and Informatics  
High-resolution digital imaging is enabling digital archiving and sharing of digitized microscopy slides and new methods for digital pathology.  ...  Few solutions exist for networking digital pathology operations.  ...  the NCRR grant Biomedical Informatics Research Network (NIH U24 RR025736-01), the BIRN Community Service Award (NIH U24 RR026057), the BIRN-CC supplemental award (NIH 3U24RR025736-01S1), and "Support for  ... 
pmid:22941985 pmcid:PMC3966426 fatcat:deramju7qfdbpppzuq4a36nfcy

Learning a Deep ConvNet for Multi-Label Classification With Partial Labels

Thibaut Durand, Nazanin Mehrasa, Greg Mori
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
To reduce the annotation cost, we propose to train a model with partial labels i.e. only some labels are known per image.  ...  Deep ConvNets have shown great performance for single-label image classification (e.g.  ...  However this strategy is designed for multi-class image classification and cannot be used for multi-label image classification because it uses a clustering-based model to measure the difficulty of the  ... 
doi:10.1109/cvpr.2019.00074 dblp:conf/cvpr/DurandMM19 fatcat:pmhwu26hcnaf7iz2gzfrwi2bzy

Special issue on semantic data analytics and bioinformatics

Haiying Wang, Man-Wai Mak, Hui Wang
2017 International Journal of Machine Learning and Cybernetics  
This special issue aims to report recent progresses in the areas spanning computer science, web technology, computational biology and Bioinformatics.  ...  Gene Ontology (GO) is becoming the de facto standard for annotating gene products. However, its significance is not limited to annotation applications.  ...  This special issue aims to report recent progresses in the areas spanning computer science, web technology, computational biology and Bioinformatics.  ... 
doi:10.1007/s13042-017-0749-6 fatcat:avywwtmaanc6zochhyzo4mfrbq

Web-based Multi-layered Exploration of Annotated Image-based Shape and Material Models

Alberto Jaspe Villanueva, Ruggero Pintus, Andrea Giachetti, Enrico Gobbetti
2019 Eurographics Workshop on Graphics and Cultural Heritage  
At run-time, an annotated multi-layered dataset is made available to clients by a standard web server.  ...  We introduce a novel versatile approach for letting users explore detailed image-based shape and material models integrated with structured, spatially-associated descriptive information.  ...  The authors thank CRBC Sassari, Accademia delle Belle Arti di Verona, and Ormylia Foundation for the access to the artworks for the purpose of digitization.  ... 
doi:10.2312/gch.20191346 dblp:conf/vast/VillanuevaPGG19 fatcat:23xx5tbb2necjc4vxykv7w4jty

Efficient data management infrastructure for the integration of imaging and omics data in life science research [article]

Luis Kuhn Cuellar, Andreas Friedrich, Gisela Gabernet, Luis de la Garza, Sven Fillinger, Adrian Seyboldt, Sven zur Oven-Krockhaus, Friederike Wanke, Sandra Richter, Wolfgang M. Thaiss, Marius Horger, Nisar Malek (+3 others)
2019 bioRxiv   pre-print
The proposed architecture introduces an interoperable image management system, the OMERO server, into the backend of qPortal, a FAIR-compliant web-based platform for omics data management.  ...  Here, we propose an approach based on principles of Service Oriented Architecture design, to allow the integrated management and analysis of multi-omics and biomedical imaging data.  ...  The copyright holder for this preprint (which this version posted April 21, 2020.  ... 
doi:10.1101/2019.12.28.889295 fatcat:mpmsznhgw5g7bcrvhdovakv5f4
« Previous Showing results 1 — 15 out of 27,099 results