Filters








2,939 Hits in 4.3 sec

Leveraging auxiliary text terms for automatic image annotation

Ning Zhou, Yi Shen, Jinye Peng, Xiaoyi Feng, Jianping Fan
2011 Proceedings of the 20th international conference companion on World wide web - WWW '11  
This paper proposes a novel algorithm to annotate web images by automatically aligning the images with their most relevant auxiliary text terms.  ...  images and their auxiliary terms.  ...  We therefore propose an unsupervised algorithm to leverage auxiliary text term extracted from associated text to annotate web images.  ... 
doi:10.1145/1963192.1963281 dblp:conf/www/ZhouSPFF11 fatcat:wh4f3z7iovgtphlxzt5pdlpeoy

Search-based automatic image annotation via Flickr photos using tag expansion

Liang-Chi Hsieh, Winston H. Hsu
2010 2010 IEEE International Conference on Acoustics, Speech and Signal Processing  
Index Terms-Search-based automatic image annotation, tag expansion  ...  Exponentially growing photo collections motivate the needs for automatic image annotation for effective manipulations (e.g., search, browsing).  ...  Recently, researchers [3, 4, 5] begin to leverage the rich resources on the Web for automatic image annotation.  ... 
doi:10.1109/icassp.2010.5496215 fatcat:6ysc67uoejgx3i4bdosuuoztlu

T-IRS

Yiming Liu, Dong Xu, Ivor W. Tsang, Jiebo Luo
2009 Proceedings of the seventeen ACM international conference on Multimedia - MM '09  
In this demonstration, we present a (quasi) real-time textual query based image retrieval system (T-IRS) for consumer photos by leveraging millions of web images and their associated rich textual descriptions  ...  After a user provides a textual query (e.g., "boat"), our system automatically finds the positive web images that are related to the textual query "boat" as well as the negative web images which are irrelevant  ...  by leveraging the pre-learned decision stump ensemble classifier (referred to as auxiliary classifier).  ... 
doi:10.1145/1631272.1631479 dblp:conf/mm/LiuXTL09a fatcat:pc3q53duyzae3aiqerzpbdbvpy

Using large-scale web data to facilitate textual query based retrieval of consumer photos

Yiming Liu, Dong Xu, Ivor W. Tsang, Jiebo Luo
2009 Proceedings of the seventeen ACM international conference on Multimedia - MM '09  
In this paper, we present a (quasi) real-time textual query based personal photo retrieval system by leveraging millions of web images and their associated rich textual descriptions (captions, categories  ...  After a user provides a textual query (e.g., "pool"), our system exploits the inverted file method to automatically find the positive web images that are related to the textual query "pool" as well as  ...  The authors also thank Yi Yang for his helpful discussions and suggestions.  ... 
doi:10.1145/1631272.1631283 dblp:conf/mm/LiuXTL09 fatcat:5yoap3corzgmtjosivf5ql2fwy

Discriminative Factor Alignment across Heterogeneous Feature Space [chapter]

Fangwei Hu, Tianqi Chen, Nathan N. Liu, Qiang Yang, Yong Yu
2012 Lecture Notes in Computer Science  
In situations where the training data in a target domain are not sufficient to learn predictive models effectively, transfer learning leverages auxiliary source data from related domains for learning.  ...  and images.  ...  We thank Weinan Zhang and Erheng Zhong for discussions. We thank the support of grants from NSFC-RGC joint research project HKUST 624/09 and 60931160445.  ... 
doi:10.1007/978-3-642-33486-3_48 fatcat:3gwvso7n6ffgveb4cz2sdsse4m

Multi-cue Zero-Shot Learning with Strong Supervision

Zeynep Akata, Mateusz Malinowski, Mario Fritz, Bernt Schiele
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
To compensate for the weaker form of auxiliary information, we incorporate stronger supervision in the form of semantic part annotations on the classes from which we transfer knowledge.  ...  The most successful zero-shot learning approaches currently require a particular type of auxiliary information -namely attribute annotations performed by humans -that is not readily available for most  ...  We argue that ultimately zero-shot learning techniques should leverage the same "auxiliary information" in terms of text books and online articles that humans use, as those are readily available in large  ... 
doi:10.1109/cvpr.2016.14 dblp:conf/cvpr/AkataMFS16 fatcat:wv5o4wbrmbhgfeodbytgudp3ym

Multi-Cue Zero-Shot Learning with Strong Supervision [article]

Zeynep Akata and Mateusz Malinowski and Mario Fritz and Bernt Schiele
2016 arXiv   pre-print
To compensate for the weaker form of auxiliary information, we incorporate stronger supervision in the form of semantic part annotations on the classes from which we transfer knowledge.  ...  The most successful zero-shot learning approaches currently require a particular type of auxiliary information -- namely attribute annotations performed by humans -- that is not readily available for most  ...  We argue that ultimately zero-shot learning techniques should leverage the same "auxiliary information" in terms of text books and online articles that humans use, as those are readily available in large  ... 
arXiv:1603.08754v1 fatcat:dtsh5b3wxnagfomn4gte3rz25i

Discovering Useful Parts for Pose Estimation in Sparsely Annotated Datasets [article]

Mikhail Breslav, Tyson L. Hedrick, Stan Sclaroff, Margrit Betke
2016 arXiv   pre-print
Our experiments on images of a hawkmoth in flight show that our proposed approach significantly improves over existing work [27] for this application, while also being more generally applicable.  ...  Our unique High-Resolution Moth Flight (HRMF) dataset is made publicly available with annotations.  ...  Figure 2 . 2 Illustrating example of how auxiliary parts are leveraged: (a) Input test image.  ... 
arXiv:1605.00707v1 fatcat:muufpvzkfrcubgf2qs2t2uembm

Textual Query of Personal Photos Facilitated by Large-Scale Web Data

Yiming Liu, Dong Xu, Ivor Wai-Hung Tsang, Jiebo Luo
2011 IEEE Transactions on Pattern Analysis and Machine Intelligence  
On the other hand, as an emerging paradigm, web data-based methods leverage millions of web images and the associated rich textual descriptions for image annotation.  ...  However, to obtain the initial annotations, the users are required to describe each photo album using textual terms, which are then submitted to an online image server (such as Flickr.com) to search for  ...  To automatically retrieve consumer photos using textual queries, we choose to leverage millions of web images and their surrounding texts as the bridge between the domains of the web images and the consumer  ... 
doi:10.1109/tpami.2010.142 pmid:20714015 fatcat:xpcvwx75gzbzlkyprakslzxqmi

Unsupervised Semantic Feature Discovery for Image Object Retrieval and Tag Refinement

Yin-Hsi Kuo, Wen-Huang Cheng, Hsuan-Tien Lin, Winston H. Hsu
2012 IEEE transactions on multimedia  
Therefore, the existing solutions for image retrieval rely on either the image contents (e.g., low-level features) or the surrounding texts (e.g., descriptions, tags) only.  ...  In this work, we tackle the problem by leveraging both the image contents and associated textual information in the social media to approximate the semantic representations for the two modalities.  ...  It can not only help to retain representative tags for each image but also automatically derive meaningful tags to annotate unlabeled images.  ... 
doi:10.1109/tmm.2012.2190386 fatcat:midugvtgbfefzgmewb5soaesda

M2FN: Multi-step modality fusion for advertisement image assessment

Kyung-Wha Park, Jung-Woo Ha, JungHoon Lee, Sunyoung Kwon, Kyung-Min Kim, Byoung-Tak Zhang
2021 Applied Soft Computing  
Although recent studies have attempted to use deep neural networks for this purpose, these studies have not utilized image-related auxiliary attributes, which include embedded text frequently found in  ...  ad dataset with rich auxiliary attributes.  ...  The authors thank NAVER AI LAB, NAVER CLOVA for constructive discussion and LINE Corp. for preparing data.  ... 
doi:10.1016/j.asoc.2021.107116 fatcat:lutrwy3ycvdrtfvw7mvca6ozcu

EZLearn: Exploiting Organic Supervision in Large-Scale Data Annotation [article]

Maxim Grechkin, Hoifung Poon, Bill Howe
2018 arXiv   pre-print
Distant supervision has emerged as a promising paradigm for exploiting such indirect supervision by automatically annotating examples where the text description contains a class mention in the lexicon.  ...  In this paper, we introduce an auxiliary natural language processing system for the text modality, and incorporate co-training to reduce noise and augment signal in distant supervision.  ...  EZLearn leverages domain lexicons to annotate noisy examples from text, similar to distant supervision [Mintz et al., 2009] .  ... 
arXiv:1709.08600v3 fatcat:gupmggcivfapva7hrv327q7khm

EZLearn: Exploiting Organic Supervision in Automated Data Annotation

Maxim Grechkin, Hoifung Poon, Bill Howe
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
Distant supervision has emerged as a promising paradigm for exploiting such indirect supervision by automatically annotating examples where the text description contains a class mention in the lexicon.  ...  In this paper, we introduce an auxiliary natural language processing system for the text modality, and incorporate co-training to reduce noise and augment signal in distant supervision.  ...  EZLearn leverages domain lexicons to annotate noisy examples from text, similar to distant supervision [Mintz et al., 2009] .  ... 
doi:10.24963/ijcai.2018/568 dblp:conf/ijcai/GrechkinPH18 fatcat:sq6vmhjy3zf5ph3yvh6qwiuzke

A Survey on Machine Learning Techniques for Auto Labeling of Video, Audio, and Text Data [article]

Shikun Zhang, Omid Jafari, Parth Nagarkar
2021 arXiv   pre-print
In this survey paper, we provide a review of previous techniques that focuses on optimized data annotation and labeling for video, audio, and text data.  ...  Machine learning has been utilized to perform tasks in many different domains such as classification, object detection, image segmentation and natural language analysis.  ...  Authors train the auto-annotated data to develop an auxiliary Long Short-Term Memory (LSTM) representation.  ... 
arXiv:2109.03784v1 fatcat:uu55zfmtajcvdjekxeaue76izy

Improvement of Ancient Shui Character Recognition model Based on convolutional neural network

Hongshuai Zhao, Haozhen Chu, Yuanyuan Zhang, Yu Jia
2020 IEEE Access  
Then the unsupervised density clustering algorithm of information entropy can automatically annotate the text image for saving labor.  ...  annotation of text or images based on the density and the information entropy.  ... 
doi:10.1109/access.2020.2972807 fatcat:stctetbnezendavm34xoxmtg5u
« Previous Showing results 1 — 15 out of 2,939 results