Retrieval of Sentence Sequences for an Image Stream via Coherence Recurrent Convolutional Networks
By a News Reporter-Staff News Editor at Journal of Robotics & Machine Learning -- Current study results on Machine Learning have been published. According to news reporting originating from Seoul, South Korea, by VerticalNews correspondents, research stated, “We propose an approach for retrieving a sequence of natural sentences for an image stream. Since general users often take a series of pictures on their experiences, much online visual information exists in the form of image streams, for which it would better take into consideration of the whole image stream to produce natural language descriptions.”
Financial support for this research came from National Research Foundation of Korea.
Our news editors obtained a quote from the research from Seoul National University, “While almost all previous studies have dealt with the relation between a single image and a single natural sentence, our work extends both input and output dimension to a sequence of images and a sequence of sentences. For retrieving a coherent flow of multiple sentences for a photo stream, we propose a multimodal neural architecture called coherence recurrent convolutional network (CRCN), which consists of convolutional neural networks, bidirectional long short-term memory (LSTM) networks, and an entity-based local coherence model. Our approach directly learns from vast user-generated resource of blog posts as text-image parallel training data. We collect more than 22 K unique blog posts with 170 K associated images for the travel topics of NYC, Disneyland, Australia, and Hawaii.”
According to the news editors, the research concluded: “We demonstrate that our approach outperforms other state-of-the-art image captioning methods for text sequence generation, using both quantitative measures and user studies via Amazon Mechanical Turk.”
For more information on this research see: Retrieval of Sentence Sequences for an Image Stream via Coherence Recurrent Convolutional Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2018;40(4):945-957. IEEE Transactions on Pattern Analysis and Machine Intelligence can be contacted at: Ieee Computer Soc, 10662 Los Vaqueros Circle, PO Box 3014, Los Alamitos, CA 90720-1314, USA. (Institute of Electrical and Electronics Engineers - http://www.ieee.org/; IEEE Transactions on Pattern Analysis and Machine Intelligence - http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=34)
The news editors report that additional information may be obtained by contacting C.C. Park, Seoul National University, Dept. of Comp Sci & Engn, Seoul 151742, South Korea. Additional authors for this research include Y. Kim and G. Kim.
The direct object identifier (DOI) for that additional information is: https://doi.org/10.1109/TPAMI.2017.2700381. This DOI is a link to an online electronic document that is either free or for purchase, and can be your direct source for a journal article and its citation.
Our reports deliver fact-based news of research and discoveries from around the world. Copyright 2018, NewsRx LLC
CITATION: (2018-04-09), Recent Findings in Machine Learning Described by Researchers from Seoul National University (Retrieval of Sentence Sequences for an Image Stream via Coherence Recurrent Convolutional Networks), Journal of Robotics & Machine Learning, 184, ISSN: 1944-186X, BUTTER® ID: 015467804
From the newsletter Journal of Robotics & Machine Learning.
https://www.newsrx.com/Butter/#!Search:a=15467804
This is a NewsRx® article created by NewsRx® and posted by NewsRx®. As proof that we are NewsRx® posting NewsRx® content, we have added a link to this steemit page on our main corporate website. The link is at the bottom left under "site links" at https://www.newsrx.com/NewsRxCorp/.
We have been in business for more than 20 years and our full contact information is available on our main corporate website.
We only upvote our posts after at least one other user has upvoted the article to increase the curation awards of upvoters.
NewsRx® offers 195 weekly newsletters providing comprehensive information on all professional topics, ranging from health, pharma and life science to business, tech, energy, law, and finance. Our newsletters report only the most relevant and authoritative information from qualified sources.