Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Sean T. Yang"'
Autor:
Sean T. Yang, Bill Howe
Publikováno v:
Companion Proceedings of the Web Conference 2022.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0ab816d893dd74b4a329308a8f295f2b
https://doi.org/10.1145/3487553.3524723
https://doi.org/10.1145/3487553.3524723
Autor:
Bill Howe, Abhishek Joshi, Lia Kazakova, Jevin D. West, Sean T. Yang, Bum Mook Oh, Po-Shen Lee
Publikováno v:
ICDAR
Publishers are increasingly using graphical abstracts to facilitate scientific search, especially across disciplinary boundaries. They are presented on various media, easily shared and information rich. However, very small amount of scientific public
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c30fb0c16bc2805a697b3f44fe799db1
https://doi.org/10.1109/icdar.2019.00173
https://doi.org/10.1109/icdar.2019.00173
Publikováno v:
WWW
We present GraviTIE (Global Representation and Visualization of Text and Image Embeddings, pronounced ”gravity”), an interactive visualization system for large-scale image datasets. GraviTIE operates on datasets consisting of images equipped with
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f507987b79a6fe23d17d5c6b2badeeb9
https://doi.org/10.1145/3308558.3314142
https://doi.org/10.1145/3308558.3314142
Publikováno v:
ICPR
We propose JECL, a method for clustering image-caption pairs by training parallel encoders with regularized clustering and alignment objectives, simultaneously learning both representations and cluster assignments. These image-caption pairs arise fre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b0d70dada9616d973c2bbc594868d125
http://arxiv.org/abs/1901.01860
http://arxiv.org/abs/1901.01860
Publikováno v:
ICDAR
We consider a new approach to extracting information from dendrograms in the biological literature representing phylogenetic trees. Existing algorithmic approaches to extract these relationships rely on tracing tree contours and are very sensitive to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::bd84a9cfe0b6e438cac20a13c82348e7
https://doi.org/10.1109/icdar.2017.180
https://doi.org/10.1109/icdar.2017.180
Publikováno v:
WWW (Companion Volume)
We consider how patterns of figure use in the scientific literature relate to impact, change over time, and vary across disciplines. We use a convolutional neural network to embed figures as feature vectors in a high-dimensional space, then visualize
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8160dde3d6c596fc65efafcca03b7704
https://doi.org/10.1145/3041021.3053065
https://doi.org/10.1145/3041021.3053065