Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Siyang Qin"'
Publikováno v:
Discrete Dynamics in Nature and Society, Vol 2019 (2019)
Considering the rapid development of the tourist leisure industry and the surge of tourist quantity, insufficient information regarding tourists has placed tremendous pressure on traffic in scenic areas. In this paper, the author uses the Big Data te
Externí odkaz:
https://doaj.org/article/4e2671bed1144302b1290387b0477ad5
Autor:
Shangbang Long, Siyang Qin, Dmitry Panteleev, Alessandro Bissacco, Yasuhisa Fujii, Michalis Raptis
Scene text detection and document layout analysis have long been treated as two separate tasks in different image domains. In this paper, we bring them together and introduce the task of unified scene text detection and layout analysis. The first hie
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::39b96e836e93f99f90d0713e382f6c81
Autor:
Chen-Yu Lee, Chu Wang, Yasuhisa Fujii, Chun-Liang Li, Ashok C. Popat, Renshen Wang, Tomas Pfister, Siyang Qin
Publikováno v:
ACL/IJCNLP (2)
Natural reading orders of words are crucial for information extraction from form-like documents. Despite recent advances in Graph Convolutional Networks (GCNs) on modeling spatial layout patterns of documents, they have limited ability to capture rea
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b89a00b489f35e16ef6f144927934194
http://arxiv.org/abs/2106.10786
http://arxiv.org/abs/2106.10786
Publikováno v:
Neat, Leo; Peng, Ren; Qin, Siyang; & Manduchi, Roberto. (2019). Scene Text Access: A Comparison of Mobile OCR Modalities for Blind Users. UC Santa Cruz: Retrieved from: http://www.escholarship.org/uc/item/50n43705
IUI
IUI
We present a study with seven blind participants using three different mobile OCR apps to find text posted in various indoor environments. The first app considered was Microsoft SeeingAI in its Short Text mode, which reads any text in sight with a mi
Publikováno v:
ICCV
We propose an end-to-end trainable network that can simultaneously detect and recognize text of arbitrary shape, making substantial progress on the open problem of reading scene text of irregular shape. We formulate arbitrary shape text detection as
Publikováno v:
3DV
Kim, S; Manduchi, R; & Qin, S. (2018). Multi-planar Monocular Reconstruction of Manhattan Indoor Scenes. UC Santa Cruz: Retrieved from: http://www.escholarship.org/uc/item/43w4v25v
Kim, S; Manduchi, R; & Qin, S. (2018). Multi-planar Monocular Reconstruction of Manhattan Indoor Scenes. UC Santa Cruz: Retrieved from: http://www.escholarship.org/uc/item/43w4v25v
We present a novel algorithm for geometry and camera pose reconstruction from image sequences that is specialized for indoor Manhattan scenes. Unlike general-purpose SfM/SLAM, our system represents geometric primitives in terms of canonically oriente
Publikováno v:
WACV
We propose a new technique for the accurate segmenta- tion of text strokes from an image. The algorithm takes in a cropped image containing a word. It first performs a coarse segmentation using a Fully Convolutional Network (FCN). While not accurate,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::224367ad03ed91762e4a314fb55d6c50
https://escholarship.org/uc/item/4pz3r5t3
https://escholarship.org/uc/item/4pz3r5t3
Autor:
Roberto Manduchi, Siyang Qin
Publikováno v:
ICDAR
We introduce an algorithm for word-level text spotting that is able to accurately and reliably determine the bounding regions of individual words of text "in the wild". Our system is formed by the cascade of two convolutional neural networks. The fir
Publikováno v:
ICME
Selfies have become commonplace. More and more people take pictures of themselves, and enjoy enhancing these pictures using a variety of image processing techniques. One specific functionality of interest is automatic skin and hair segmentation, as t
Publikováno v:
2017 29th Chinese Control And Decision Conference (CCDC).
Compared with conventional travel data such as GPS data, detector data and float car data, call detail record data from the cell phone communication not only cost low but also has a large scale which demonstrate it is the best way to collect travel i