Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Feiqi Cao"'
Publikováno v:
Robotics, Vol 12, Iss 4, p 114 (2023)
Visual Question Answering (VQA) models fail catastrophically on questions related to the reading of text-carrying images. However, TextVQA aims to answer questions by understanding the scene texts in an image–question context, such as the brand nam
Externí odkaz:
https://doaj.org/article/7d186ce23f2d4b57bdfa7605718c5654
Autor:
Luo, Siwen1 (AUTHOR) siwen.luo@uwa.edu.au, Ivison, Hamish2 (AUTHOR) hamishiv@cs.washington.edu, Han, Soyeon Caren3 (AUTHOR) caren.han@unimelb.edu.au, Poon, Josiah4 (AUTHOR) josiah.poon@sydney.edu.au
Publikováno v:
ACM Computing Surveys. Sep2024, Vol. 56 Issue 9, p1-36. 36p.
Autor:
MANZOOR, MUHAMMAD ARSLAN, ALBARRI, SARAH, ZITING XIAN, ZAIQIAO MENG, NAKOV, PRESLAV, SHANGSONG LIANG
Publikováno v:
ACM Transactions on Multimedia Computing, Communications & Applications; Mar2024, Vol. 20 Issue 3, p1-34, 34p
Publikováno v:
Robotics; Aug2023, Vol. 12 Issue 4, p114, 18p
Autor:
Jin Huei Wong1, Alfatah, Mohammad1, Mei Fang Sin2, Hong May Sim2, Verma, Chandra S.1,3,4, Lane, David P.5, Arumugam, Prakash1 prakasha@bii.a-star.edu.sg
Publikováno v:
BMC Biology. 11/9/2017, Vol. 15, p1-17. 17p.