DE eng

Search in the Catalogues and Directories

Hits 1 – 14 of 14

1
A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer ...
Abstract: Most existing video text spotting benchmarks focus on evaluating a single language and scenario with limited data. In this work, we introduce a large-scale, Bilingual, Open World Video text benchmark dataset(BOVText). There are four features for BOVText. Firstly, we provide 2,000+ videos with more than 1,750,000+ frames, 25 times larger than the existing largest dataset with incidental text in videos. Secondly, our dataset covers 30+ open categories with a wide selection of various scenarios, e.g., Life Vlog, Driving, Movie, etc. Thirdly, abundant text types annotation (i.e., title, caption or scene text) are provided for the different representational meanings in video. Fourthly, the BOVText provides bilingual text annotation to promote multiple cultures live and communication. Besides, we propose an end-to-end video text spotting framework with Transformer, termed TransVTSpotter, which solves the multi-orient text spotting in video with a simple, but efficient attention-based query-key mechanism. It ... : 20 pages, 6 figures ...
Keyword: Computation and Language cs.CL; Computer Vision and Pattern Recognition cs.CV; FOS Computer and information sciences
URL: https://arxiv.org/abs/2112.04888
https://dx.doi.org/10.48550/arxiv.2112.04888
BASE
Hide details
2
GrantRel: Grant Information Extraction via Joint Entity and Relation Extraction ...
BASE
Show details
3
Sentence Context Differentially Modulates Contributions of Fundamental Frequency Contours to Word Recognition in Chinese-Speaking Children With and Without Dyslexia
In: Front Psychol (2020)
BASE
Show details
4
Additional file 1: of Taxonomic integrative and phylogenetic identification of the first recorded Triatoma rubrofasciata in Zhangzhou, Fujian Province and Maoming, Guangdong Province, China ...
Hu, Yue; Gao, Min-Zhao; Huang, Ping. - : figshare, 2019
BASE
Show details
5
Additional file 1: of Taxonomic integrative and phylogenetic identification of the first recorded Triatoma rubrofasciata in Zhangzhou, Fujian Province and Maoming, Guangdong Province, China ...
Hu, Yue; Gao, Min-Zhao; Huang, Ping. - : figshare, 2019
BASE
Show details
6
Mandarin-Speaking Children’s Speech Recognition: Developmental Changes in the Influences of Semantic Context and F0 Contours
Zhou, Hong; Li, Yu; Liang, Meng. - : Frontiers Media S.A., 2017
BASE
Show details
7
Co-adaption of tRNA gene copy number and amino acid usage influences translation rates in three life domains
Du, Meng-Ze; Wei, Wen; Qin, Lei. - : Oxford University Press, 2017
BASE
Show details
8
Additional file 1: of Malaria control along China-Myanmar Border during 2007â 2013: an integrated impact evaluation ...
Xu, Jian-Wei; Li, Yong; Heng-Lin Yang. - : Figshare, 2016
BASE
Show details
9
Additional file 1: of Malaria control along China-Myanmar Border during 2007â 2013: an integrated impact evaluation ...
Xu, Jian-Wei; Li, Yong; Heng-Lin Yang. - : Figshare, 2016
BASE
Show details
10
Hybridization of harmony search with variable neighborhood search for restrictive single-machine earliness/tardiness problem
In: Information sciences. - New York, NY : Elsevier Science Inc. 226 (2013), 68-92
OLC Linguistik
Show details
11
Enriching career experience of international academics through language training and practicing programs
Zhou, Hong; Basnet, Badri; Pigozzo, Robyn. - : Griffith University, 2013
BASE
Show details
12
Searching for the neural mechanism of color filling-in
In: Filling-in (Oxford, 2003), p. 106-127
MPI für Psycholinguistik
Show details
13
Vowel systems in Mandarin languages
Zhou, Hong. - 1999
BASE
Show details
14
Cognate objects in Chinese
In: https://jps.library.utoronto.ca/index.php/twpl/article/viewFile/6265/3253/
BASE
Show details

Catalogues
0
0
1
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
1
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
12
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern