Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Shaofei Huang"'
Autor:
Tianrui Hui, Si Liu, Zihan Ding, Shaofei Huang, Guanbin Li, Wenguan Wang, Luoqi Liu, Jizhong Han
Publikováno v:
IEEE Transactions on Pattern Analysis and Machine Intelligence. :1-14
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c517f0df005e8870a94ff275e91b63af
https://doi.org/10.1109/tpami.2023.3235720
https://doi.org/10.1109/tpami.2023.3235720
Autor:
Shaofei Huang
Publikováno v:
Litera. :176-183
The principle of politeness is a means of communication widely used in every society by individuals, but this principle has peculiarities in different cultures. The principles of politeness play an important role in the analysis of the speech etiquet
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::978ee80d5dc667f66bd62bb005b0679c
https://doi.org/10.25136/2409-8698.2022.5.37904
https://doi.org/10.25136/2409-8698.2022.5.37904
Publikováno v:
SSRN Electronic Journal.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::1b909d0747b0c96aee4ceaba4c0e631c
https://doi.org/10.2139/ssrn.4214323
https://doi.org/10.2139/ssrn.4214323
Publikováno v:
ACM Multimedia
Recently proposed fine-grained 3D visual grounding is an essential and challenging task, whose goal is to identify the 3D object referred by a natural language sentence from other distractive objects of the same category. Existing works usually adopt
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::95f1e36cf8186b4b4dc3bc9358c549d9
http://arxiv.org/abs/2108.02388
http://arxiv.org/abs/2108.02388
Autor:
Si Liu, Tianrui Hui, Wenguan Wang, Fei Wang, Shaofei Huang, Jizhong Han, Zihan Ding, Guanbin Li
Publikováno v:
CVPR
Language-queried video actor segmentation aims to predict the pixel-level mask of the actor which performs the actions described by a natural language query in the target frames. Existing methods adopt 3D CNNs over the video clip as a general encoder
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::17cb558b9eca1815fdf8eb31c508f489
https://doi.org/10.1109/cvpr46437.2021.00417
https://doi.org/10.1109/cvpr46437.2021.00417
Publikováno v:
IEEE transactions on pattern analysis and machine intelligence. 44(9)
Given a natural language expression and an image/video, the goal of referring segmentation is to produce the pixel-level masks of the entities described by the subject of the expression. Previous approaches tackle this problem by implicit feature int
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1ec7949edfc6ecfdf585326c5ee435d5
https://pubmed.ncbi.nlm.nih.gov/33983880
https://pubmed.ncbi.nlm.nih.gov/33983880
Publikováno v:
2020 5th International Conference on Information Science, Computer Technology and Transportation (ISCTT).
In this paper, methods of realizing sign language recognition (SLR) on mobile edge devices - AutoML and Transfer Learning - are recommended and compared. Their performance in SLR is compared in this article in terms of model size, speed, and accuracy
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ef99a70078c309eee7ef6a802e35008f
https://doi.org/10.1109/isctt51595.2020.00093
https://doi.org/10.1109/isctt51595.2020.00093
Publikováno v:
ACM Multimedia
Video super-resolution (SR) aims at generating high-resolution (HR) frames from consecutive low-resolution (LR) frames. The challenge is how to make use of temporal coherence among neighbouring LR frames. Most previous works use motion estimation and
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::18cebde38f65b5c00bd63124c3e052b1
https://doi.org/10.1145/3394171.3413587
https://doi.org/10.1145/3394171.3413587
Publikováno v:
CVPR
Referring image segmentation aims at segmenting the foreground masks of the entities that can well match the description given in the natural language expression. Previous approaches tackle this problem using implicit feature interaction and fusion b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5efe0c548b07bad932a37b70234f3ccd
http://arxiv.org/abs/2010.00514
http://arxiv.org/abs/2010.00514
Publikováno v:
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society.
Learning to capture dependencies between spatial positions is essential to many visual tasks, especially the dense labeling problems like scene parsing. Existing methods can effectively capture long-range dependencies with self-attention mechanism wh
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2cc0dfa8494dc378b74d195330c075f5
https://pubmed.ncbi.nlm.nih.gov/32755858
https://pubmed.ncbi.nlm.nih.gov/32755858