Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2017
2017
2021
2021

Publication Types

Select...
4
2
2

Relationship

0
8

Authors

Journals

citations
Cited by 56 publications
(4 citation statements)
references
References 5 publications
(18 reference statements)
0
4
0
Order By: Relevance
“…We then combine the two representations to form the scene embedding (the late fusion as shown in the figure). This late fusion allows the downstream prediction to give more emphasis to the separated feature, which may be lost in early fusion (Lu et al [30]). Late fusion of the metric properties along with the hidden states of objects obtained through the GCN ensures that information like object position and size are available when predicting tool likelihoods.…”
Section: B Fusion Of Metric and Semantic Attributes (+Metric)mentioning
confidence: 99%
“…We then combine the two representations to form the scene embedding (the late fusion as shown in the figure). This late fusion allows the downstream prediction to give more emphasis to the separated feature, which may be lost in early fusion (Lu et al [30]). Late fusion of the metric properties along with the hidden states of objects obtained through the GCN ensures that information like object position and size are available when predicting tool likelihoods.…”
Section: B Fusion Of Metric and Semantic Attributes (+Metric)mentioning
confidence: 99%
“…In the last several years the leading positions in the area of text detection and recognition are occupied by neural networks methods [8] [9], but they have some drawbacks [5].…”
Section: Related Workmentioning
confidence: 99%
“…Recently, several approaches have been proposed to detect and recognize texts in videos and natural scene images [1,2,15,16].…”
Section: Literature Reviewmentioning
confidence: 99%
“…Prior work has addressed specific research problems that have bordered on printed and handwritten texts in scanned documents. Recently, embedded text in videos has received increasing attention as it often gives crucial information about the media content [1][2][3]. News videos generally contain two types of texts [2]: scene text and artificial text ( Figure 1).…”
Section: Introductionmentioning
confidence: 99%