2021
DOI: 10.1109/tcsvt.2020.3036860
|View full text |Cite
|
Sign up to set email alerts
|

Noise Augmented Double-Stream Graph Convolutional Networks for Image Captioning

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1

Citation Types

0
4
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
6
3

Relationship

0
9

Authors

Journals

citations
Cited by 48 publications
(4 citation statements)
references
References 47 publications
0
4
0
Order By: Relevance
“…Among the list of the current state-of-the-art works in the field of image captioning which also resembles our idea up to a certain extent only is the use of graph convolution neural networks to understand the global and regional context of an image and its objects [23,24,25]. The graph convolution neural networks are used to understand the semantic and spatial relationship which helps the captioning model to generate spatial tokens e.g., towards, inside, near, etc.…”
Section: Related Workmentioning
confidence: 93%
“…Among the list of the current state-of-the-art works in the field of image captioning which also resembles our idea up to a certain extent only is the use of graph convolution neural networks to understand the global and regional context of an image and its objects [23,24,25]. The graph convolution neural networks are used to understand the semantic and spatial relationship which helps the captioning model to generate spatial tokens e.g., towards, inside, near, etc.…”
Section: Related Workmentioning
confidence: 93%
“…After that, Anderson et al [3] propose to use Faster R-CNN [36] as encoder and achieve significant improvement. Some subsequent works [4], [5], [8], [37], [38] follow this paradigm. Recently, transformerbased models have demonstrated excellent performance in image captioning task [5], [7], [39]- [41].…”
Section: Introductionmentioning
confidence: 97%
“…For difficulty 1), encouraging by the method (Wu et al, 2021b), the noise can be injected into RNN hidden states to predict the mean and standard deviation, and manipulate the RNN transition states. In this way, the network robustness can be significantly enhanced and the issue can be well solved.…”
Section: Introductionmentioning
confidence: 99%