Graph edit distance reward : learning to edit scene graph
Scene Graph, as a vital tool to bridge the gap between language domain and image domain, has been widely adopted in the cross-modality task like VQA. In this paper, we propose a new method to edit the scene graph according to the user instructions, which has never been explored. To be specific, in o...
Main Authors: | Chen, Lichang, Lin, Guosheng, Wang, Shijie, Wu, Qingyao |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Conference Paper |
Language: | English |
Published: |
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/144419 |
Similar Items
-
Textual Research on the Gongxu Edition of Guoyu during the Song Dynasty
by: Qu, Jingyi, et al.
Published: (2017) -
Age-related differences in functional connectivity during scene encoding
by: Leow, Dayton Wei Yang
Published: (2014) -
Learning on heterogeneous graphs using high-order relations
by: Lee, See Hian, et al.
Published: (2021) -
On taxonomy of fuzzy graphs and their isomorphisms /
by: Nurfarhana Hassan, 1993-, author 613905, et al.
Published: (2017) -
On taxonomy of fuzzy graphs and their isomorphisms /
by: Nurfarhana Hassan, 1993-, author 613905
Published: (2017)