TRRNet : tiered relation reasoning for compositional visual question answering
Compositional visual question answering requires reasoning over both semantic and geometry object relations. We propose a novel tiered reasoning method that dynamically selects object level candidates based on language representations and generates robust pairwise relations within the selected candi...
Saved in:
Main Authors: | Yang, Xiaofeng, Lin, Guosheng, Lv, Fengmao, Liu, Fayao |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/144262 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Visual questioning and answering
by: Ong, Zavier Jian Le
Published: (2024) -
VISUAL RELATION DRIVEN VIDEO QUESTION ANSWERING
by: XIAO JUNBIN
Published: (2023) -
Retrieving questions and answers in community-based question answering services
by: WANG KAI
Published: (2011) -
Answers or no answers : studying question answerability in stack overflow
by: Chua, Alton Yeow Kuan, et al.
Published: (2020) -
Aggregated community question answering
by: Snehasish Banerjee, et al.
Published: (2015)