SegEQA : video segmentation based visual attention for embodied question answering
Embodied Question Answering (EQA) is a newly defined research area where an agent is required to answer the user's questions by exploring the real world environment. It has attracted increasing research interests due to its broad applications in automatic driving system, in-home robots, and per...
Saved in:
Main Authors: | Luo, Haonan, Lin, Guosheng, Liu, Zichuan, Liu, Fayao, Tang, Zhenmin, Yao, Yazhou |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/144345 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Robust-EQA: robust learning for embodied question answering with noisy labels
by: Luo, Haonan, et al.
Published: (2023) -
TRRNet : tiered relation reasoning for compositional visual question answering
by: Yang, Xiaofeng, et al.
Published: (2020) -
SmooSeg: smoothness prior for unsupervised semantic segmentation
by: Lan, Mengcheng, et al.
Published: (2024) -
CANet : class-agnostic segmentation networks with iterative refinement and attentive few-shot learning
by: Zhang, Chi, et al.
Published: (2020) -
Debiasing visual question and answering with answer preference
by: Zhang, Xinye
Published: (2020)