728x90
반응형
Embodied Question Answering
We present a new AI task -- Embodied Question Answering (EmbodiedQA) -- where an agent is spawned at a random location in a 3D environment and asked a question ("What color is the car?"). In order to answer, the agent must first intelligently navigate to e
arxiv.org
논문을 깊게 읽고 만든 자료가 아니므로, 참고만 해주세요. 얕은 지식으로 모델의 핵심 위주로만 파악한 자료이다 보니 없는 내용도 많습니다. 혹시 사용하실 경우 댓글 부탁드립니다.
728x90
반응형
'Paper Reading > Vision and Language Navigation(VLN)' 카테고리의 다른 글
| QMDP-Net (0) | 2020.08.11 |
|---|---|
| FollowNet: Robot Navigation by Following Natural Language Directions with Deep Reinforcement Learning (0) | 2020.08.11 |
| Speaker-Follower Models for Vision-and-Language Navigation (0) | 2020.08.11 |
| Vision-and-Language Navigation (0) | 2020.08.11 |
| IQA: Visual Question Answering in Interactive Environments (0) | 2020.08.11 |
