728x90
반응형
GuessWhat?! Visual object discovery through multi-modal dialogue
We introduce GuessWhat?!, a two-player guessing game as a testbed for research on the interplay of computer vision and dialogue systems. The goal of the game is to locate an unknown object in a rich image scene by asking a sequence of questions. Higher-lev
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 > Dialogue System' 카테고리의 다른 글
| Evaluating Visual Conversational Agents via Cooperative Human-AI Games (0) | 2020.08.11 |
|---|---|
| Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning (0) | 2020.08.11 |
| Visual Dialogue (0) | 2020.08.11 |
| Modulating early visual processing by language (0) | 2020.08.11 |
| End-to-end optimization of goal-driven and visually grounded dialogue systems (0) | 2020.08.11 |
