728x90
반응형
Modulating early visual processing by language
It is commonly assumed that language refers to high-level visual concepts while leaving low-level visual processing unaffected. This view dominates the current literature in computational models for language-vision tasks, where visual and linguistic input
arxiv.org
180112_Modulating early visual processing by language.pptx
0.61MB
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 |
| End-to-end optimization of goal-driven and visually grounded dialogue systems (0) | 2020.08.11 |
| GuessWhat?! Visual object discovery through multi-modal dialogue (0) | 2020.08.11 |
