2. 강의교수 정보
|
이름 |
손진희 |
학과(전공) |
인공지능대학원 |
| 이메일 주소 |
jeany@postech.ac.kr
|
Homepage |
|
| 연구실 |
공학2동 317호 |
전화 |
054-279-2251 |
| Office Hours |
|
3. 강의목표
1. Gain the background to conduct interdisciplinary research at the intersection of Vision and Language.
2. Obtain an overview of current research trends at the intersection of Vision and Language.
3. Acquire the skills to design a non-trivial deep learning model for a vision and language problem.
4. 강의선수/수강필수사항
Background: Calculus, probability theory, linear algebra,
Coursework: At least one among computer vision, natural Language processing, and machine learning
Programming skill: Substantial programming experience including script languages in Unix/Linux/MacOS environmen.
5. 성적평가
| 중간고사 |
기말고사 |
출석 |
과제 |
프로젝트 |
발표/토론 |
실험/실습 |
퀴즈 |
기타 |
계 |
|
|
|
|
|
|
|
|
|
|
| 비고 |
Assignments (20%): Reading assignments, paper reviews
Quizzes (20%): Short quizzes on key concepts covered in class
Class Participation (10%): Attendance and in-class discussion
Final Project (50%): Research project, presentations, and final report
Note: No Pass/Fail grading
|
6. 강의교재
| 도서명 |
저자명 |
출판사 |
출판년도 |
ISBN |
|
Course slides and papers
|
|
|
0000
|
|
7. 참고문헌 및 자료
Deep Learning by I. Goodfellow, Y. Bengio, and A. Courville
Computer Vision: A Modern Approach by D. Forsyth and J. Ponce
Foundations of Statistical Natural Language Processing by C. Manning and H. Schuetze
8. 강의진도계획
1주차: Intro. to CV & NLP
2주차: Convolutional Networks (CNNs) & Recurrent Networks (RNNs)
3주차: Attention and Transformers
4주차: Vision-language models: Contrastive learning
5주차: Vision-language models: Grounding for object detection & segmentation
6주차: Vision-language models: Reasoning and visual question answering
7주차: Project intermediate presentation 1
8주차: Project intermediate presentation 2
9주차: Multimodal Generation: Image and Video Generation
10주차: Beyond Image and Text: Video, Audio, Actions, and Embodied AI
11주차: Post-training and Reinforcement Learning for Multimodal Models
12주차: Multimodal Agents and Reasoning
13주차: Emerging Topics in Vision and Language / Guest Lecture (tentative)
14-15주차: Project final presentation
9. 수업운영
Lecture + research paper reviews + research project
11. 장애학생에 대한 학습지원 사항
- 수강 관련: 문자 통역(청각), 교과목 보조(발달), 노트필기(전 유형) 등
- 시험 관련: 시험시간 연장(필요시 전 유형), 시험지 확대 복사(시각) 등
- 기타 추가 요청사항 발생 시 장애학생지원센터(279-2434)로 요청