ResearchWho?

김은솔

겸임교수

한양대학교(서울) 공과대학 데이터사이언스학부

논문[24]

#24. Efficient Compositional Translation Embedding for Visual Relationship Detection

2022.7 · Journal of KIISE 49(7):544-554

(DOI) https://doi.org/10.5626/JOK.2022.49.7.544

#23. MSTR: Multi-Scale Transformer for End-to-End Human-Object Interaction Detection

2022.6

(DOI) https://doi.org/10.1109/CVPR52688.2022.01897

프로시딩[3]

#3. Video-Text Representation Learning via Differentiable Weak Temporal Alignment

2022.6.18:5006-5015

(DOI) https://doi.org/10.1109/CVPR52688.2022.00496

#2. MSTR: Multi-Scale Transformer for End-to-End Human-Object Interaction Detection

2022.6.18:19556-19565

(DOI) https://doi.org/10.1109/CVPR52688.2022.01897