Type | Year | Title | Cited | Download |
---|---|---|---|---|
Conference
|
2024 | Look and Edit: Visual-Guided Multimodal Editing with Retrieval-Enhanced Counterfactuals Jin Seong, Ji-Yun Park 한국인공지능학회 학술 대회 (추계) 2024, pp.1-9 | ||
Conference
|
2024 | Can We Edit the Eyes? A Comparative Analysis of Knowledge Editing in Vision and Language Modules of Multimodal Models Jin Seong, Han-Woong Ryu 한국인공지능학회 학술 대회 (추계) 2024, pp.1-6 | ||
Conference
|
2023 | High-Quality Multimodal Dataset Construction Methodology for ChatGPT-Based Korean Vision-Language Pre-training 성진, 한승헌 한글 및 한국어 정보처리 학술 대회 2023, pp.603-608 | ||
Conference
|
2023 | Towards Korean-Centric Token-free Pretrained Language Model 신종훈 한글 및 한국어 정보처리 학술 대회 2023, pp.711-715 | ||
Journal
|
2023 | Online and real-time mask-guided multi-person tracking and segmentation Jin Seong Pattern Recognition Letters, v.172, pp.144-150 | 0 |