연구물
21건 검색
- 연구출판물 · 학술대회 발표논문Zero-shot Building Attribute Extraction from Large-Scale Vision and Language Models
Pan, Fei전상률Wang, BrianMcKenna, FrankYu, Stella X.
Source Proceedings - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 20242024피인용 10등재 Scopus - 연구출판물 · 학술지 논문JCR Q2Scopus Q1Unsupervised Knowledge Distillation via Local Representations for Vision-Language Models
- 연구출판물 · 학술지 논문JCR Q2Scopus Q1A Robust Framework for Coffee Bean Package Label Recognition: Integrating Image Enhancement with Vision-Language OCR Models
- 연구출판물 · 학술지 논문JCR Q1Scopus Q2Integrating Large Language Models with Deep Learning for Breast Cancer Treatment Decision Support
- 연구출판물 · 학술지 논문Decision-informed neural network with large language model integration for portfolio optimization
황윤태Kong, YaxuanZohren, StefanLee, Yongjae
- 연구출판물 · 학술지 논문JCR Q1Scopus Q1Target-Aware Change Detection for Efficient VLM Gating in Mobile Robots
- 연구출판물 · 학술지 논문JCR Q2Scopus Q1Stimulus-Design Confounds in Progressive Rendered 3-D VLM Evaluation
- 연구출판물 · 학술지 논문KCI Q1CV-VLM 캐스케이드 기반 생성형 AI 슬라이드 이미지의 편집 가능 문서 복원 기술
CV-VLM Cascade-based Reconstruction of Editable Documents from Generative AI Slide Images
- 연구출판물 · 학술대회 발표논문Visual Reasoning for Construction Safety Monitoring
강경남Lee, JeonghoonLee, JeeheeKim, HyunsooPark, Hyunjung전정호
Source International Conference on Construction Engineering and Project Management2025피인용 0등재 Scopus - 연구출판물 · 학술지 논문KCI Q4비전-언어모델의 내부 표현 해석을 통한 추가 학습 없는 영역 단위의 장면 이해 기법
Training-Free Region-Level Semantic Understanding via Interpreting Internal Representations of Vision-Language Models
- 연구출판물 · 학술대회 발표논문Scopus Q33DZip: Spatial-Aware Feature Diversity-Guided Token Compression for 3D Question Answering
- 연구출판물 · 학술지 논문KCI Q1멀티모달 LLM에서의 비전 인코더 계층별 엔트로피 변화를 활용한 시각 토큰 프루닝
Visual Token Pruning Based on Entropy Dynamics in Vision Encoders of Multimodal LLMs
- 연구출판물 · 학술대회 발표논문Enhancing Contextual Understanding with Multimodal Siamese Networks Using Contrastive Loss and Text Embeddings
- 연구출판물 · 학술지 논문KCI Q3부위별 의미적 속성을 이용한 키포인트 기반 개인 재식별
Keypoint-based Re-identification with Part-level Semantic Attributes
- 연구출판물 · 학술지 논문JCR Q1Scopus Q1HCP A multimodal generative AI copilot for human pathology
- 연구출판물 · 학술지 논문JCR Q1Scopus Q1AT-adapter: Leveraging attribute knowledge of CLIP for few-shot classification
- 연구출판물 · 학술지 논문JCR Q1Scopus Q1HP A multimodal whole-slide foundation model for pathology
Ding, TongWagner, Sophia J.Song, Andrew H.Chen, Richard J.Lu, Ming Y.김아롱외 23명
- 연구출판물 · 학술지 논문JCR Q2Scopus Q1Image clustering using generated text centroids
Kong, Daehyeon공경보Kang, Suk-Ju
- 연구출판물 · 학술대회 발표논문Human Motion Aware Text-to-Video Generation with Explicit Camera Control
Kim, TaehoonKang, ChanheePark, JaehyukJeong, DaunYang, Changhee공경보외 1명
Source Proceedings - 2024 IEEE Winter Conference on Applications of Computer Vision, WACV 20242024피인용 5등재 Scopus - 연구출판물 · 학술대회 발표논문BAC-GCN: Background-Aware CLIP-GCN Framework for Unsupervised Multi-Label Classification



로그인
홈
Researcher Page
ORCID
ISNI