all AI news
ANCHOR: LLM-driven News Subject Conditioning for Text-to-Image Synthesis
April 17, 2024, 4:46 a.m. | Aashish Anantha Ramakrishnan, Sharon X. Huang, Dongwon Lee
cs.CL updates on arXiv.org arxiv.org
Abstract: Text-to-Image (T2I) Synthesis has made tremendous strides in enhancing synthesized image quality, but current datasets evaluate model performance only on descriptive, instruction-based prompts. Real-world news image captions take a more pragmatic approach, providing high-level situational and Named-Entity (NE) information and limited physical object descriptions, making them abstractive. To evaluate the ability of T2I models to capture intended subjects from news captions, we introduce the Abstractive News Captions with High-level cOntext Representation (ANCHOR) dataset, containing 70K+ …
abstract anchor arxiv captions cs.cl cs.cv cs.mm current datasets image information llm making object performance prompts quality synthesis synthesized text text-to-image them type world world news
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Business Intelligence Manager
@ Sanofi | Budapest
Principal Engineer, Data (Hybrid)
@ Homebase | Toronto, Ontario, Canada