StyleBabel: Artistic Style Tagging and Captioning
원문 초록
We present StyleBabel, a unique open access dataset of natural language captions and free-form tags describing the artistic style of over 135K digital artworks, collected via a novel participatory method from experts studying at specialist art and design schools. StyleBabel was collected via an iterative method, inspired by `Grounded Theory': a qualitative approach that enables annotation while co-evolving a shared language for fine-grained artistic style attribute description. We demonstrate several downstream tasks for StyleBabel, adapting the recent ALADIN architecture for fine-grained style similarity, to train cross-modal embeddings for: 1) free-form tag generation; 2) natural language description of artistic style; 3) fine-grained text search of style. To do so, we extend ALADIN with recent advances in Visual Transformer (ViT) and cross-modal representation learning, achieving a state of the art accuracy in fine-grained style retrieval.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model
Language-Guided Contrastive Audio-Visual Masked Autoencoder with Automatically Generated Audio-Visual-Text Triplets from Videos
An analysis of vision-language models for fabric retrieval
Controlled Retrieval-augmented Context Evaluation for Long-form RAG
H-QuEST: Accelerating Query-by-Example Spoken Term Detection with Hierarchical Indexing
DisProtEdit: Exploring Disentangled Representations for Multi-Attribute Protein Editing
토론
이 논문과 연결된 포럼 글이 아직 없습니다.