4 papers
Towards Vision-Free CIR: Attribute-Augmented Scoring and LLM-Based Reranking for Zero-Shot Composed Image Retrieval
Ryotaro Shimada, Yu-Chieh Lin, Yuji Nozawa +3
Recent work has shown that "Vision-Free'' approaches (representing images as text) can be effective for standard image retrieval tasks. However, it remains unclear whether this par…
CIRCLED: A Multi-turn CIR Dataset with Consistent Dialogues across Domains
Tomohisa Takeda, Yu-Chieh Lin, Yuji Nozawa +3
Existing Multi-Turn Composed Image Retrieval (MTCIR) datasets lack dialogue-historyconsistency and are restricted to the fashion domain. To address these limitations, we construct…
SVGEditBench V2: A Benchmark for Instruction-based SVG Editing
Kunato Nishina, Yusuke Matsui
Vector format has been popular for representing icons and sketches. It has also been famous for design purposes. Regarding image editing, research on vector graphics editing rarely…
SVGEditBench: A Benchmark Dataset for Quantitative Assessment of LLM's SVG Editing Capabilities
Kunato Nishina, Yusuke Matsui
Text-to-image models have shown progress in recent years. Along with this progress, generating vector graphics from text has also advanced. SVG is a popular format for vector graph…