3 papers
cs.CV2026
Towards Training-Free Scene Text Editing
Yubo Li, Xugong Qin, Peng Zhang +3
Scene text editing seeks to modify textual content in natural images while maintaining visual realism and semantic consistency. Existing methods often require task-specific trainin…
cs.CV2025
Towards Natural Language-Based Document Image Retrieval: New Dataset and Benchmark
Hao Guo, Xugong Qin, Jun Jie Ou Yang +4
Document image retrieval (DIR) aims to retrieve document images from a gallery according to a given query. Existing DIR methods are primarily based on image queries that retrieve d…
cs.CV2024
Focus, Distinguish, and Prompt: Unleashing CLIP for Efficient and Flexible Scene Text Retrieval
Gangyan Zeng, Yuan Zhang, Jin Wei +5
Scene text retrieval aims to find all images containing the query text from an image gallery. Current efforts tend to adopt an Optical Character Recognition (OCR) pipeline, which r…