Papers Text Spotting
“Text Spotting” 태그가 달린 논문 125편 · 필터 해제
One Patch Is Enough: Reinforcement-Optimized Visual Token Grounding for MLLM-Based Scene Text Spotting
Scene text spotting requires high-precision alignment between textual recognition and spatial localization. While visual-token grounding has emerged as a promising formulation for Multimodal Large Language Models (MLLMs)…
Reinforcement LearningText SpottingHunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better
We present HunyuanOCR-1.5, a lightweight end-to-end OCR-specialized vision-language model. HunyuanOCR unifies document parsing, text spotting, information extraction, text-image translation, and multi-image document unde…
Information ExtractionText SpottingTraRA: Trajectory-level Recognition Aggregation for Video Text Spotting in Urban Surveillance
Video Text Spotting (VTS) is essential for urban surveillance and intelligent transportation systems, enabling automated reading of street signs, vehicle markings, and scene text in video streams. However, reliable recog…
Text SpottingFrom Recognition to Reasoning: Benchmarking and Enhancing MLLMs on Real-World Receipt Document Understanding
Extracting structured information from visual documents (Visual Information Extraction, VIE) is a cornerstone of business automation. While recent Multimodal Large Language Models (MLLMs) have shown promising capabilitie…
Reinforcement LearningInformation ExtractionText SpottingDo You Need Text Rectification? Soft Attention Mask Embedding for Rectification-Free Scene Text Spotting
End-to-end scene text spotting, which unifies text detection and recognition within a single framework, has witnessed remarkable progress driven by deep learning advances. However, most existing approaches still suffer f…
Text DetectionText SpottingBeyond Detection: A Structure-Aware Framework for Scene Text Tracking
Modern visual object trackers show impressive results on general targets, yet their performance drops substantially when dealing with scene text. Although currently underexplored, tracking text in videos is essential for…
Text SpottingPositionOCR: Augmenting Positional Awareness in Multi-Modal Models via Hybrid Specialist Integration
In recent years, Multi-modal Large Language Models (MLLMs) have achieved strong performance in OCR-centric Visual Question Answering (VQA) tasks, illustrating their capability to process heterogeneous data and exhibit ad…
Visual Question AnsweringText SpottingTiCLS : Tightly Coupled Language Text Spotter
Scene text spotting aims to detect and recognize text in real-world images, where instances are often short, fragmented, or visually ambiguous. Existing methods primarily rely on visual cues and implicitly capture local …
Text SpottingPaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing
We introduce PaddleOCR-VL-1.5, an upgraded model achieving a new state-of-the-art (SOTA) accuracy of 94.5% on OmniDocBench v1.5. To rigorously evaluate robustness against real-world physical distortions, including scanni…
Text SpottingUnified Diffusion Transformer for High-fidelity Text-Aware Image Restoration
Text-Aware Image Restoration (TAIR) aims to recover high-quality images from low-quality inputs containing degraded textual content. While diffusion models provide strong generative priors for general image restoration, …
Image RestorationText SpottingHunyuanOCR Technical Report
This paper presents HunyuanOCR, a commercial-grade, open-source, and lightweight (1B parameters) Vision-Language Model (VLM) dedicated to OCR tasks. The architecture comprises a Native Vision Transformer (ViT) and a ligh…
Reinforcement LearningText SpottingLRANet++: Low-Rank Approximation Network for Accurate and Efficient Text Spotting
End-to-end text spotting aims to jointly optimize text detection and recognition within a unified framework. Despite significant progress, designing an accurate and efficient end-to-end text spotter for arbitrary-shaped …
Text DetectionText SpottingText-VQA Aug: Pipelined Harnessing of Large Multimodal Models for Automated Synthesis
Creation of large-scale databases for Visual Question Answering tasks pertaining to the text data in a scene (text-VQA) involves skilful human annotation, which is tedious and challenging. With the advent of foundation m…
Visual Question AnsweringQuestion GenerationText SpottingText-Aware Image Restoration with Diffusion Models
Image restoration aims to recover degraded images. However, existing diffusion-based restoration methods, despite great success in natural image restoration, often struggle to faithfully reconstruct textual regions in de…
DenoisingHallucinationImage RestorationText SpottingGoMatching++: Parameter- and Data-Efficient Arbitrary-Shaped Video Text Spotting and Benchmarking
Video text spotting (VTS) extends image text spotting (ITS) by adding text tracking, significantly increasing task complexity. Despite progress in VTS, existing methods still fall short of the performance seen in ITS. Th…
BenchmarkingText SpottingSemiETS: Integrating Spatial and Content Consistencies for Semi-Supervised End-to-end Text Spotting
Most previous scene text spotting methods rely on high-quality manual annotations to achieve promising performance. To reduce their expensive costs, we study semi-supervised text spotting (SSTS) to exploit useful informa…
Domain AdaptationText DetectionText SpottingTextInPlace: Indoor Visual Place Recognition in Repetitive Structures with Scene Text Spotting and Verification
Visual Place Recognition (VPR) is a crucial capability for long-term autonomous robots, enabling them to identify previously visited locations using visual information. However, existing methods remain limited in indoor …
Robot NavigationSTStext similarityText Spotting+1OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models
Visually-situated text parsing (VsTP) has recently seen notable advancements, driven by the growing demand for automated document understanding and the emergence of large language models capable of processing document-ba…
document understandingKey Information ExtractionLarge Language ModelMultimodal Large Language Model+2CLIP is Almost All You Need: Towards Parameter-Efficient Scene Text Retrieval without OCR
Scene Text Retrieval (STR) seeks to identify all images containing a given query string. Existing methods typically rely on an explicit Optical Character Recognition (OCR) process of text spotting or localization, wh…
AllOptical Character RecognitionOptical Character Recognition (OCR)Reranking+3Hear the Scene: Audio-Enhanced Text Spotting
Recent advancements in scene text spotting have focused on end-to-end methodologies that heavily rely on precise location annotations, which are often costly and labor-intensive to procure. In this study, we introduce an…
Text Spotting