Papers with Code 아카이브
Text Spotting
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 4
- 보존된 평가 기록
- 50
Scene Text Spotting is the combination of Scene Text Detection and Scene Text Recognition in an end-to-end manner. It is the ability to read natural text in the wild.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
GoMatching++: Parameter- and Data-Efficient Arbitrary-Shaped Video Text Spotting and Benchmarking
SemiETS: Integrating Spatial and Content Consistencies for Semi-Supervised End-to-end Text Spotting
TextInPlace: Indoor Visual Place Recognition in Repetitive Structures with Scene Text Spotting and Verification
OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models
Hear the Scene: Audio-Enhanced Text Spotting
InstructOCR: Instruction Boosting Scene Text Spotting
Arbitrary Reading Order Scene Text Spotter with Local Semantics Guidance
HIP: Hierarchical Point Modeling and Pre-training for Visual Information Extraction
FastTextSpotter: A High-Efficiency Transformer for Multilingual Scene Text Spotting
DNTextSpotter: Arbitrary-Shaped Scene Text Spotting via Improved Denoising Training
WeCromCL: Weakly Supervised Cross-Modality Contrastive Learning for Transcription-only Supervised Text Spotting
CLII: Visual-Text Inpainting via Cross-Modal Predictive Interaction
Block-level Text Spotting with LLMs
LOGO: Video Text Spotting with Language Collaboration and Glyph Perception Model
VimTS: A Unified Video and Image Text Spotter for Enhancing the Cross-domain Generalization
Mixed Text Recognition with Efficient Parameter Fine-Tuning and Transformer
Bridging the Gap Between End-to-End and Two-Step Text Spotting
Ensemble Learning for Vietnamese Scene Text Spotting in Urban Environments
OmniParser: A Unified Framework for Text Spotting, Key Information Extraction and Table Recognition
TextBlockV2: Towards Precise-Detection-Free Scene Text Spotting with Pre-trained Language Model
TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document
Efficiently Leveraging Linguistic Priors for Scene Text Spotting
Beyond the Mud: Datasets and Benchmarks for Computer Vision in Off-Road Racing
SwinTextSpotter v2: Towards Better Synergy for Scene Text Spotting
GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matching
Watermark Text Pattern Spotting in Document Images
Inverse-like Antagonistic Scene Text Spotting via Reading-Order Estimation and Dynamic Sampling
GloTSFormer: Global Video Text Spotting Transformer
Word length-aware text spotting: Enhancing detection and recognition in dense text image
Parrot Captions Teach CLIP to Spot Text
Hierarchical Text Spotter for Joint Text Spotting and Layout Analysis
Harnessing the Power of Multi-Lingual Datasets for Pre-training: Towards Enhancing Text Spotting Performance
Diving into the Depths of Spotting Text in Multi-Domain Noisy Scenes
STEP -- Towards Structured Scene-Text Spotting
Attention Where It Matters: Rethinking Visual Document Understanding with Selective Region Concentration
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.