Cover Image

A Lightweight Context-Driven Training-Free Network for Scene Text Segmentation and Recognition

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chakraborty, Ritabrata, Palaiahnakote, Shivakumara, Pal, Umapada, Liu, Cheng-Lin
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Transformer Based Handwriting Recognition System Jointly Using Online and Offline Features
by: Lodh, Ayush, et al.
Published: (2025)

Towards Robust Cross-Dataset Object Detection Generalization under Domain Specificity
by: Chakraborty, Ritabrata, et al.
Published: (2026)

TruthLens:A Training-Free Paradigm for DeepFake Detection
by: Chakraborty, Ritabrata, et al.
Published: (2025)

See in Depth: Training-Free Surgical Scene Segmentation with Monocular Depth Priors
by: Yang, Kunyi, et al.
Published: (2025)

Mask & Match: Learning to Recognize Handwritten Math with Self-Supervised Attention
by: Mitra, Shree, et al.
Published: (2025)

CAMBench-QR : A Structure-Aware Benchmark for Post-Hoc Explanations with QR Understanding
by: Chakraborty, Ritabrata, et al.
Published: (2025)

Conformal uncertainty quantification to evaluate predictive fairness of foundation AI model for skin lesion classes across patient demographics
by: Bhattacharyya, Swarnava, et al.
Published: (2025)

Dynamic-eDiTor: Training-Free Text-Driven 4D Scene Editing with Multimodal Diffusion Transformer
by: Lee, Dong In, et al.
Published: (2025)

UR2P-Dehaze: Learning a Simple Image Dehaze Enhancer via Unpaired Rich Physical Prior
by: Xue, Minglong, et al.
Published: (2025)

Zero-Shot Low-Light Image Enhancement via Joint Frequency Domain Priors Guided Diffusion
by: He, Jinhong, et al.
Published: (2024)

Unified Image Restoration and Enhancement: Degradation Calibrated Cycle Reconstruction Diffusion Model
by: Xue, Minglong, et al.
Published: (2024)

DFDNet: Dynamic Frequency-Guided De-Flare Network
by: Xue, Minglong, et al.
Published: (2025)

Unleashing Hierarchical Reasoning: An LLM-Driven Framework for Training-Free Referring Video Object Segmentation
by: Zhao, Bingrui, et al.
Published: (2025)

STEFANN: Scene Text Editor using Font Adaptive Neural Network
by: Roy, Prasun, et al.
Published: (2019)

Staircase Cascaded Fusion of Lightweight Local Pattern Recognition and Long-Range Dependencies for Structural Crack Segmentation
by: Liu, Hui, et al.
Published: (2024)

Do We Need Large VLMs for Spotting Soccer Actions?
by: Chakraborty, Ritabrata, et al.
Published: (2025)

GeoSeg: Training-Free Reasoning-Driven Segmentation in Remote Sensing Imagery
by: Jiang, Lifan, et al.
Published: (2026)

Diving into the Depths of Spotting Text in Multi-Domain Noisy Scenes
by: Das, Alloy, et al.
Published: (2023)

TSTMotion: Training-free Scene-aware Text-to-motion Generation
by: Guo, Ziyan, et al.
Published: (2025)

LAPX: Lightweight Hourglass Network with Global Context
by: Zhao, Haopeng, et al.
Published: (2025)

360PanT: Training-Free Text-Driven 360-Degree Panorama-to-Panorama Translation
by: Wang, Hai, et al.
Published: (2024)

3D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation
by: Zhang, Frank, et al.
Published: (2024)

DreamText: High Fidelity Scene Text Synthesis
by: Wang, Yibin, et al.
Published: (2024)

EventSTR: A Benchmark Dataset and Baselines for Event Stream based Scene Text Recognition
by: Wang, Xiao, et al.
Published: (2025)

Pathology Context Recalibration Network for Ocular Disease Recognition
by: Xiao, Zunjie, et al.
Published: (2025)

FastTextSpotter: A High-Efficiency Transformer for Multilingual Scene Text Spotting
by: Das, Alloy, et al.
Published: (2024)

ECMNet:Lightweight Semantic Segmentation with Efficient CNN-Mamba Network
by: Du, Feixiang, et al.
Published: (2025)

LatentEditor: Text Driven Local Editing of 3D Scenes
by: Khalid, Umar, et al.
Published: (2023)

Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis
by: Hu, Taihang, et al.
Published: (2024)

Lightweight Multimodal Artificial Intelligence Framework for Maritime Multi-Scene Recognition
by: Xi, Xinyu, et al.
Published: (2025)

OTSNet: A Neurocognitive-Inspired Observation-Thinking-Spelling Pipeline for Scene Text Recognition
by: Sun, Lixu, et al.
Published: (2025)

Adversarial Training with OCR Modality Perturbation for Scene-Text Visual Question Answering
by: Shen, Zhixuan, et al.
Published: (2024)

Depth Map Denoising Network and Lightweight Fusion Network for Enhanced 3D Face Recognition
by: Xu, Ruizhuo, et al.
Published: (2024)

Training-Free Global Geometric Association for 4D LiDAR Panoptic Segmentation
by: Oh, Gyeongrok, et al.
Published: (2025)

DRScaffold: Boosting Dense-Scene Reasoning in Lightweight Vision Language Models
by: Shi, Xinrui, et al.
Published: (2026)

An End-to-End, Segmentation-Free, Arabic Handwritten Recognition Model on KHATT
by: Aabed, Sondos, et al.
Published: (2024)

Leveraging Text-Driven Semantic Variation for Robust OOD Segmentation
by: Song, Seungheon, et al.
Published: (2025)

Lightweight Multimodal Adaptation of Vision Language Models for Species Recognition and Habitat Context Interpretation in Drone Thermal Imagery
by: Chen, Hao, et al.
Published: (2026)

RASA: Replace Anyone, Say Anything -- A Training-Free Framework for Audio-Driven and Universal Portrait Video Editing
by: Pan, Tianrui, et al.
Published: (2025)

DNTextSpotter: Arbitrary-Shaped Scene Text Spotting via Improved Denoising Training
by: Xie, Yu, et al.
Published: (2024)