Open Vocabulary Word Recognition From Transcribed Bangla Texts

arXiv:2610.01134 · cs.CV, cs.LG · Submitted 2026-10-01 · Read on arXiv

cs.CV, cs.LG

Submitted: 2026-10-01

Updated: 2026-10-02

Code: https://github.com/tensorflow/models

Terminology

• Accuracy — 16× in this paper · explained in 1 episode
• Non-Maximum Suppression — 6× in this paper
• Benchmark — 3× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Deep Convolutional Neural Network — 2× in this paper
• Preserving Necessary Overlap — 2× in this paper
• Single Shot MultiBox Detector — 2× in this paper
• Ensemble Approach — 1× in this paper · explained in 3 episodes
• F1 Score — 1× in this paper · explained in 3 episodes
• False Positive — 1× in this paper
• International Conference on Computer and Information Technology — 1× in this paper
• Overlap Value — 1× in this paper
• True Positive — 1× in this paper

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models