IIIT5k

Dataset Information
Modalities
Images
License
Unknown
Homepage

Overview

The IIIT5K dataset contains 5,000 text instance images: 2,000 for training and 3,000 for testing. It contains words from street scenes and from originally-digital images. Every image is associated with a 50 -word lexicon and a 1,000 -word lexicon.

Variants: IIIT5k

Associated Benchmarks

This dataset is used in 1 benchmark:

Recent Benchmark Submissions

Task Model Paper Date
Scene Text Recognition DTrOCR 105M DTrOCR: Decoder-only Transformer for Optical … 2023-08-30
Scene Text Recognition CPPD Context Perception Parallel Decoder for … 2023-07-23
Scene Text Recognition DiffusionSTR DiffusionSTR: Diffusion Model for Scene … 2023-06-29
Scene Text Recognition CLIP4STR-B CLIP4STR: A Simple Baseline for … 2023-05-23
Scene Text Recognition CLIP4STR-B (DataComp-1B) CLIP4STR: A Simple Baseline for … 2023-05-23
Scene Text Recognition CLIP4STR-L CLIP4STR: A Simple Baseline for … 2023-05-23
Scene Text Recognition CLIP4STR-L (DataComp-1B) CLIP4STR: A Simple Baseline for … 2023-05-23
Scene Text Recognition CCD-ViT-Small(ARD_2.8M) Self-supervised Character-to-Character Distillation for Text … 2022-11-01
Scene Text Recognition CCD-ViT-Base(ARD_2.8M) Self-supervised Character-to-Character Distillation for Text … 2022-11-01
Scene Text Recognition CCD-ViT-Tiny(ARD_2.8M) Self-supervised Character-to-Character Distillation for Text … 2022-11-01
Scene Text Recognition MGP-STR Multi-Granularity Prediction for Scene Text … 2022-09-08
Scene Text Recognition PARSeq Scene Text Recognition with Permuted … 2022-07-14
Scene Text Recognition SIGA_S Self-supervised Implicit Glyph Attention for … 2022-03-07
Scene Text Recognition S-GTR Visual Semantics Allow for Textual … 2021-12-24
Scene Text Recognition MATRN Multi-modal Text Recognition Networks: Interactive … 2021-11-30
Scene Text Recognition CDistNet (Ours) CDistNet: Perceiving Multi-Domain Character Distance … 2021-11-22

Research Papers

Recent papers with results on this dataset: