Tobacco-3482

Dataset Information
License
Unknown
Contents

Overview

The Tobacco-3482 dataset consists of document images belonging to 10 classes such as letter, form, email, resume, memo, etc. The dataset has 3482 images.

Variants: Tobacco-3482

Associated Benchmarks

This dataset is used in 2 benchmarks:

Recent Benchmark Submissions

Task Model Paper Date
Document Image Classification Multimodal Side-Tuning (ResNet50) Multimodal Side-Tuning for Document Classification 2023-01-16
Document Image Classification Multimodal Side-Tuning (MobileNetV2) Multimodal Side-Tuning for Document Classification 2023-01-16
Document Image Classification DocBERT [DOCBERT] Efficient Document Image Classification Using … 2021-06-25
Document Image Classification BERT [BERT] Efficient Document Image Classification Using … 2021-06-25
Document Image Classification Eff-GNN + Word2Vec [word2vec] + Image Embedding Efficient Document Image Classification Using … 2021-06-25
Document Image Classification Eff-GNN+ Word2Vec [word2vec] Efficient Document Image Classification Using … 2021-06-25
Document Image Classification VGG Efficient Document Image Classification Using … 2021-06-25
Document Image Classification DocBert [DOCBERT] Efficient Document Image Classification Using … 2021-06-25
Document Image Classification Eff-GNN + Word2Vec [word2vec] Efficient Document Image Classification Using … 2021-06-25
Document Text Classification Optimized Text CNN Light-Weighted CNN for Text Classification 2020-04-16
Document Text Classification Lightweight TextCNN with Dual Optimizer Light-Weighted CNN for Text Classification 2020-04-16
Document Text Classification Lightweight Text CNN Light-Weighted CNN for Text Classification 2020-04-16

Research Papers

Recent papers with results on this dataset:

External Links: