Research map / Vision-language and multimodal / Human and embodied modeling
Reading Scene Text in Deep Convolutional Sequences
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add bidirectional LSTM+CTC over CNN sequence instead of isolated character classification | Maxout CNN (DeepFeatures) · SVT-50 | accuracy: 86.1 -> 93.5 | Helped |
| DTRN vs PhotoOCR with far less training data | scene text recognition · SVT-50 | accuracy: 90.4 -> 93.5 | Helped |
| add more LSTM layers (ablation) | DTRN · scene text benchmarks | accuracy | No clear effect |
| DTRN vs Jaderberg2015b dictionary classifier | scene text recognition · IIIT5k-1K | accuracy: 92.7 vs 91.5 | Hurt |
Closest papers by meaning
- Recursive Recurrent Nets With Attention Modeling for OCR in the Wild (CVPR 2016 · similarity 0.89)
- Scene Text Recognition from Two-Dimensional Perspective (AAAI 2019 · similarity 0.88)
- SqueezedText: A Real-Time Scene Text Recognition by Binary Convolutional Encoder-Decoder Network (AAAI 2018 · similarity 0.88)
- Convolutional Sequence to Sequence Learning (ICML 2017 · similarity 0.87)
- Deep Structured Scene Parsing by Learning With Image Descriptions (CVPR 2016 · similarity 0.87)
- OTE: Exploring Accurate Scene Text Recognition Using One Token (CVPR 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.