Dataset from Papers With Code
82 results indexed across 6 metrics. Shaded row marks current SOTA; ties broken by submission date.
| # | Model | Org | Submitted | Paper / code | f-measure-full-lexicon |
|---|---|---|---|---|---|
| 01 | SPTS | — | Dec 2021 | SPTS: Single-Point Text Spotting · code | 83.80 |
| 02 | A3S | — | Feb 2023 | A3S: Adversarial learning of semantic representations fo… | 82.30 |
| 03 | TESTR | — | Apr 2022 | Text Spotting Transformers · code | 81.50 |
| 04 | DeepSolo (ResNet-50) | — | May 2023 | DeepSolo++: Let Transformer Decoder with Explicit Points… · code | 81.40 |
| 05 | ABINet++ | — | Nov 2022 | ABINet++: Autonomous, Bidirectional and Iterative Langua… · code | 80.30 |
| 06 | TPSNet | — | Oct 2021 | TPSNet: Reverse Thinking of Thin Plate Splines for Arbit… · code | 79.20 |
| 07 | MANGO | — | Dec 2020 | MANGO: A Mask Attention Guided One-Stage Scene Text Spot… · code | 78.70 |
| 08 | ABCNet v2 | — | May 2021 | ABCNet v2: Adaptive Bezier-Curve Network for Real-time E… · code | 77.20 |
| 09 | SwinTextSpotter | — | Mar 2022 | SwinTextSpotter: Scene Text Spotting via Better Synergy … · code | 77 |
| 10 | TextDragon | — | Oct 2019 | papers-with-code | 72.40 |
| # | Model | Org | Submitted | Paper / code | f-measure-no-lexicon |
|---|---|---|---|---|---|
| 01 | A3S | — | Feb 2023 | A3S: Adversarial learning of semantic representations fo… | 64.40 |
| 02 | DeepSolo (ResNet-50) | — | May 2023 | DeepSolo++: Let Transformer Decoder with Explicit Points… · code | 64.20 |
| 03 | SPTS | — | Dec 2021 | SPTS: Single-Point Text Spotting · code | 63.60 |
| 04 | ABINet++ | — | Nov 2022 | ABINet++: Autonomous, Bidirectional and Iterative Langua… · code | 60.20 |
| 05 | TPSNet | — | Oct 2021 | TPSNet: Reverse Thinking of Thin Plate Splines for Arbit… · code | 59.70 |
| 06 | MANGO | — | Dec 2020 | MANGO: A Mask Attention Guided One-Stage Scene Text Spot… · code | 58.90 |
| 07 | ABCNet v2 | — | May 2021 | ABCNet v2: Adaptive Bezier-Curve Network for Real-time E… · code | 57.50 |
| 08 | TextPerceptron | — | Feb 2020 | Text Perceptron: Towards End-to-End Arbitrary-Shaped Tex… · code | 57 |
| 09 | TESTR | — | Apr 2022 | Text Spotting Transformers · code | 56 |
| 10 | SwinTextSpotter | — | Mar 2022 | SwinTextSpotter: Scene Text Spotting via Better Synergy … · code | 51.80 |
| 11 | TextDragon | — | Oct 2019 | papers-with-code | 39.70 |
| # | Model | Org | Submitted | Paper / code | fps |
|---|---|---|---|---|---|
| 01 | FAST-T-512 | — | Nov 2021 | FAST: Faster Arbitrarily-Shaped Text Detector with Minim… · code | 129.10 |
| 02 | FAST-S-512 | — | Nov 2021 | FAST: Faster Arbitrarily-Shaped Text Detector with Minim… · code | 112.90 |
| 03 | FAST-B-512 | — | Nov 2021 | FAST: Faster Arbitrarily-Shaped Text Detector with Minim… · code | 92.60 |
| 04 | FAST-B-640 | — | Nov 2021 | FAST: Faster Arbitrarily-Shaped Text Detector with Minim… · code | 66.50 |
| 05 | PAN | — | Nov 2018 | Mask R-CNN with Pyramid Attention Network for Scene Text… | 65.20 |
| 06 | MixNet | — | Aug 2023 | MixNet: Toward Accurate Detection of Challenging Scene T… · code | 15.20 |
Every paper below corresponds to at least one row in the leaderboard above. Click through for the arXiv preprint and, when available, the reference implementation.
Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.