ICDAR2017 Robust Reading Challenge on Multi-Lingual Scene Text Detection and Script Identification - RRC-MLT

By Nibal Nayef, Fei Yin, Imen Bizid, Hyunsoo Choi, Yuan Feng, Dimosthenis Karatzas, Zhenbo Luo, Umapada Pal, Christophe Rigaud, J. Chazalon and 5 more. IEEE International Conference on Document Analysis and Recognition, 2017

417 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/d899525e35ef784afd2aeeac977d7bb361fd7092

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Cong Yao
2. Fahad Shahbaz Khan
3. Xiang Bai
4. Minghui Liao
5. Junchi Yan
6. Xue Yang
7. Qi Tian
8. Chenglin Liu

In Computer Vision and Pattern Recognition

1. Xiang Bai
2. Cong Yao
3. Chunhua Shen
4. Qi Tian
5. Luc Van Gool
6. Dacheng Tao
7. Ming-Hsuan Yang
8. Fahad Shahbaz Khan

In Media Technology

1. Cong Yao
2. Xiang Bai
3. Minghui Liao
4. Pengyuan Lyu
5. Chenglin Liu
6. Chengquan Zhang
7. Xue Yang
8. Junchi Yan

Citations in the corpus

• Learning High-Precision Bounding Box for Rotated Object Detection via Kullback-Leibler Divergence (2021, background): “ICDAR2017 MLT is a multi-lingual text dataset, which includes 7,200 training images, 1,800 validation images and 9,000 testing images.”
• Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes (2019, methodology): “The ICDAR2017-MLT [26] is a large scale multi-lingual text dataset, which includes 7200 training images, 1800 validation images and 9000 test images.”
• Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes (2018, methodology): “MLT [54] is a multi-language scene text dataset proposed in ICDAR 2017.”
• Character Region Awareness for Text Detection (2019, methodology): “We demonstrate extensive experiments on ICDAR datasets [15, 14, 28] to validate our method, and the experi-1 ments show that the proposed method outperforms state-of-the-art text detectors.”
• DeepSeek-VL: Towards Real-World Vision-Language Understanding (2024, neutral): “ArT (Chng et al., 2019) 1.2% MLT-17 (Nayef et al., 2017) LSVT (Sun et al., 2019) UberText (Zhang et al., 2017) Coco-text (Veit et al., 2016) RCTW-17 (Shi et al., 2017) ReCTS (Zhang et al., 2019) TextOCR (Singh et al., 2021) OpenVINO (Krylov et al., 2021) HierText (Long et al., 2022) Document OCR…”
• Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss (2021, background): “ICDAR 2017 MLT [38] is a multi-lingual text dataset, which includes 7,200 training images, 1,800 validation images and 9,000 testing images.”
• Dense Label Encoding for Boundary Discontinuity Free Rotation Detection (2020, background): “Extensive experiments and visual analysis on large-scale public datasets for aerial images i.e. DOTA, UCAS-AOD, HRSC2016, as well as scene text dataset ICDAR2015 and MLT, show the effectiveness of our approach.”
• TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text (2021, methodology): “Prior to TextOCR, many OCR datasets exist [38, 59, 35, 24, 23, 45, 48, 8, 61, 34, 57, 41, 50, 40, 9, 54] that propelled the field’s development, but many of these are either relatively small, or focus mostly on outdoor or store-front scenes.”
• Transformers in Remote Sensing: A Survey (2022, methodology): “RBox [42] Detection SynthText [89], ICDAR 2015 (IC15) [90], MLT-2017 (MLT17) [91], MSRA-TD500 [92], MTWI [93], Total-Text [94], CTW1500 [95] mAP Proposes a framework employing transformers to model the relationship of sampled features for better grouping and box prediction without requiring post-pro”
• Visual Semantics Allow for Textual Reasoning Better in Scene Text Recognition (2021, positive): “As shown in Table 6, S-GTR outperforms other methods sig-nificantly on the multi-language dataset MLT-2017 (Nayef et al. 2017).”
• Total-Text: toward orientation robustness in scene text detection (2019, methodology): “[19] introduced theMLT dataset, which is one of the latest multi script datasets collected for scene text detection, recognition, and script identification task.”
• Arbitrary-Oriented Object Detection with Circular Smooth Label (2020, background): “ICDAR 2017 MLT [28] is a multi-lingual text dataset, which includes 7,200 training images, 1,800 validation images and 9,000 testing images.”