DeepDeSRT: Deep Learning for Detection and Structure Recognition of Tables in Document Images

By Sebastian Schreiber, Stefan Agne, Ivo Wolf, Andreas R. Dengel, Sheraz Ahmed. IEEE International Conference on Document Analysis and Recognition, 2017

365 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/f8bead3ae810cd3f7427d3004e45b4158da9b744

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. Furu Wei
2. Shaohan Huang
3. Ming Zhou
4. Lei Cui
5. Minghao Li
6. Antonio Jimeno-Yepes
7. Raghavan Manmatha
8. Xu Zhong

In Computer Vision and Pattern Recognition

1. Furu Wei
2. Lei Cui
3. Shaohan Huang
4. Ming Zhou
5. Raghavan Manmatha
6. Minghao Li
7. Antonio Jimeno-Yepes
8. Xu Zhong

Citations in the corpus

• DocFormer: End-to-End Transformer for Document Understanding (2021, background): “Document understanding methods in the literature have used various combinations of image, spatial and text features in order to understand and extract information from structurally rich documents such as forms [18, 57, 12], tables [44, 56, 24], receipts [27, 26] and invoices [35, 42, 37].”
• PubLayNet: Largest Dataset Ever for Document Layout Analysis (2019, methodology): “The fine tuned F-RCNN model achieves the state-of-the-art performance reported in [6], where the F-RCNN model was fine tuned with 1600 samples from a pre-trained object detection model.”
• Image-based table recognition: data, model, and evaluation (2019, methodology): “ion [23]–[25]. In addition, deep neural networks for object detection, such as Faster-RCNN [26], Mask-RCNN [27], and YOLO [28] have been exploited for table detection and row/column segmentation [7], [29]–[31]. Furthermore, graph neural networks are used for table detection and recognition by encodi”
• LayoutLM: Pre-training of Text and Layout for Document Image Understanding (2019, methodology): “After that, [21, 24, 29] also leveraged more advanced Faster R-CNN model [19] or Mask R-CNN model [9] to further improve the accuracy of document layout analysis.”
• Invoice Haystack: Benchmarking Document Retrieval and Visual Question Answering Under Strong Visual Homogeneity (2026, unknown): “Document AI has evolved from modular pipelines combining OCR [3,62], layout analysis [59, 77], and NLP models [18,45] toward unified end-to-end architectures.”