Abstract: A method and apparatus for processing an image, a device and a storage medium are provided. An implementation of the method includes: acquiring a template image, the template image including at least one region of interest; determining a first feature map corresponding to each region of interest in the template image; acquiring a target image; determining a second feature map of the target image; and determining at least one region of interest in the target image according to the first feature map and the second feature map.

Abstract: There is provided an image-based information extraction model, method, and apparatus, a device, and a storage medium, which relates to the field of artificial intelligence (AI) technologies, specifically to fields of deep learning, image processing, computer vision technologies, and is applicable to optical character recognition (OCR) and other scenarios. A specific implementation solution involves: acquiring a to-be-extracted first image and a category of to-be-extracted information; and inputting the first image and the category into a pre-trained information extraction model to perform information extraction on the first image to obtain text information corresponding to the category.

Abstract: A method for visual question answering, a computer device implementing the method and a medium for storing instructions on performing the method are provided. The method includes: acquiring an input image and an input question; constructing a visual graph based on the input image, wherein the visual graph comprises a first node feature and a first edge feature; constructing a question graph based on the input question, wherein the question graph comprises a second node feature and a second edge feature; performing a multimodal fusion on the visual graph and the question graph to obtain an updated visual graph and an updated question graph; determining a question feature based on the input question; determining a fusion feature based on the updated visual graph, the updated question graph and the question feature; and generating a predicted answer for the input image and the input question.

Abstract: The present disclosure provides a method for visual question answering, which relates to a field of computer vision and natural language processing. The method includes: acquiring an input image and an input question; constructing a Visual Graph based on the input image, wherein the Visual Graph comprises a Node Feature and an Edge Feature; updating the Node Feature by using the Node Feature and the Edge Feature to obtain an updated Visual Graph; determining a question feature based on the input question; fusing the updated Visual Graph and the question feature to obtain a fused feature; and generating a predicted answer for the input image and the input question based on the fused feature. The present disclosure further provides an apparatus for visual question answering, a computer device and a non-transitory computer-readable storage medium.

Abstract: Embodiments of the present disclosure provide a method and apparatus for correcting a distorted document image, where the method for correcting a distorted document image includes: obtaining a distorted document image; and inputting the distorted document image into a correction model, and obtaining a corrected image corresponding to the distorted document image; where the correction model is a model obtained by training with a set of image samples as inputs and a corrected image corresponding to each image sample in the set of image samples as an output, and the image samples are distorted. By inputting the distorted document image to be corrected into the correction model, the corrected image corresponding to the distorted document image can be obtained through the correction model, which realizes document image correction end-to-end, improves accuracy of the document image correction, and extends application scenarios of the document image correction.

Abstract: A method of processing a task, an electronic device, and a storage medium are provided, which relate to a field of artificial intelligence, in particular to fields of deep learning and computer vision, and may be applied to OCR optical character recognition and other scenarios. The method includes: parsing labeled data to be processed according to a task type identification, to obtain task labeled data, a tag information of the task labeled data is matched with the task type identification, and the task labeled data includes first task labeled data and second task labeled data; training a model using the first task labeled data, to obtain candidate models, the model is determined according to the task type identification; and determining a target model from the candidate models according to a performance evaluation result obtained by performing performance evaluation on the plurality of candidate models using the second task labeled data.

Abstract: A text extraction method and a text extraction model training method are provided. The present disclosure relates to the technical field of artificial intelligence, in particular to the technical field of computer vision. An implementation of the method comprises: obtaining a visual encoding feature of a to-be-detected image; extracting a plurality of sets of multimodal features from the to-be-detected image, wherein each set of multimodal features includes position information of one detection frame extracted from the to-be-detected image, a detection feature in the detection frame and first text information in the detection frame; and obtaining second text information matched with a to-be-extracted attribute based on the visual encoding feature, the to-be-extracted attribute and the plurality of sets of multimodal features, wherein the to-be-extracted attribute is an attribute of text information needing to be extracted.

Abstract: A method and a platform of generating a document, an electronic device, and a storage medium are provided, which relate to a field of an artificial intelligence technology, in particular to fields of computer vision and deep learning technologies, and may be applied to a text recognition scenario and other scenarios. The method includes: performing a category recognition on a document picture to obtain a target category result; determining a target structured model matched with the target category result; and performing, by using the target structured model, a structure recognition on the document picture to obtain a structure recognition result, so as to generate an electronic document based on the structure recognition result, wherein the structure recognition result includes a field attribute recognition result and a field position recognition result.

Abstract: A method for training a model includes: obtaining a scene image, second actual characters in the scene image and a second construct image; obtaining first features and first recognition characters of characters obtained by performing character recognition on the scene image using the model to be trained; obtaining second features of characters obtained by performing character recognition on the second construct image using the training auxiliary model; and obtaining a character recognition model by adjusting model parameters of the model to be trained based on the first recognition characters, the second actual characters, the first features and the second features.

Abstract: A method for training a text positioning model includes: obtaining a sample image, where the sample image contains a sample text to be positioned and a text marking box for the sample text; inputting the sample image into a text positioning model to be trained to position the sample text, and outputting a prediction text box for the sample image; obtaining a sample prior anchor box corresponding to the sample image; and adjusting model parameters of the text positioning model based on the sample prior anchor box, the text marking box and the prediction text box, and continuing training the adjusted text positioning model based on a next sample image until model training is completed, to generate a target text positioning model.

Abstract: The present disclosure discloses an image processing method, an electronic device and a storage medium, and relates to the field of artificial intelligence technologies, and particularly to the fields of computer vision technologies, deep learning technologies, or the like. The image processing method includes: acquiring a multi-modal feature of each of at least one text region in an image, the multi-modal feature including features in plural dimensions; performing a global attention processing operation on the multi-modal feature of each text region to obtain a global attention feature of each text region; determining a category of each text region based on the global attention feature of each text region; and constructing structured information based on text content and the category of each text region.

Abstract: Provided are a method and apparatus for extracting information about a negotiable instrument, an electronic device and a storage medium. The method includes inputting a to-be-recognized negotiable instrument into a pretrained deep learning network and obtaining a visual image corresponding to the to-be-recognized negotiable instrument through the deep learning network; matching the visual image corresponding to the to-be-recognized negotiable instrument with a visual image corresponding to each negotiable-instrument template in a preconstructed base template library; and in response to the visual image corresponding to the to-be-recognized negotiable instrument successfully matching a visual image corresponding to one negotiable-instrument template in the base template library, extracting structured information of the to-be-recognized negotiable instrument by using the negotiable-instrument template.

Abstract: The disclosure discloses a method for character recognition, an electronic device, and a storage medium. The technical solution includes: obtaining a test sample image and a test sample character both corresponding to a test task; performing fine-tuning on a trained meta-learning model based on the test sample image and the test sample character to obtain a test task model; obtaining a test image corresponding to the test task; and generating a test character corresponding to the test image by inputting the test image into the test task model.

Abstract: The present disclosure provides a method for visual question answering, which relates to a field of computer vision and natural language processing. The method includes: acquiring an input image and an input question; constructing a Visual Graph based on the input image, wherein the Visual Graph comprises a Node Feature and an Edge Feature; updating the Node Feature by using the Node Feature and the Edge Feature to obtain an updated Visual Graph; determining a question feature based on the input question; fusing the updated Visual Graph and the question feature to obtain a fused feature; and generating a predicted answer for the input image and the input question based on the fused feature. The present disclosure further provides an apparatus for visual question answering, a computer device and a non-transitory computer-readable storage medium.

Abstract: The present disclosure provides a method for visual question answering. The method includes: acquiring an input image and an input question; constructing a visual graph based on the input image, wherein the visual graph comprises a first node feature and a first edge feature; constructing a question graph based on the input question, wherein the question graph comprises a second node feature and a second edge feature; performing a multimodal fusion on the visual graph and the question graph to obtain an updated visual graph and an updated question graph; determining a question feature based on the input question; determining a fusion feature based on the updated visual graph, the updated question graph and the question feature; and generating a predicted answer for the input image and the input question. The present disclosure further provides an apparatus for visual question answering, a computer device and a medium.

Abstract: A method and apparatus for processing an image, a device and a storage medium are provided. An implementation of the method includes: acquiring a template image, the template image including at least one region of interest; determining a first feature map corresponding to each region of interest in the template image; acquiring a target image; determining a second feature map of the target image; and determining at least one region of interest in the target image according to the first feature map and the second feature map.

Abstract: The present disclosure discloses a method, apparatus and device for recognizing a bill, and a storage medium. The method comprises: acquiring a bill image; inputting the bill image into a feature extraction network layer of a pre-trained bill recognition model, to obtain a bill key field feature map and a bill key field value feature map of the bill image; inputting the bill key field feature map into a first head network layer of the bill recognition model, to obtain a bill key field; processing the bill key field value feature map by a second head network layer of the bill recognition model, to obtain a bill key field value, the feature extraction network layer being respectively connected with the first head network layer and the second head network layer; and generating structured information of the bill image based on the bill key field and the bill key field value.

Abstract: The present application discloses an image questioning and answering method, apparatus, device and storage medium, relating to the technical field of image processing, computer vision, deep learning and natural language processing. The specific implementation solution is as follows: constructing a question graph with a topological structure and extracting a question feature of a query sentence, according to the query sentence; constructing a visual graph with a topological structure and a text graph with a topological structure according to a target image corresponding to the query sentence; performing fusion on the visual graph, the text graph and the question graph by using a fusion model, to obtain a final fusion graph; and determining reply information of the query sentence according to a reasoning feature extracted from the final fusion graph and the question feature.

Abstract: Embodiments of the present disclosure provide a method and apparatus for correcting a distorted document image, where the method for correcting a distorted document image includes: obtaining a distorted document image; and inputting the distorted document image into a correction model, and obtaining a corrected image corresponding to the distorted document image; where the correction model is a model obtained by training with a set of image samples as inputs and a corrected image corresponding to each image sample in the set of image samples as an output, and the image samples are distorted. By inputting the distorted document image to be corrected into the correction model, the corrected image corresponding to the distorted document image can be obtained through the correction model, which realizes document image correction end-to-end, improves accuracy of the document image correction, and extends application scenarios of the document image correction.