Abstract: The present disclosure discloses a data processing circuit, a data processing method, and related products. The data processing circuit is implemented as a computing apparatus included in a combined processing apparatus. The combined processing apparatus further includes an interface apparatus and other processing apparatus. The computing apparatus interacts with other processing apparatus to jointly complete a user specified computation operation. The combined processing apparatus further includes a storage apparatus. The storage apparatus is connected to the computing apparatus and other processing apparatus, respectively. The storage apparatus is used to store data of the computing apparatus and other processing apparatus. The solution disclosed in the present disclosure provides hardware implementation for operations related to structured sparsity, which can simplify processing and improve processing efficiency of a machine.

Abstract: Embodiments of a multimodal question answering (mQA) system are presented to answer a question about the content of an image. In embodiments, the model comprises four components: a Long Short-Term Memory (LSTM) component to extract the question representation; a Convolutional Neural Network (CNN) component to extract the visual representation; an LSTM component for storing the linguistic context in an answer, and a fusing component to combine the information from the first three components and generate the answer. A Freestyle Multilingual Image Question Answering (FM-IQA) dataset was constructed to train and evaluate embodiments of the mQA model. The quality of the generated answers of the mQA model on this dataset is evaluated by human judges through a Turing Test.

Abstract: The present disclosure provides an image recognition method and apparatus, a device and a non-volatile computer storage medium. In embodiments of the present disclosure, it is feasible to obtain the to-be-recognized image of the designated space, then perform image segmentation processing for the to-be-recognized image, to obtain at least one area image of the designated space, and then perform image matching processing for each area image in said at least one area image, to obtain a reference image corresponding to said each area image, so that it is possible to perform recognition processing for said each area image according to image information of the reference image corresponding to said each area image to obtain article information of said each area image. The so doing does not require manual participation and exhibits simple operations and a high rate of correctness, and thereby improves the recognition efficiency and reliability.

Abstract: The present disclosure provides an image recognition method and apparatus, a device and a non-volatile computer storage medium. In embodiments of the present disclosure, it is feasible to obtain the to-be-recognized image of the designated space, then perform image segmentation processing for the to-be-recognized image, to obtain at least one area image of the designated space, and then perform image matching processing for each area image in said at least one area image, to obtain a reference image corresponding to said each area image, so that it is possible to perform recognition processing for said each area image according to image information of the reference image corresponding to said each area image to obtain article information of said each area image. The so doing does not require manual participation and exhibits simple operations and a high rate of correctness, and thereby improves the recognition efficiency and reliability.

Abstract: A method and an apparatus for photograph classification and storage by matching an image characteristic of a first photograph with an image characteristic of a second photograph in a directory, and calculating the similarity between the first photograph and the second photograph and presenting the first photograph and the second photograph in a front-end page as located in a same subdirectory when the similarity between the first photograph and the second photograph is larger than a preset threshold. The beneficial effects being that a number of similar images in a user's photo album can be sorted efficiently and placed into the same directory to facilitate the user's management and viewing of the photographs.

Abstract: A method and an apparatus for photograph classification and storage by matching an image characteristic of a first photograph with an image characteristic of a second photograph in a directory, and calculating the similarity between the first photograph and the second photograph and presenting the first photograph and the second photograph in a front-end page as located in a same subdirectory when the similarity between the first photograph and the second photograph is larger than a preset threshold. The beneficial effects being that a number of similar images in a user's photo album can be sorted efficiently and placed into the same directory to facilitate the user's management and viewing of the photographs.

Abstract: Embodiments of a multimodal question answering (mQA) system are presented to answer a question about the content of an image. In embodiments, the model comprises four components: a Long Short-Term Memory (LSTM) component to extract the question representation; a Convolutional Neural Network (CNN) component to extract the visual representation; an LSTM component for storing the linguistic context in an answer, and a fusing component to combine the information from the first three components and generate the answer. A Freestyle Multilingual Image Question Answering (FM-IQA) dataset was constructed to train and evaluate embodiments of the mQA model. The quality of the generated answers of the mQA model on this dataset is evaluated by human judges through a Turing Test.