Figure 1 - uploaded by Rajeev Srivastava
Content may be subject to copyright.
Contexts in source publication
Context 1
... are many advances in this field as large datasets like MSCOCO, Flickr30k etc. are available to train the model more efficiently. The basic model (as shown in figure 1.) for image captioning works like, first gather the features of an image and given captions in the dataset, and based on features provide a suitable annotation to that image. In figure 1, it shows a man lying on the table and a dog sitting near him. ...
Context 2
... basic model (as shown in figure 1.) for image captioning works like, first gather the features of an image and given captions in the dataset, and based on features provide a suitable annotation to that image. In figure 1, it shows a man lying on the table and a dog sitting near him. As this is a sample input image firstly its features based on colour, objects, boundaries, texture etc. is extracted and also features of given captions, then based on its attributes a common representation is produced. ...
Similar publications
Citations
... In the training network the system have explored the effectiveness and efficiency of shuffle sampling with cross-validation and find an outstanding effect in medical images classification. The purpose of this work [12] was to provide an effective and accurate image description of an unknown image by using deep learning methods. The authors have proposed a novel generative robust model that trains a Deep Neural Network to learn about features in images after extracting information about the content of images, for that the used the novel combination of CNN and LSTM. ...
Report generated by radiologists using chest X-rays has significant potential to improve clinical patient care. Diagnosing chest X-rays can be challenging and sometimes more difficult than diagnosis via chest CT imaging. Lack of availability of well-trained radiologists and delayed report generation results in long waiting time which indeed leads to delayed medical assistance. As the interpretation of chest X-rays is time consuming, we propose a system that assist the medical professionals in doing the same job within minimum time. In this work, the proposed system can detect heart and pulmonary diseases such as pneumonia and enlargement of heart from chest radiographs at a level equal to the knowledge and skill set of practicing radiologist. The system employs artificial intelligence techniques. Using such techniques improves a patient's overall treatment with less hospital time and can also be used to deliver high-quality and cost-effective care. Its focus is to produce accurate disease profiles to power downstream tasks such as diagnosis and care providing.
... Deep convolutional neural networks have produced state-of-the-art results on various benchmarks [1], [2]. Many Researches in the field of convolutional neural networks, practically proved that deeper networks have higher accuracy. ...
... The different approaches for image caption generation can be either based on retrievable or constructive approaches as pointed out in [9], [10], [13], [14]. This taxonomy is clearly depicted in Fig. 2. ...
The automatic generation of correct syntaxial and semantical image captions is an essential problem in Artificial Intelligence. The existence of large image caption copra such as Flickr and MS COCO have contributed to the advance of image captioning in English. However, it is still behind for Arabic given the scarcity of image caption corpus for the Arabic language. In this work, an Arabic version that is a part of the Flickr and MS COCO caption dataset is built. Moreover, a generative merge model for Arabic image captioning based on a deep RNN-LSTM and CNN model is developed. The results of the experiments are promising and suggest that the merge model can achieve excellent results for Arabic image captioning if a larger corpus is used.
