Abstract Urdu is morphologically rich language and lacks the resources available in English. While several studies on image captioning task English have been published, this among pioneer generative captioning. The study makes key contributions: (i) it presents a new dataset for captioning, (ii) different attention-based architectures language. These attention mechanisms are to language, as tho...

The task of associating images and videos with a natural language description has attracted a great amount of attention recently. The state-of-the-art results on some of the standard datasets have been pushed into the regime where it has become more and more difficult to make significant improvements. Instead of proposing new models, this work investigates performances that an oracle can obtain...

This study investigated the effects of captioned texts on second/foreign (L2) listening comprehension and vocabulary gains using a computer multimedia program. Additionally, it explored the caption ordering effect (i.e. captions displayed during the first or second listening), and the interaction of captioning order with the L2 proficiency level of language learners in listening comprehension a...

This project aims at generating captions for images using neural language models. There has been a substantial increase in number of proposed models for image captioning task since neural language models and convolutional neural networks(CNN) became popular. Our project has its base on one of such works, which uses a variant of Recurrent neural network coupled with a CNN. We intend to enhance t...

Remote sensing image captioning aims to describe the content of images using natural language. In contrast with images, scale, distribution, and number objects generally vary in remote making it hard capture global semantic information relationships between at different scales. this paper, order improve accuracy diversity captioning, a mask-guided Transformer network topic token is proposed. Mu...

With the growth of remote sensing images, un-derstanding image content automatically has attracted many researchers' interests in deep learning for image. Inspired from natural captioning, model with CNN-RNN as backbone and supplemented by attention been widely used captioning. However, it is inefficient current layer to simultaneously mine hidden foreground background perform feature interacti...

Quantitative modeling of human brain activity based on language representations has been actively studied in systems neuroscience. However, previous studies examined word-level representation, and little is known about whether we could recover structured sentences from brain activity. This study attempts to generate natural language descriptions of semantic contents from human brain activity ev...

We propose a novel extension of the encoder-decoder framework, called a review network. The review network is generic and can enhance any existing encoderdecoder model: in this paper, we consider RNN decoders with both CNN and RNN encoders. The review network performs a number of review steps with attention mechanism on the encoder hidden states, and outputs a thought vector after each review s...

This article describes the real-time speech recognition system for closed-captioning of TV ice-hockey commentaries. Automatic transcription of TV commentary accompanying an ice-hockey match is usually a hard task due to the spontaneous speech of a commentator put often into a very loud background noise created by the public, music, siren, drums, whistle, etc. Data for building this system was c...