and NPRM). More than five years have passed since the Commission sought comment on several important matters relating to the quality and implementation of closed captioning of video programming, and a variety of changes in the closed captioning landscape warrant a refresh of the record created in response to that proceeding. For example, the benchmarks for 100% captioning of nonexempt new Engli...

As a fine-grained video understanding task, dense video captioning involves first localizing events in a video and then generating captions for the identified events. We present the Joint Event Detection and Description Network (JEDDi-Net) that solves the dense captioning task in an end-to-end fashion. Our model continuously encodes the input video stream with three-dimensional convolutional la...

Automatic video captioning is challenging due to the complex interactions in dynamic real scenes. A comprehensive system would ultimately localize and track the objects, actions and interactions present in a video and generate a description that relies on temporal localization in order to ground the visual concepts. However, most existing automatic video captioning systems map from raw video da...

Generating natural language descriptions of images is an important capability for a robot or other visual-intelligence driven AI agent that may need to communicate with human users about what it is seeing. Such image captioning methods are typically trained by maximising the likelihood of ground-truth annotated caption given the image. While simple and easy to implement, this approach does not ...

This study aims to clarify the so-called ‘‘summarized captioning via computer assistance’’ in Japan. Summarized captioning [Youyaku-hikki] is an organizational activity that is planned and performed by volunteers. This activity is an essential service, particularly for people with hearing impairments. This study will first describe the general situation concerning PC-summarized captioning. Seco...

Attention mechanisms have attracted considerable interest in image captioning due to its powerful performance. However, existing methods use only visual content as attention and whether textual context can improve attention in image captioning remains unsolved. To explore this problem, we propose a novel attention mechanism, called textconditional attention, which allows the caption generator t...

Closed captioning to convey the speech of TV programs by text is becoming a useful means of providing information for elderly people and the hearing impaired, and real-time captioning of live programs is expanding yearly thanks to the use of speech recognition technology and special keyboards for high-speed input. This paper describes the current state of closed captioning, provides an overview...

This study analyses the possible use of automatic speech recognition (ASR) for the automatic captioning of TV programs. Captioning requires: (1) transcribing the spoken words and (2) determining the times at which the caption has to appear and disappear on the screen. These times have to match as closely as possible the corresponding times on the audio signal. Automatic speech recognition can b...

Although manual transcription and captioning can increase the accessibility of multimedia for deaf students it is rarely provided in educational contexts in the UK due to the cost and shortage of highly skilled and trained stenographers. Speech recognition has the potential to reduce the cost and increase the availability of captioning if it could satisfy accuracy and readability requirements. ...

Modern neural image captioning systems typically adopt the encoder-decoder framework consisting of two principal components: a convolutional neural network (CNN) for image feature extraction and a recurrent neural network (RNN) for caption generation. Inspired by the robustness analysis of CNN-based image classifiers to adversarial perturbations, we propose Show-and-Fool, a novel algorithm for ...