There are errors in the first paragraph of the " Predicted undercover cropland " section of the Results. " Hectares per pixel " should read " m 2 per pixel. " There are errors in Fig 4 and in its caption. Please see the complete, correct Fig 4 here. There are errors in the caption for S5 Fig. Please view the correct S5 Fig. caption below. Copyright: © 2015 Ayanu et al. This is an open access ar...

Visual information is quite important for the task of video captioning. However, in the video, there are a lot of uncorrelated content, which may cause interference to generate a correct caption. Based on this point, we attempt to exploit the visual features which are most correlated to the caption. In this paper, a Multi-level Attention Model based Recurrent Neural Network (MAM-RNN) is propose...

There is considerable interest in the task of automatically generating image captions. However, evaluation is challenging. Existing automatic evaluation metrics are primarily sensitive to n-gram overlap, which is neither necessary nor sufficient for the task of simulating human judgment. We hypothesize that semantic propositional content is an important component of human caption evaluation, an...

This paper presents an overview of the ImageCLEF 2017 caption tasks on the analysis of images from the biomedical literature. Two subtasks were proposed to the participants: a concept detection task and caption prediction task, both using only images as input. The two subtasks tackle the problem of providing image interpretation by extracting concepts and predicting a caption based on the visua...

Accessing images online is often difficult for users with vision impairments. This population relies on text descriptions of images that vary based on website authors’ accessibility practices. Where one author might provide a descriptive caption for an image, another might provide no caption for the same image, leading to inconsistent experiences. In this work, we present the Caption Crawler sy...

The OLIVE project aims the development of a multilingual indexing tool for broadcast material based on speech recognition, which automatically produces indexes from the sound track of a program (television or radio). Such a tool allows multimedia archives to be searched by keywords and corresponding fragments to be retrieved. This paper gives a report on the alignment module, which is one of th...

The automatic extraction and reading of news captions and annotations can be of great help locating topics of interest in digital news video archives. To achieve this goal, we present a technique, called Video OCR, which detects, extracts, and reads text areas in digital video data. In this paper, we address problems, describe the method by which Video OCR operates, and suggest applications for...

Closed captioning dramatically improves deaf people's enjoyment of television shows, and appears to augment the auditory signal for people with some degree of hearing impairment. However, reports from people with mild to severe hearing loss suggest that when there is a delay between the audio track and the caption, perceivers are confused unless they turn down the volume. These effects have not...

Correction After publication of the original article [1] it was noted that the caption of Table two was incorrect. This caption should read “Distribution of ovarian follicles depending on the type (healthy, transitional, and atretic). Small superscript letters a and b indicate significant differences in the respective ovarian follicle numbers within the various types of follicles (P < 0.05) as ...

Automatically generating text to accompany information graphics Mary Ellen Foster Master of Science Graduate Department of Computer Science University of Toronto 1999 Generally, when quantitative information is to be presented, some form of graphical presentation is used, often with a textual caption to ensure that the audience notices particular aspects of the data. This thesis presents the pr...