Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 56 for “"Captions"”.

  1. Using the visual denotations of image captions for semantic inference

    … we create an image caption corpus consisting of captions and images depicting everyday actions. This corpus has a number of useful features that would assist in investigating everyday events and the different ways in which they can be described. We use the captions in the corpus as the starting …

    uiuc Repository record for Using the visual denotations of image captions for semantic inference (opens in a new tab)

  2. Efficient Monte Carlo simulations of pricing captions using Libor market models

    … a scalar variable and vector variable. Moreover, captions are second order with respect to the discount bonds in that they are options on caps (which are also options on bonds). These reasons make it of particular interest to study efficient numerical solutions to price captions. Monte Carlo …

    cape-town Repository record for Efficient Monte Carlo simulations of pricing captions using Libor market models (opens in a new tab)

  3. Text-Free Audio Captions of Short Videos from Latent Space Representation

    … than image data and analyze the resulting speech captions. We conduct experiments on the Wav2Vec2 and HuBERT Automatic Speech Recognition models, and identify which works best with synthesized speech.

    mit Repository record for Text-Free Audio Captions of Short Videos from Latent Space Representation (opens in a new tab)

  4. THE ACQUISITION OF PHRASAL VERBS THROUGH ENHANCED AUDIOVISUAL CAPTIONS. IMPLICATIONS FOR THE DEVELOPMENT OF A SUBTITLING TOOL FOR EFL LEARNERS

    … verbs. Preliminary results suggest that coloured captions may significantly enhance learners’ ability to notice phrasal verbs, although further research is required to determine the impact on retention. The second component involves the creation of a software tool, “SubTeachMe,” designed to assist …

    milano Repository record for THE ACQUISITION OF PHRASAL VERBS THROUGH ENHANCED AUDIOVISUAL CAPTIONS. IMPLICATIONS FOR THE DEVELOPMENT OF A SUBTITLING TOOL FOR EFL LEARNERS (opens in a new tab)

  5. Attitudes, behaviors, and learning outcomes from using classtranscribe, a UDL-featured video-based online learning platform with learnersourced text-searchable captions

    … course. Users could edit the machine-generated captions in a crowdsourcing way. The system logged student viewing, searching, and editing behaviors as fine-grained web browser interaction events including full-screen-switching, loss-of-focus, caption searching and editing events, and …

    uiuc Repository record for Attitudes, behaviors, and learning outcomes from using classtranscribe, a UDL-featured video-based online learning platform with learnersourced text-searchable captions (opens in a new tab)

  6. Automatic Image Captioning with Style

    … has focused on generating purely descriptive captions; I focus on generating visually relevant captions with a distinct linguistic style. Captions with style have the potential to ease communication and add a new layer of personalisation. First, I consider naming variations in image captions, …

    aus-cath Repository record for Automatic Image Captioning with Style (opens in a new tab)

  7. Automatic Image Captioning with Style

    … has focused on generating purely descriptive captions; I focus on generating visually relevant captions with a distinct linguistic style. Captions with style have the potential to ease communication and add a new layer of personalisation. First, I consider naming variations in image captions, …

    anu Repository record for Automatic Image Captioning with Style (opens in a new tab)

  8. VisText: A Benchmark for Semantically Rich Chart Captioning

    Captions that describe or explain charts help improve recall and comprehension of the depicted data and provide a more accessible medium for people with visual disabilities. However, current approaches for automatically generating such captions struggle to articulate the perceptual or cognitive …

    mit Repository record for VisText: A Benchmark for Semantically Rich Chart Captioning (opens in a new tab)

  9. Image captioning using compositional sentiments

    … thesis presents a method to generate emotional captions of images. An adequate caption should precisely describe the contents in an image. While humans can readily identify the most emotionally salient aspects of an image, many captioning models have difficulties in detecting and generating …

    uiuc Repository record for Image captioning using compositional sentiments (opens in a new tab)

  10. Using Sports Videos to Showcase Exciting Content to Viewers

    … as well as utilize NLP techniques to generate captions for such videos. We create pipelines for the extraction of highlight clips using an audio heuristic for which we obtain transcriptions and, using a defined schema for exciting captions, fine-tune pre-trained transformer models to extract …

    mit Repository record for Using Sports Videos to Showcase Exciting Content to Viewers (opens in a new tab)

  11. The Unconscious Influence of Mortality Salience on Younger and Older Adults

    … neutral and emotional (positive and negative) captions paired with neutral pictures. A defense was operationalized as higher suitability ratings and faster reaction times to the positive captions, as well as lower suitability ratings and slower reaction times to the negative captions. Based on …

    wku-diss Repository record for The Unconscious Influence of Mortality Salience on Younger and Older Adults (opens in a new tab)

  12. Understanding what a captioning network doesn't know

    … on the image encoding by observing the generated captions, which are inherently understandable by humans and thus convenient and informative to use. We also generate and analyze captions of images modified by inserting small sub-images of single, human-interpretable concepts. These modifications …

    mit Repository record for Understanding what a captioning network doesn't know (opens in a new tab)

  13. Learning multiple solutions to computer vision problems

    … be described in many ways, therefore multiple captions are correct. We show that convolutional networks can be used to model the language (or output caption), which previously was done using recurrent networks only. We find that convolutional networks produce more entropy in their posteriors …

    uiuc Repository record for Learning multiple solutions to computer vision problems (opens in a new tab)

  14. Exposing and correcting the gender bias in image captioning datasets and models

    … arising from the gender and gives good quality captions. This model gives comparable results to a gendered model even when evaluating against a dataset that possesses similar bias as the training data. Interestingly, the predictions by this model on images without humans, are also visibly …

    uiuc Repository record for Exposing and correcting the gender bias in image captioning datasets and models (opens in a new tab)

  15. You Had Me at Helen: The Name Letter Effect in Judgments of Humor

    … that participants would exhibit biases toward captions submitted by writers with whom they shared a first initial letter, and additionally, their gender. A name letter effect was found in participants' judgments of humor and on the NLT. Shared gender with a caption writer--when coupled with a …

    loyola-thes Repository record for You Had Me at Helen: The Name Letter Effect in Judgments of Humor (opens in a new tab)

  16. Towards multilingual lexicon discovery from visually grounded speech

    … model to map images and their spoken audio captions in both English and Hindi to a shared, multimodal embedding space. Next, we use this model to segment and cluster regions of the spoken captions which approximately correspond to words. Then, we exploit between-cluster similarities in the …

    mit Repository record for Towards multilingual lexicon discovery from visually grounded speech (opens in a new tab)

  17. Towards abstractive captioning of infographics

    … spatial arrangement, and subsequently generate captions for given infographics automatically. To shine light at the reasoning behind the captions being generated, we develop a graphical user interface that helps visualize the portions of a document being used when generating specific parts of a …

    mit Repository record for Towards abstractive captioning of infographics (opens in a new tab)

  18. The Effects Of Closed-Captioned Television On The Oral Reading Fluency Of Low Socioeconomic 2nd Grade Students

    … in viewing the Arthur video series with captions, while the control group participated in viewing the same videos without captions. Pretests and posttests were given using Reading Curriculum Based Measures from Aimsweb. The results of the ANCOVA shono statistical differences between the …

    mississippi Repository record for The Effects Of Closed-Captioned Television On The Oral Reading Fluency Of Low Socioeconomic 2nd Grade Students (opens in a new tab)

  19. Kukataa: An Afrocentric Exploration of Nongovernmental Organization Refusal in the Context of Female Genital Cutting in Tanzania

    … numerical statistics and one to two-lined captions that do not effectively capture the full humanity of the Black girls and women they are describing. The numerical statistics and pictorial captions provide myopic and ahistorical interpretations of African people and paint Africa as a …

    temple Repository record for Kukataa: An Afrocentric Exploration of Nongovernmental Organization Refusal in the Context of Female Genital Cutting in Tanzania (opens in a new tab)

  20. Evaluation of Speech And Text-Based Indexing For Classroom Lecture Videos

    … lecture video segmentation using speech text/captions. The purpose of this thesis is to utilize the spoken text of a lecture video to assign index points using an underlying text-based indexing algorithm. To achieve this goal, a set of twenty-five lecture videos was taken from various …

    houston Repository record for Evaluation of Speech And Text-Based Indexing For Classroom Lecture Videos (opens in a new tab)

Page 1 of 3