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 170 for “"CAPTION"”.
-
Textual entailment from image caption denotations
… by building representations from grounded image captions. This allows us to use descriptions of the world to learn connections that would be difficult to identify in text-based corpora. In particular, we explore novel approaches to entailment that capture everyday world knowledge missing from …
-
VIDEO SCENE DETECTION USING CLOSED CAPTION TEXT
Issues in Automatic Video Biography Editing are similar to those in Video Scene Detection and Topic Detection and Tracking (TDT). The techniques of Video Scene Detection and TDT can be applied to interviews to reduce the time necessary to edit a video biography. The system has attacked the problems …
-
Multimodal Representation Learning for Face Understanding: From Caption Supervision to Foundation Model Adaptation
… natural language supervision, large-scale face-caption pre-training, and parameter-efficient foundation model adaptation. It hypothesizes that textual supervision provides complementary semantic cues that improve the robustness, interpretability, and generalizability of facial representations …
-
A caption-based natural-language interface handling descriptive captions for a multimedia database system
… the grammar structure of descriptive English captions on multimedia data. The research was composed of three phases. The first phase was to investigate the grammar structure of example descriptive captions from a variety of subject domains. The second phase was to develop a set of domain …
-
Investigating the Importance of Non-Textual Caption Properties From Deaf and Hard of Hearing Viewers' Perspective
Deaf and hard-of-hearing (DHH) viewers rely on captioning to perceive auditory information while watching live television programming. Captioning ensures that viewers can receive textual and non-textual information that is crucial to comprehend the content of the video. However, no research has …
-
The effects of a caption-viewing strategy on hearing students viewing captioned programs in a postsecondary setting
… purpose of this study was to determine whether a caption-viewing intervention presented with challenging instructional television program content can benefit hearing students' comprehension performance and improve attitudes toward captioning. A secondary purpose was to determine whether a long …
-
Towards an Automatic Caption Quality Assessment Model Reflecting the Subjective Views of Deaf, and Hard of Hearing Audiences
Closed Captioning (CC) was designed to serve Deaf and Hard of Hearing viewers, but the quality of CC has been assessed without much inclusion of these primary consumer groups. Currently, caption quality is mostly measured using arithmetic counts based on “errors” between the original spoken words …
-
The effects of partial captions on Korean EFL learners' listening comprehension
… authentic video clips with three modes of captions, partial-, full-, and no-caption modes. The participants, divided into three groups (aboveintermediate, intermediate, and below intermediate) based on their English proficiency, watched six video clips with different caption modes. Prior to …
-
An analysis of the portrayal of immigration in the Spanish press with a particular focus on compassion fatigue and the impact of the image and the caption
… reviews the photographic techniques and the captions used to portray immigration related events and argues that the lack of interest in immigration is a result of Susan Sontag’s theory of compassion fatigue. The negative stigma attached to immigration in Almeria is a consequence of the …
-
Advanced AI for Histopathological Whole Slide Image Classification and Captioning
… diagnosis and treatment. Classification and captioning Whole Slide Images (WSIs) for pathological analysis is an essential but not extensively explored aspect of computer-aided pathological diagnosis. Challenges arise from insufficient datasets and the effectiveness of model training. …
-
Developing Informative and Faithful Image Captioning Systems with Compositional Generalizability
Image captioning systems aim to generate visually grounded descriptions for given images. It has been an active multimodal research problem in artificial intelligence---humans are able to understand the content of images and describe them with natural language, and we expect computers to possess …
-
Taming Data and Transformers for Audio Generation
… task due to data scarcity and often insufficient caption quality, making it difficult to employ large-scale generative models for the task. In this work, we tackle this problem by introducing two new models. First, we propose AutoCap, a high-quality and efficient automatic audio captioning model. …
-
Within-Channel Redundancy Versus Between-Channel Redundancy in Instructional Material and Its Association with Amount Learned
… redundancy! audio—video, audio—video—caption, and audio-caption with one form of within-channel redundancy: video-caption. These comparisons were designed to demonstrate which form of redundancy had a higher association with recall of information. The subjects were administered the …
-
Automatic Image Captioning with Style
… and language. The problem of choice is image caption generation: automatically constructing natural language descriptions of image content. Previous research into image caption generation has focused on generating purely descriptive captions; I focus on generating visually relevant captions …
-
You Had Me at Helen: The Name Letter Effect in Judgments of Humor
… as "mock" judges in a simulated cartoon caption contest and evaluated writers' caption submissions for two cartoons. It was hypothesized that participants would exhibit biases toward captions submitted by writers with whom they shared a first initial letter, and additionally, their …
-
Post-Hoc Alignment for Theory-Aware Music Retrieval: Evaluating the Impact of Theory-Enriched Semantic Features
This thesis investigates whether enriching text captions with music-theoretic and affective information improves music-text retrieval through post-hoc alignment. Lightweight MLP adapters are trained to project frozen pretrained audio and text embeddings into a shared space. Four caption variants …
Page 1 of 9