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 9 of 9 for “"Video Search"”.
-
A DOMAIN-CENTRIC APPROACH TO DESIGNING USER INTERFACES OF VIDEO RETRIEVAL SYSTEMS
User- and task-centric efforts in video information retrieval (IR) research are needed because current experiments are showing few significant results. It is our belief that unsatisfactory results in video IR can be partially attributed to the overemphasis on technologically-driven approaches to …
-
Learning Audio-Video Language Representations
… speech data. Unlabeled multi-modal data, such as videos, are now increasingly available in many different languages and provide opportunities to scale speech technologies. In this thesis, we introduce models and datasets for learning visually grounded spoken language from raw audio in videos. We …
-
Grounding language in events
Broadcast video and virtual environments are just two of the growing number of domains in which language is embedded in multiple modalities of rich non-linguistic information. Applications for such multimodal domains are often based on traditional natural language processing techniques that ignore …
-
VideoTag: encouraging the effective tagging of internet videos through tagging games
The tags and descriptions entered by video owners in video sharing sites are typically inadequate for retrieval purposes, yet the majority of video search still uses this text. This problem is escalating due to the ease with which users can self-publish videos, generating masses that are poorly …
-
Characterizing Audio Events for Video Soundtrack Analysis
There is an entire emerging ecosystem of amateur video recordings on the internet today, in addition to the abundance of more professionally produced content. The ability to automatically scan and evaluate the content of these recordings would be very useful for search and indexing, especially as …
-
Attitudes, behaviors, and learning outcomes from using classtranscribe, a UDL-featured video-based online learning platform with learnersourced text-searchable captions
… a Universal Design for Learning (UDL) featured video-based online learning platform. ClassTranscribe provided accurate accessible transcriptions and captioning plus a custom text-searchable interface to rapidly find relevant video moments from the entire course. Users could edit the …
-
Recognising and localising human actions
Human action recognition in challenging video data is becoming an increasingly important research area. Given the growing number of cameras and robots pointing their lenses at humans, the need for automatic recognition of human actions arises, promising Google-style video search and automatic video …
-
Design, implementation and effectiveness of ClassTranscribe
ClassTranscribe is an accessible online video lecture platform designed with the principles of Universal Design for Learning enriched with Closed Captions produced in real-time using Artificial Intelligence and Crowd-Sourcing, and Searchability for efficient student-directed learning. It is an …
-
MOOC video: a video segment search engine for MOOCs
… Chengxiang Zhai, I have worked on building a search system for MOOC, which will give video results to users for the queries that they make. Whenever the user makes a search from the client, video results will be fetched from the server and displayed to the user. The user will also be pointed …