191 to 200 of 1,643 Results
Feb 28, 2025 -
Code for Improving Video Caption Accuracy with LLMs
Jupyter Notebook - 7.8 KB -
MD5: 58be18532e56dbbe2ea70f2dd564f3f8
|
Feb 28, 2025 -
Code for Improving Video Caption Accuracy with LLMs
Jupyter Notebook - 4.8 KB -
MD5: 0d371e20b73fe73d51366becd673c5ca
|
Feb 28, 2025 -
Code for Improving Video Caption Accuracy with LLMs
Plain Text - 1.0 KB -
MD5: aadc2e2eeb8a75df7a5843133be16dd6
|
Feb 28, 2025 -
Code for Improving Video Caption Accuracy with LLMs
Jupyter Notebook - 4.4 KB -
MD5: 1e3fe7a495cd36dc8328ee1c464d4b3c
|
Feb 28, 2025 -
Code for Improving Video Caption Accuracy with LLMs
Jupyter Notebook - 7.4 KB -
MD5: 27167e9740456c66174d9070e08c35f6
|
Feb 28, 2025 -
Code for Improving Video Caption Accuracy with LLMs
Markdown Text - 3.8 KB -
MD5: d9c31ba29a0a95e82ec2fc6602db412f
|
Feb 28, 2025 -
Code for Improving Video Caption Accuracy with LLMs
Jupyter Notebook - 6.2 KB -
MD5: cd98c305f14bf313951e8a011ba587b9
|
Feb 28, 2025 -
Code for Improving Video Caption Accuracy with LLMs
Jupyter Notebook - 83.9 KB -
MD5: aa3156de5a3212699671b753b28c33d8
|
Feb 28, 2025 - Analytic Computing
Fathallah, Nadeen; Staab, Steffen, 2025, "Code for Caption Crowd (IKILeUS)", https://doi.org/10.18419/DARUS-4775, DaRUS, V1, UNF:6:e9mxpfNAwwwZlt8Uc4I+mQ== [fileUNF]
CaptionCrowd is an interactive platform developed within the IKILeUS project at the University of Stuttgart to improve video caption accuracy for the Deaf and Hard of Hearing (DHH) community. While automatic captions provide some accessibility, they often contain errors in grammar, homophones, and domain-specific terminology, making comprehension c... |
Feb 28, 2025 -
Code for Caption Crowd (IKILeUS)
Javascript Code - 1.7 KB -
MD5: b15cc8ceeec5970d2cbf6fa7329d998e
|